Not in the top 1,000 by GitHub stars
OSideMedia/higgsfield-ai-prompt-skill
Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an acting system, Cinema Studio 2.5/3.0/3.5, MCSLA, Soul ID consistency, Kling 3.0 Motion Control, the DISCIPLINE framework, and 18 templates.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-3d/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-acting/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-apps/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-assist/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-audio/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-camera/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-canvas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-character-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-cinema/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-content-factory/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-facs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-gpt-image-2/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-image-shots/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-marketing-studio/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-mixed-media/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-models/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-moodboard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-motion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-motion-design/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-pipeline/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-prompt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-recall/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-recipes/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-repurpose/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-scene-engine/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-seedance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-seedance-2-5/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-seedance-vfx/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-shotlist-director/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-soul/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-stack/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-style/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-troubleshoot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-vibe-motion/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
skills/higgsfield-workspaces/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6a6a5dd105d2 → 6a6a5dd105d2
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6a6a5dd105d2
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit 6a6a5dd105d285782dd6992692be4d8b3825ca13
git clone --filter=blob:none --no-checkout https://github.com/OSideMedia/higgsfield-ai-prompt-skill.git .hotskills/osidemedia-higgsfield-ai-prompt-skill && git -C .hotskills/osidemedia-higgsfield-ai-prompt-skill checkout --detach 6a6a5dd105d285782dd6992692be4d8b3825ca13
# Copy each selected skill directory from .hotskills/osidemedia-higgsfield-ai-prompt-skill into .claude/skills/<skill-name>/869GitHub stars
38stars in 7 days
36skills in this repository
14commits in 30 days
Heat
7.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- higgsfield
/ - higgsfield-3d
skills/higgsfield-3d - higgsfield-acting
skills/higgsfield-acting - higgsfield-apps
skills/higgsfield-apps - higgsfield-assist
skills/higgsfield-assist - higgsfield-audio
skills/higgsfield-audio - higgsfield-camera
skills/higgsfield-camera - higgsfield-canvas
skills/higgsfield-canvas - higgsfield-character-design
skills/higgsfield-character-design - higgsfield-cinema
skills/higgsfield-cinema - higgsfield-content-factory
skills/higgsfield-content-factory - higgsfield-facs
skills/higgsfield-facs - higgsfield-gpt-image-2
skills/higgsfield-gpt-image-2 - higgsfield-image-shots
skills/higgsfield-image-shots - higgsfield-marketing-studio
skills/higgsfield-marketing-studio - higgsfield-mixed-media
skills/higgsfield-mixed-media - higgsfield-models
skills/higgsfield-models - higgsfield-moodboard
skills/higgsfield-moodboard - higgsfield-motion
skills/higgsfield-motion - higgsfield-motion-design
skills/higgsfield-motion-design - higgsfield-pipeline
skills/higgsfield-pipeline - higgsfield-prompt
skills/higgsfield-prompt - higgsfield-recall
skills/higgsfield-recall - higgsfield-recipes
skills/higgsfield-recipes - higgsfield-repurpose
skills/higgsfield-repurpose - higgsfield-scene-engine
skills/higgsfield-scene-engine - higgsfield-seedance
skills/higgsfield-seedance - higgsfield-seedance-2-5
skills/higgsfield-seedance-2-5 - higgsfield-seedance-vfx
skills/higgsfield-seedance-vfx - higgsfield-shotlist-director
skills/higgsfield-shotlist-director - higgsfield-soul
skills/higgsfield-soul - higgsfield-stack
skills/higgsfield-stack - higgsfield-style
skills/higgsfield-style - higgsfield-troubleshoot
skills/higgsfield-troubleshoot - higgsfield-vibe-motion
skills/higgsfield-vibe-motion - higgsfield-workspaces
skills/higgsfield-workspaces
How it works
higgsfield
When your agent uses it
Writes and refines prompts for Higgsfield AI's video and image models, and picks the model, camera controls and motion presets for each shot. Use whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema Studio 2.5/3.0, Vibe Motion, troubleshooting failed generations, credit optimization, Photodump, or any mention of higgsfield.ai. Also trigger on generic "write me a video prompt" or "make me an AI video prompt" requests when Higgsfield is the user's configured platform.
What it loads into context
Frontmatter
256 tokensAlways available to the agent
SKILL.md
12,018 tokensWhen the skill is activated
Reference documents
327,625 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- HARD RULES — pre-delivery checklist
- What Is Higgsfield?
- Working Folders — file handling
- Handling a Request
- Generation Ledger — log every result
- @ Reference Rules
- Shared Resources
- Sub-Skills — open `skills/<name>/SKILL.md` yourself
Scripts executed separately
evals/run_evals.pyscripts/build_index.pyscripts/claims_lint.pyscripts/generate_user_guide.pyscripts/higgsfield_memory.pyscripts/preflight.pyscripts/refresh_specs.pyscripts/repo_walk.pyscripts/seedance_lint.pyscripts/snapshot_crosscheck.pyscripts/sub_skill_descriptions.pyscripts/sync_specs.pyscripts/user_guide_content.pyscripts/validate.pyscripts/validate_user_guide.pytests/conftest.pytests/test_build_index.pytests/test_claims_lint.pytests/test_commands.pytests/test_ledger.pytests/test_lint_rules.pytests/test_memory.pytests/test_memory_location.pytests/test_preflight.pytests/test_prompt_gates_wiring.pytests/test_refresh.pytests/test_repo_walk.pytests/test_routing.pytests/test_run_evals.pytests/test_snapshot_crosscheck.pytests/test_sync_specs.pytests/test_user_guide.pytests/test_validate.pytests/test_workflows.py
Files
.claude/commands/refresh-specs.mddoc5,816 bytes.claude/commands/release.mddoc3,825 bytes.claude/commands/validate.mddoc1,320 bytes.claude/rules/cinematic-vocab.mddoc306 bytes.claude/rules/image-models.mddoc300 bytes.claude/rules/model-reference.mddoc278 bytes.claude/rules/photodump-presets.mddoc258 bytes.claude/rules/prompt-formula.mddoc293 bytes.claude/settings.jsonasset108 bytes.gitattributesasset34 bytes.github/workflows/spec-drift.ymlasset16,961 bytes.github/workflows/validate.ymlasset4,177 bytes.gitignoreasset810 bytes.markdownlint.jsonasset228 bytesCHANGELOG.mddoc164,453 bytesCLAUDE.mddoc7,838 bytesCONTRIBUTING.mddoc1,621 bytesDISCIPLINE.mddoc18,447 bytesINDEX.mddoc102,593 bytesLICENSEasset1,069 bytesREADME.mddoc27,364 bytesSKILL.mdcore47,686 bytesSKILL.mdcore47,686 bytesSKILL.mdcore47,686 bytesassets/fonts/DejaVuSansCondensed-Bold.ttfasset665,028 bytesassets/fonts/DejaVuSansCondensed-Oblique.ttfasset599,292 bytesassets/fonts/DejaVuSansCondensed.ttfasset680,264 bytesassets/fonts/DejaVuSansMono.ttfasset340,712 bytesassets/fonts/README.mddoc4,849 bytesdb/filter-memory.jsonasset3,705 bytesdb/ledger/README.mddoc8,538 bytesdb/ledger/_demo.jsonasset2,709 bytesdb/ledger/_global.jsonasset184 bytesdb/memory-summary.mddoc4,727 bytesdb/quality-memory.jsonasset5,592 bytesdb/routing-log.jsonasset421 bytesdocs/Seedance 2 Skill.mddoc19,429 bytesdocs/archive/AUDIT-2026-06-03.mddoc11,718 bytesdocs/archive/CHANGELOG-v3.0-v3.14.mddoc376,749 bytesdocs/archive/HISTORY.mddoc91,643 bytesdocs/field-test-queue.mddoc5,506 bytesdocs/user-guide/MANIFEST.jsonasset306 bytesevals/cases/3d.jsonasset5,225 bytesevals/cases/acting.jsonasset5,280 bytesevals/cases/ad-multiplier.jsonasset4,091 bytesevals/cases/audio.jsonasset3,079 bytesevals/cases/cinema-4-0.jsonasset3,463 bytesevals/cases/cinema.jsonasset8,112 bytesevals/cases/gpt-image-2.jsonasset3,725 bytesevals/cases/harvest.jsonasset9,376 bytesevals/cases/model-lanes.jsonasset9,465 bytesevals/cases/models.jsonasset6,518 bytesevals/cases/prompt.jsonasset9,914 bytesevals/cases/repurpose.jsonasset5,144 bytesevals/cases/seedance-2-5.jsonasset19,670 bytesevals/cases/seedance.jsonasset16,207 bytesevals/cases/stack-workflows.jsonasset3,269 bytesevals/cases/troubleshoot.jsonasset5,910 bytesevals/cases/voice.jsonasset3,389 bytesevals/run_evals.pyruns14,437 bytesevals/spec-claims.jsonasset11,492 bytesimage-models.mddoc49,861 bytesmodel-guide.mddoc44,140 bytesphotodump-presets.mddoc5,015 bytesproduction-benchmarks.mddoc16,174 bytesprompt-examples.mddoc39,904 bytesrequirements.txtdoc503 bytesscripts/build_index.pyruns17,846 bytesscripts/claims_lint.pyruns16,183 bytesscripts/generate_user_guide.pyruns84,836 bytesscripts/higgsfield_memory.pyruns90,379 bytesscripts/preflight.pyruns61,890 bytesscripts/refresh_specs.pyruns42,754 bytesscripts/repo_walk.pyruns1,953 bytesscripts/seedance_lint.pyruns69,846 bytesscripts/snapshot_crosscheck.pyruns19,405 bytesscripts/sub_skill_descriptions.pyruns3,606 bytesscripts/sync_specs.pyruns41,231 bytesscripts/user_guide_content.pyruns9,941 bytesscripts/validate.pyruns58,707 bytesscripts/validate_user_guide.pyruns17,986 bytesskills/shared/house-rulings.mddoc31,836 bytesskills/shared/negative-constraints.mddoc21,447 bytesskills/shared/provenance.mddoc7,237 bytesspecs/3D-MODEL-SPECS.mddoc1,969 bytesspecs/3d-model-specs.jsonasset48,391 bytesspecs/3d-model-specs.yamlasset37,787 bytesspecs/AUDIO-MODEL-SPECS.mddoc1,000 bytesspecs/IMAGE-MODEL-SPECS.mddoc4,851 bytesspecs/MODEL-SPECS.mddoc6,406 bytesspecs/audio-model-specs.jsonasset11,812 bytesspecs/audio-model-specs.yamlasset9,787 bytesspecs/cli_baseline.jsonasset138,507 bytesspecs/crosscheck_allowlist.jsonasset27,125 bytesspecs/image-model-specs.jsonasset42,275 bytesspecs/image-model-specs.yamlasset31,996 bytesspecs/model-specs.jsonasset62,693 bytesspecs/model-specs.yamlasset47,604 bytesspecs/models_explore_snapshot_2026-06-11.jsonasset16,282 bytesspecs/models_explore_snapshot_2026-06-22.jsonasset20,620 bytesspecs/models_explore_snapshot_2026-07-05.jsonasset28,391 bytesspecs/models_explore_snapshot_2026-08-01.jsonasset30,510 bytesspecs/models_explore_snapshot_2026-08-07.jsonasset32,523 bytesspecs/models_explore_snapshot_2026-09-26.jsonasset41,131 bytesspecs/models_explore_snapshot_3d_2026-09-26.jsonasset34,255 bytesspecs/models_explore_snapshot_audio_2026-07-05.jsonasset5,657 bytesspecs/models_explore_snapshot_audio_2026-08-01.jsonasset7,564 bytesspecs/models_explore_snapshot_audio_2026-09-26.jsonasset7,715 bytesspecs/models_explore_snapshot_image_2026-06-22.jsonasset16,501 bytesspecs/models_explore_snapshot_image_2026-07-05.jsonasset21,918 bytesspecs/models_explore_snapshot_image_2026-08-01.jsonasset22,872 bytesspecs/models_explore_snapshot_image_2026-09-26.jsonasset28,125 bytesspecs/retired-model-ids.jsonasset1,057 bytestemplates/01-cinematic-action-chase.mddoc4,366 bytestemplates/02-product-ugc-showcase.mddoc4,231 bytestemplates/03-horror-atmosphere.mddoc4,520 bytestemplates/04-fashion-editorial.mddoc4,234 bytestemplates/05-sci-fi-vfx.mddoc5,012 bytestemplates/06-portrait-character-intro.mddoc4,540 bytestemplates/07-landscape-establishing-shot.mddoc4,311 bytestemplates/08-comedy-social-media.mddoc4,224 bytestemplates/09-romantic-intimate.mddoc4,427 bytestemplates/10-dance-music-performance.mddoc7,098 bytestemplates/ad-asset-prep.mddoc18,459 bytestemplates/character-design/9-question-character-sheet.mddoc2,040 bytestemplates/character-design/character-web.mddoc1,396 bytestemplates/character-design/premise.mddoc1,315 bytestemplates/character-design/story-spine.mddoc1,653 bytestemplates/character-design/style-sheet.mddoc2,245 bytestemplates/character-design/world-sheet.mddoc1,759 bytestemplates/seedance/anime-animation.mddoc9,203 bytestemplates/seedance/facs-expression-beats.mddoc3,150 bytestemplates/seedance/footage-vfx-transform.mddoc8,741 bytestemplates/seedance/global-style-prefix.mddoc10,521 bytestemplates/seedance/multi-character-anchor.mddoc4,229 bytestemplates/seedance/omni-reference-2-5.mddoc8,998 bytestemplates/seedance/single-character-position.mddoc2,530 bytestemplates/seedance/staging-reference.mddoc14,904 bytestemplates/seedance/top-down-map.mddoc5,533 bytestemplates/seedance/worked-example-two-character.mddoc4,371 bytestemplates/text-overlays/slogan.mddoc1,457 bytestemplates/text-overlays/speech-bubble.mddoc1,416 bytestemplates/text-overlays/subtitle.mddoc1,449 bytestests/conftest.pyruns1,543 bytestests/fixtures/claims_doctrine_v3_35_0_excerpt.jsonasset16,900 bytestests/fixtures/cli_1_0_1_model_get_seedance_2_0.jsonasset2,910 bytestests/fixtures/cli_1_0_1_model_list_video.jsonasset2,372 bytestests/fixtures/cli_1_1_23_model_get_gpt_image_2.jsonasset1,434 bytestests/fixtures/cli_1_1_23_model_get_seedance_2_5.jsonasset4,095 bytestests/fixtures/cli_1_1_23_model_list_all_excerpt.jsonasset487 bytestests/fixtures/cli_baseline_2026-08-07_excerpt.jsonasset3,292 bytestests/fixtures/cli_rules_live_2026-09-26.jsonasset14,999 bytestests/fixtures/models_explore_snapshot_2026-06-11.jsonasset6,654 bytestests/test_build_index.pyruns11,865 bytestests/test_claims_lint.pyruns15,860 bytestests/test_commands.pyruns3,999 bytestests/test_ledger.pyruns24,413 bytestests/test_lint_rules.pyruns25,580 bytestests/test_memory.pyruns6,232 bytestests/test_memory_location.pyruns18,203 bytestests/test_preflight.pyruns23,229 bytestests/test_prompt_gates_wiring.pyruns2,682 bytestests/test_refresh.pyruns27,884 bytestests/test_repo_walk.pyruns2,998 bytestests/test_routing.pyruns2,641 bytestests/test_run_evals.pyruns5,948 bytestests/test_snapshot_crosscheck.pyruns12,946 bytestests/test_sync_specs.pyruns16,298 bytestests/test_user_guide.pyruns8,856 bytestests/test_validate.pyruns17,474 bytestests/test_workflows.pyruns12,380 bytesvocab.mddoc37,690 bytesworkspace/README.mddoc1,766 bytesworkspace/input/.gitignoreasset88 bytesworkspace/input/README.mddoc437 bytesworkspace/output/.gitignoreasset88 bytesworkspace/output/README.mddoc356 bytesworkspace/processed/.gitignoreasset88 bytesworkspace/processed/README.mddoc361 bytes
Read SKILL.md
# Higgsfield AI Prompt Skill
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [HARD RULES — pre-delivery checklist](#hard-rules--pre-delivery-checklist)
- [What Is Higgsfield?](#what-is-higgsfield)
- [Working Folders — file handling](#working-folders--file-handling)
- [Handling a Request](#handling-a-request)
- [Fast Path — Simple Creative Requests](#fast-path--simple-creative-requests)
- [Full Path — Production Requests](#full-path--production-requests)
- [Route to the Right Skill](#route-to-the-right-skill)
- [Load Map — how much to read](#load-map--how-much-to-read)
- [Check Templates for Genre Match](#check-templates-for-genre-match)higgsfield-3d
When your agent uses it
Use when the user wants a 3D model, mesh or GLB out of Higgsfield — image-to-3D, multi-view-to-3D, text-to-3D, rigging or animating a mesh, remesh / retopology, retexture, or 3D Body (human shape + pose from one photo) — or mentions 3D Jutsu / Scene Builder 3D (private Blender scene projects built through Python). Also use for a 3D turnaround of a character or prop as a consistent multi-angle reference, or a physical 3D blockout rendered as a staging reference for a video shot. Names that trigger it: generate_3d, sam_3_3d, image_to_3d, multi_image_to_3d, meshy_v7_image_to_3d, tripo_h3_1_image_to_3d, tripo_h3_1_multiview_to_3d, hunyuan3d_v3_image_to_3d, meshy_v6_text_to_3d, hunyuan3d_v3_1_text_to_3d, tripo_3d, 3d_rigging, meshy_v5_remesh, meshy_v5_retexture, sam_3_3d_body, animation_actions, scene_builder_3d_*.
What it loads into context
Frontmatter
392 tokensAlways available to the agent
SKILL.md
7,769 tokensWhen the skill is activated
Reference documents
63,512 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- What this sub-skill is for
- The catalog — 17 models, six jobs
- The source-image law
- Multi-view beats single-view
- The prompt field — two surfaces disagree
- Parameter rules the server enforces
- Rigging and animation
- Cost and submission discipline
- 3D Jutsu (Scene Builder 3D)
- Film use 1 — a 3D turnaround as a multi-angle reference
- Film use 2 — a 3D blockout as a staging reference
- Provenance and what is not known
- Related skills
Scripts executed separately
../../scripts/sync_specs.py
Files
../../scripts/sync_specs.pyruns41,231 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytesSKILL.mdcore27,627 bytes../higgsfield-cinema/SKILL.mddoc108,850 bytes../higgsfield-gpt-image-2/SKILL.mddoc27,879 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../higgsfield-stack/SKILL.mddoc35,193 bytes../../specs/models_explore_snapshot_3d_2026-09-26.jsonasset34,255 bytes../../templates/ad-asset-prep.mddoc18,459 bytes../../templates/seedance/staging-reference.mddoc14,904 bytes../../templates/seedance/top-down-map.mddoc5,533 bytes
Read SKILL.md
# Higgsfield 3D — Meshes, Rigs, and 3D Jutsu Scenes
## QUICK FACTS
*Routing aids — read the linked sections for the full rules. Nothing in this sub-skill is field-tested.*
- 17 3D models in the 2026-09-26 snapshot, six jobs: single image→3D, multi-view→3D, text→3D, rig, remesh / retexture, 3D Body [→](#the-catalog--17-models-six-jobs)
- **THE law:** the mesh reproduces only what is in the source image — to add or change props, clothing or held objects, edit the IMAGE first, then convert the edited result [→](#the-source-image-law)
- Multi-view beats single-view for geometry: 2–4 views of the same subject → `multi_image_to_3d` / `tripo_h3_1_multiview_to_3d` [→](#multi-view-beats-single-view)
- The `prompt` field: the MCP schema says only `sam_3_3d` accepts one; the CLI marks it REQUIRED on the three text→3D models — send it there, confirm with `get_cost` [→](#the-prompt-field--two-surfaces-disagree)
- Server-enforced rules: animation needs rigging; texture options need texturing ON; Hunyuan std caps the prompt at 200 characters and has no PBR [→](#parameter-rules-the-server-enforces)
- Rig + animate: humanoids rig best; `animation_action_id` comes from a 678-action library (ids 0–696, not contiguous — look up, never guess) [→](#rigging-and-animation)
- `get_cost: true` preflights for free; never auto-resubmit after a transport timeout [→](#cost-and-submission-discipline)
- 3D Jutsu = private Blender 5.2 scene projects: inspect (query) → guarded edit (run) → `show_scene` LAST [→](#3d-jutsu-scene-builder-3d)
- A generated GLB cannot enter a 3D Jutsu scene — imports are curated-catalog assets only in this version [→](#what-3d-jutsu-cannot-take-in)
- Film use 1: a mesh turnaround as a multi-angle reference — UNMEASURED [→](#film-use-1--a-3d-turnaround-as-a-multi-angle-reference)higgsfield-acting
When your agent uses it
Writes the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per character plus a per-scene rewrite of it, and a locked voice prompt. Use whenever a prompt needs acting, performance, or emotion direction; whenever characters read wooden, dead-eyed, or 'AI'; whenever a character must stay themselves across many shots; or when the user asks for character behavior, mannerisms, tics, a gait, or how someone reacts. Pairs with higgsfield-facs (muscle-level AU codes) and higgsfield-seedance (the prompt the paragraph goes into).
What it loads into context
Frontmatter
243 tokensAlways available to the agent
SKILL.md
9,763 tokensWhen the skill is activated
Reference documents
112,825 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Where this sits among the repo's performance tools
- What good acting is
- The five pillars of every scene
- The layer above the pillars — one direction, different fuel
- Listening and reaction
- The body
- How good acting sounds
- The acting master profile
- Eye life
- Scene adaptation
- Voice — fixed identity, never adapted
- States, not transitions
- Ensemble and space
- The atlas of bad acting
- The performance scale
- Pre-send checklist
- Master profile
- Scene adaptation
- Final axioms
- Related Skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytesSKILL.mdcore40,993 bytes../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-character-design/SKILL.mddoc26,041 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-scene-engine/SKILL.mddoc12,007 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance-2-5/VFX-PIPELINE.mddoc33,799 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../shared/house-rulings.mddoc31,836 bytes../shared/provenance.mddoc7,237 bytes
Read SKILL.md
# Higgsfield Acting Director
`[OFFICIAL — Higgsfield "Hell Grind" open-source brief]` — the performance system behind
Higgsfield's 95-minute AI feature film, adapted to this repo's prompt surfaces. That tag
covers the **untagged** text only: § The layer above the pillars, the silent-listener task,
the eye-task paragraph and the voice-bible note each carry their own tag and are not from
the brief (label legend: `../shared/provenance.md`).
**The core axiom of the entire system: acting is BEHAVIOR under pressure, not a display of
emotion.** A character wants something, something is in the way, and they act to get it.
Emotion is a byproduct of that struggle — never the thing you write directly.
This is a **layer on top of** `../higgsfield-seedance/SKILL.md`: the paragraph this skill
produces goes into the PERFORMANCE / CHARACTER ACTING block of an otherwise normal Seedancehiggsfield-apps
When your agent uses it
Use when the user asks about Higgsfield's one-click Apps, wants to know which app to use for a specific output, or needs guidance on the Apps workflow.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,599 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Top Apps by Use Case
- When to Use Apps vs. Manual Prompting
- Cinema Studio
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore6,734 bytes
Read SKILL.md
# Higgsfield Apps — One-Click Workflows
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Top Apps by Use Case](#top-apps-by-use-case)
- [Content Creator / Social Media](#content-creator--social-media)
- [Product & Commercial](#product--commercial)
- [Character & Face](#character--face)
- [Lifestyle & Fun](#lifestyle--fun)
- [Animation & Effects](#animation--effects)
- [Audio / Lipsync](#audio--lipsync)
- [When to Use Apps vs. Manual Prompting](#when-to-use-apps-vs-manual-prompting)
- [Cinema Studio](#cinema-studio)higgsfield-assist
When your agent uses it
Use when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to get more from fewer credits, or platform efficiency tips.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
3,101 tokensWhen the skill is activated
Reference documents
15,889 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Higgsfield Assist (GPT-5 Powered Copilot)
- Credit Optimization Guide
- Related skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/sync_specs.py
Files
../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/sync_specs.pyruns41,231 bytesSKILL.mdcore12,691 bytesSKILL.mdcore12,691 bytes../higgsfield-recall/SKILL.mddoc11,999 bytes
Read SKILL.md
# Higgsfield Assist + Credit Optimization
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Higgsfield Assist (GPT-5 Powered Copilot)](#higgsfield-assist-gpt-5-powered-copilot)
- [What Assist Can Do](#what-assist-can-do)
- [How to Use Assist](#how-to-use-assist)
- [When to Use Assist vs Claude with This Skill](#when-to-use-assist-vs-claude-with-this-skill)
- [Coming Features in Assist](#coming-features-in-assist)
- [Credit Optimization Guide](#credit-optimization-guide)
- [Understanding Credits](#understanding-credits)
- [Credit Cost Tiers (Approximate)](#credit-cost-tiers-approximate)
- [Quote From the Ledger, Not From Vibes](#quote-from-the-ledger-not-from-vibes)higgsfield-audio
When your agent uses it
Use when the user asks about audio in Higgsfield videos, needs to add dialogue or lip-sync, wants sound effects or ambient sound in generated video, asks about music or BGM in output, or is using any audio-capable model (Kling 3.0, Seedance 1.5 Pro, Seedance 2.0, Veo 3/3.1, Grok Video / Grok Imagine). Also use when the user's prompt would benefit from audio direction but they haven't mentioned it. Also use when the user wants standalone audio — a soundtrack, ambience bed, multi-speaker scene audio (Seed Audio 1.0), or text-to-speech voiceover. Also use to swap or revoice the speaker in an existing video (voice_change), or to clone / create a reusable voice (create_voice → a voice_type 'element' voice usable in TTS and voice change).
What it loads into context
Frontmatter
293 tokensAlways available to the agent
SKILL.md
11,420 tokensWhen the skill is activated
Reference documents
60,642 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Which Models Support Audio?
- The Four Audio Layers
- Audio Prompt Structure
- Lip-Sync Rules
- Audio as a Conditioning Input — Seedance 2.0 (`@Audio1`)
- Audio by Model — What Works Best Where
- Common Audio Failures and Fixes
- When to Skip Audio
- Cinema Studio 3.0 Audio (Business/Team Plan)
- Scene-Audio Generation — Seed Audio 1.0
- Standalone Audio tab — tool catalog (2026-09-26 snapshot)
- Voice change and voice cloning
- Related skills
Scripts executed separately
../../scripts/higgsfield_memory.py../../scripts/sync_specs.py
Files
../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/sync_specs.pyruns41,231 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytesSKILL.mdcore46,358 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-repurpose/SKILL.mddoc15,669 bytes../higgsfield-seedance-vfx/references/dialogue-timing.mddoc3,365 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes../../specs/AUDIO-MODEL-SPECS.mddoc1,000 bytes../../specs/audio-model-specs.jsonasset11,812 bytes../../specs/models_explore_snapshot_audio_2026-09-26.jsonasset7,715 bytes../../templates/seedance/global-style-prefix.mddoc10,521 bytes
Read SKILL.md
# Higgsfield Audio Prompting Guide
## QUICK FACTS
*Routing aids — read the linked sections for the full rules.*
- Native-joint audio models: Kling 3.0, Seedance 2.0 / 1.5 Pro, Veo 3/3.1, Grok — all others add audio in post [→](#which-models-support-audio)
- Four layers to consider per prompt: Dialogue / SFX / Ambient / BGM [→](#the-four-audio-layers)
- Suppressing a score: name the diegetic sound first, then the suppression as plain text; `NO BGM` vs `No music.` is OPEN (house-rulings P2-7) [→](#suppressing-music--no-bgm-is-a-spec-no-music-is-a-preference)
- Lip-sync is the most failure-prone feature: 3–8s clips, MCU framing, one speaking face, locked camera, no head-motion tokens; per-language sync-word budgets come from a third-party skill (EMPIRICAL, unmeasured here) [→](#lip-sync-rules)
- **Seedance 2.0 `@Audio1` is a conditioning INPUT** — beat sync, the `[AUDIO: Xs]` script block, and the first-15s extraction trap [→](#audio-as-a-conditioning-input--seedance-20-audio1)
- Scope an audio reference like an image one: name the property that rides, the property that must NOT, and where the excluded one comes from instead [→](#scope-an-audio-reference--say-which-property-rides)
- Multi-clip assembly: one master track · cuts land on musical punctuation, never inside a sung vowel (ECU mouth-match is the one exception) · unified grain + LUT masks batch color drift [→](#cutting-to-music--assembling-separately-generated-clips-on-one-track)
- Cinema Studio 3.0 native joint audio (SCELA): describe audio as a separate section; specific foley beats generic moods [→](#cinema-studio-30-audio-businessteam-plan)
- **Seed Audio 1.0** (`seed_audio`, standalone) = whole-scene audio in ONE pass — multi-speaker dialogue + music + SFX + ambience mixed [→](#scene-audio-generation--seed-audio-10)
- Standalone Audio catalog (2026-09-26 snapshot): `seed_audio`, `qwen_audio_tts` (Qwen 3.0 TTS Flash — gained `batch_size` 1–4 on 2026-09-26, the only audio change since 08-01), `text2speech_v2` (5 engines incl. cozy_voice), plus 3 game-pipeline-only tools — distinct from in-video joint audio [→](#standalone-audio-tab--tool-catalog-2026-09-26-snapshot)higgsfield-camera
When your agent uses it
Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
6,600 tokensWhen the skill is activated
Reference documents
39,338 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Dolly Movements
- Crane / Vertical Movements
- Orbit / Arc Movements
- Zoom Effects
- Follow / Action Movements
- Specialty / Cinematic
- Time-Based
- Through-Object
- Specialty Vehicle / Action
- Pitch & Perspective — Camera Angles
- Shot Sizes
- Combining Camera Controls
- Camera-Emotion Sync — Movement per Focal Character Emotion
- Cinema Studio 3.0 Camera Best Practices (Business/Team Plan)
- Video Reference — What It Reads, and What It Can't
- Related skills
Files
SKILL.mdcore28,856 bytesSKILL.mdcore28,856 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Camera Controls
Always reference camera controls by their **exact preset name** in prompts.
Higgsfield recognizes these names directly.
## QUICK FACTS
*Routing aids — read the linked sections for the actual rules.*
- Named preset tables by family: dolly / crane / orbit / zoom / follow / specialty / time-based / through-object / vehicle, plus angles and shot sizes — always cite the **exact preset name** [→](#dolly-movements)
- Layer max two *compatible* moves; sequenced combos get explicit timing; static-pan beats glide for most coverage [→](#combining-camera-controls)
- **The camera is the emotional double of the focal character** — 7 emotional registers map to camera prescriptions; arcs change the camera in named phases [→](#camera-emotion-sync--movement-per-focal-character-emotion)
- [OFFICIAL] Lens + aperture chosen by shot *purpose* (85/100mm F1.4 tight emotional CU … 45mm macro F2.8), with standing focus-lock and distortion-forbid clauses [→](#lens--aperture-by-shot-purpose)
- [OFFICIAL] Shot duration by type: flash establish 0.3–0.5s · dialogue line 3–7s · wordless reaction 5–10s · full-arc emotional CU 8–15s [→](#shot-duration-by-type)
- Micro-moves need exact distances — state total travel + time ("10–15 cm over 7 seconds"); never write `zoom` for a physical move [→](#micro-moves-need-exact-distances)
- Cinema Studio 3.0: One-Move Rule, genre presets, reliable phrasing library, camera transfer via `@Video` [→](#cinema-studio-30-camera-best-practices-businessteam-plan)higgsfield-canvas
When your agent uses it
Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven models that run inside Canvas, the named canvas patterns (Simple Seedance, Extend Video, Image Edit, StoryBoard With Elements, Long Video fan-out), the build-free / generate-paid cost model, reusable templates, assets-as-nodes, and Shared Canvas live collaboration. Also trigger on 'Higgsfield ComfyUI alternative', 'node workflow', or 'connect nodes to build a scene/campaign'.
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
2,242 tokensWhen the skill is activated
Reference documents
88,334 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. When to use Canvas
- 2. Node categories
- 3. Models that run inside Canvas
- 4. Named canvas patterns
- 5. Cost model
- 6. Templates and assets-as-nodes
- 7. Shared Canvas — live collaboration
- 8. Cross-surface context
- 9. Source acknowledgment
Scripts executed separately
../../scripts/build_index.py
Files
../../image-models.mddoc49,861 bytes../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytesSKILL.mdcore9,419 bytes../higgsfield-content-factory/SKILL.mddoc15,152 bytes../higgsfield-gpt-image-2/SKILL.mddoc27,879 bytes../higgsfield-gpt-image-2/reference-sheet-workflow.mddoc18,364 bytes../higgsfield-motion/SKILL.mddoc21,460 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../higgsfield-workspaces/SKILL.mddoc19,203 bytes
Read SKILL.md
# Higgsfield Canvas — Node-Based Production Workspace
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [1. When to use Canvas](#1-when-to-use-canvas)
- [2. Node categories](#2-node-categories)
- [3. Models that run inside Canvas](#3-models-that-run-inside-canvas)
- [4. Named canvas patterns](#4-named-canvas-patterns)
- [5. Cost model](#5-cost-model)
- [6. Templates and assets-as-nodes](#6-templates-and-assets-as-nodes)
- [7. Shared Canvas — live collaboration](#7-shared-canvas--live-collaboration)
- [8. Cross-surface context](#8-cross-surface-context)
- [9. Source acknowledgment](#9-source-acknowledgment)higgsfield-character-design
When your agent uses it
Pre-production story-and-character development for Higgsfield projects — the upstream layer that decides WHAT to prompt before any model runs. Use when the user wants to build a character, design a world, develop a story or premise, create a character sheet / character bible / story bible, lock a visual style or 'visual DNA', plan a multi-shot narrative with consistent characters, or says things like 'help me design a character', 'build the world', 'I need a backstory', 'make this character consistent across shots', 'develop my film/series concept', or 'I keep getting generic AI characters'. Routes the locked outputs into higgsfield-prompt + the right model. Adapted from Higgsfield's official character-design framework by @vavavinca.
What it loads into context
Frontmatter
236 tokensAlways available to the agent
SKILL.md
6,116 tokensWhen the skill is activated
Reference documents
88,768 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- The method: world first
- Step 1 — Premise
- Step 2 — World Sheet (six dimensions)
- Step 3 — Character (9 questions + the web)
- Step 4 — Story Spine
- Step 5 — Style Sheet (Visual DNA + Forbidden List)
- Step 6 — Hand off to generation
- Sheet Construction Laws
- Screen Test / Audition
- Anti-generic drills
- Hard vs soft worldbuilding
- Templates
- Related skills
Files
../../SKILL.mddoc47,686 bytes../../image-models.mddoc49,861 bytes../higgsfield-acting/SKILL.mddoc40,993 bytesSKILL.mdcore26,041 bytesSKILL.mdcore26,041 bytesSKILL.mdcore26,041 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-seedance-2-5/VFX-PIPELINE.mddoc33,799 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../shared/house-rulings.mddoc31,836 bytes../../templates/ad-asset-prep.mddoc18,459 bytes../../templates/character-design/9-question-character-sheet.mddoc2,040 bytes../../templates/character-design/character-web.mddoc1,396 bytes../../templates/character-design/premise.mddoc1,315 bytes../../templates/character-design/story-spine.mddoc1,653 bytes../../templates/character-design/style-sheet.mddoc2,245 bytes../../templates/character-design/world-sheet.mddoc1,759 bytes
Read SKILL.md
# Higgsfield Character Design — Story Bible
The rest of this skill library answers *"how do I prompt this?"* This skill answers the question upstream of it: *"what am I prompting, and why this and not generic AI slop?"* It is the pre-production layer — premise, world, character, story, and a locked visual style — that you build **before** writing a single generation prompt, then hand off to `higgsfield-prompt` and the model guides.
> **Attribution.** The framework, worksheet structure, and the "world first" method are adapted from Higgsfield's official *Character Design* materials by **@vavavinca**. We reuse the *schemas and method*; all examples here are original. Credit Vinca when sharing.
## QUICK FACTS
*Routing aids — read the linked sections for the actual method.*
- **World first, always.** Lock the world before you cast a character; the world is the gravity that shapes who they have to become [→](#the-method-world-first)
- Six steps, each locks an output you do not revisit: Premise → World → Character → Story Spine → Style Sheet → hand-off [→](#the-method-world-first)
- The flagship artifact is the **9-Question Character Sheet** — thematic role, external/internal goal, psychological/moral need, wound, spark, silhouette, contradiction [→](#step-3--character-9-questions--the-web)
- The strongest anti-slop tool is the **Forbidden List** in the Style Sheet — naming what the world is NOT is often more useful than the palette [→](#step-5--style-sheet-visual-dna--forbidden-list)
- Specificity beats adjectives: if *any* character could say it, it's a stereotype; keep asking **"why?"** until the answer surprises you [→](#anti-generic-drills)
- Fillable worksheets live in `../../templates/character-design/` — hand them to the user or fill them together [→](#templates)higgsfield-cinema
When your agent uses it
Guides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements. Use when the user mentions Cinema Studio, Cinema Studio 2.5, Cinema Studio 3.0, Cinema Studio 3.5, Cinema Studio 4.0 (`cinematic_studio_video_4_0` — its four modes, camera/lens/aperture/era/genre/pacing ids, light presets, color palette), Soul Cast, color grading, multi-shot video, shot sequences, storyboard workflow, Hero Frame, optical stack, keyframe interpolation, Elements system (@Characters/@Locations/@Props), Speed Ramp, Director Panel, Higgsfield Popcorn, Single Shot / Multi-Shot Auto / Multi-Shot Manual modes, Reference Anchor, Smart shot control, or any professional filmmaking workflow inside Higgsfield.
What it loads into context
Frontmatter
290 tokensAlways available to the agent
SKILL.md
25,711 tokensWhen the skill is activated
Reference documents
156,558 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Cinema Studio vs Standard Generation
- ⚠ Version Detection — Ask First
- The 10-Step Cinema Studio 2.5 Workflow
- Elements System — Define Once, Call Everywhere
- Soul Cast — AI Actor Generation
- Built-in Color Grading Suite
- Optical Physics Engine
- Director Panel — 18 Camera Movements
- Speed Ramp
- Genre Selection
- Shot Modes
- Reference Anchor System
- Location Reference Sheets
- Reference Sheet Types — Beyond Characters and Locations
- Hero Frame
- Higgsfield Popcorn — Storyboard Integration
- Keyframe Interpolation — Start/End Frames
- 3D Mode — Gaussian Splatting
- Grid Generation — Batch Variations
- Resolution Settings
- Frame Extraction Loop — Build, Animate, Extract, Repeat
- Object & Person Insertion
- Clustering — Automatic Generation Grouping
- Cinema Studio Output Format
- ⚠ Prompt Character Limit — 512 Characters
- @ Element Persistence Across Scenes
- Prompting Best Practices
- Fight Scene & Action Design Rules (Tested)
- Model Selection for Cinema Studio
- Quick Decision — Cinema Studio vs Other Tools
- Cinema Studio 3.0 (Business/Team Plan)
- Cinema Studio 3.5
- Cinema Studio 4.0
- Physics Rendering — Resolution Decision Matrix
- Related skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-3d/SKILL.mddoc27,627 bytes../higgsfield-assist/SKILL.mddoc12,691 bytes../higgsfield-audio/SKILL.mddoc46,358 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesSKILL.mdcore108,850 bytesreferences/output-formats-2-5-3-0.mddoc10,742 bytesreferences/reference-sheet-types.mddoc11,255 bytes../higgsfield-models/MODELS-DEEP-REFERENCE.mddoc78,991 bytes../higgsfield-moodboard/SKILL.mddoc10,259 bytes../higgsfield-pipeline/SKILL.mddoc52,656 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../shared/negative-constraints.mddoc21,447 bytes../../specs/model-specs.jsonasset62,693 bytes../../specs/model-specs.yamlasset47,604 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Cinema Studio 2.5
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- Four Cinema Studio versions are on the platform (2.5 / 3.0 / 3.5 / 4.0) — user-selected, no auto-routing; always detect the version first [→](#-version-detection--ask-first)
- **Cinema Studio 4.0** (`cinematic_studio_video_4_0`, CLI workflow schema 2026-09-26): the same four modes as `seedance_2_5` (t2v / omni_reference / video_edit / video_extension), 480p–1080p, start/end image + image/video/audio refs; the 3.5 enum pills are GONE — camera / lens / aperture / era / genre / pacing are free `*_id` strings with no published values, so never invent one [→](#cinema-studio-40)
- 4.0 vs 3.5 at the API: no `multi_shots` / `multi_prompt`, no `genre` enum, no `enhance_prompt`; `prompt` now REQUIRED; audio defaults ON; duration default 5s (range unpublished) [→](#what-changed-from-35-at-the-api)
- Hard 512-character prompt cap; 2.5 @ Element chips eat ~80–100 hidden chars each [→](#-prompt-character-limit--512-characters)
- Elements System: define @Characters/@Locations/@Props once, call everywhere [→](#elements-system--define-once-call-everywhere)
- 3.5 main UI = three pills (Genre / Style / Camera), each Auto by default — override only with a creative reason [→](#the-three-pill-main-surface)
- 7 confirmed 3.5 genres: General · Action · Horror · Comedy · Noir · Drama · Epic — never invent genre names [→](#cinema-studio-35-genres)
- Style presets: 8 Color Palettes · 6 Lighting · 9 Camera Moveset Styles, or free-form Manual Style [→](#style-settings--three-operating-modes)
- Camera axes: 3 bodies · 5 lenses · focal 8/14/35/50/75mm · aperture f/1.4–f/4–f/11; two camera vocabularies coexist — vocabulary follows the selected model [→](#camera-settings--four-axis-panel)
- Output enums: 7 aspect ratios incl. 21:9 · 480p/720p/1080p · duration 4–15s · Sound On/Off [→](#cinema-studio-35-output-controls)higgsfield-content-factory
When your agent uses it
Use when the user wants to run a full ad-campaign pipeline on top of Higgsfield Marketing Studio — 'create a campaign', 'build a content plan', 'run the content pipeline', 'generate 100 UGC videos', 'plan and schedule a launch', 'make a batch of ads from my product', or 'how much did this save vs traditional production'. Covers the 5-stage orchestration (Research → Plan → Generate → Publish → Report), the UGC-first 5-format campaign mix (UGC Entertainment, Street Interview, Unboxing, Product Review, ASMR), the even-split allocation math, button-driven onboarding, the per-batch generation gate, and the publish + cost-report tail (satellite). Defers all Marketing Studio API ground-truth (presets, params, hooks, avatars) to higgsfield-marketing-studio.
What it loads into context
Frontmatter
260 tokensAlways available to the agent
SKILL.md
3,757 tokensWhen the skill is activated
Reference documents
23,692 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Two operating principles
- 2. Onboarding — one message, all buttons, no pauses
- 3. The campaign mix — 5 UGC formats (even split)
- 4. Stage 1 — Trend research & viral ideas
- 5. Stage 2 — Video content plan
- 6. Stage 3 — Generate in Marketing Studio
- 7. Stages 4–5 — Publish & report
- 8. Hard rules (consolidated)
- 9. Source acknowledgment
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore15,152 bytesSKILL.mdcore15,152 bytesSKILL.mdcore15,152 bytespublish-and-report-workflow.mddoc8,781 bytes../higgsfield-gpt-image-2/SKILL.mddoc27,879 bytes../higgsfield-marketing-studio/SKILL.mddoc60,125 bytes
Read SKILL.md
# Higgsfield Content Factory — Campaign Orchestration Pipeline
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [1. Two operating principles](#1-two-operating-principles)
- [Stage banners](#stage-banners)
- [2. Onboarding — one message, all buttons, no pauses](#2-onboarding--one-message-all-buttons-no-pauses)
- [3. The campaign mix — 5 UGC formats (even split)](#3-the-campaign-mix--5-ugc-formats-even-split)
- [Format → preset routing](#format--preset-routing)
- [Concept seeds (vary within each format)](#concept-seeds-vary-within-each-format)
- [ASMR is a style, not a preset](#asmr-is-a-style-not-a-preset)
- [4. Stage 1 — Trend research & viral ideas](#4-stage-1--trend-research--viral-ideas)
- [5. Stage 2 — Video content plan](#5-stage-2--video-content-plan)higgsfield-facs
When your agent uses it
Controls facial expressions in Seedance 2.0 with FACS (Facial Action Coding System) Action Unit codes — muscle-level direction (AU12 = lip-corner puller, AU6 = cheek raiser) instead of emotion labels. Use whenever the user wants precise facial acting, a forced/uncanny/mixed expression, micro-performance in a close-up, monologue or dialogue facial beats, a 'which AU code for anger/fear/disgust' answer, or to generate a FACS reference sheet for a character. Pairs with higgsfield-soul Micro-Expressions (named expressions), higgsfield-audio (dialogue + lip-sync), and higgsfield-gpt-image-2 (the reference-sheet image).
What it loads into context
Frontmatter
235 tokensAlways available to the agent
SKILL.md
7,175 tokensWhen the skill is activated
Reference documents
75,246 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- What FACS Is
- Provenance and the "Not a Guarantee" Rule
- The Plan-First Workflow
- Step 1 — Generate the FACS Reference Sheet
- Step 2 — Put AU Codes in the Seedance Prompt
- AU Code Reference
- Emotion → AU Recipes
- Physical Micro-Beats — the Body Beyond the Face
- Dialogue & Monologue Facial Acting
- Worked Examples
- Related Skills
Scripts executed separately
../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-audio/SKILL.mddoc46,358 bytesSKILL.mdcore27,393 bytes../higgsfield-gpt-image-2/SKILL.mddoc27,879 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../../templates/seedance/facs-expression-beats.mddoc3,150 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield FACS Director
Direct a face the way an animator does — by **muscle**, not by mood. FACS (the
Facial Action Coding System) names each facial movement as an **Action Unit**:
`AU12` is the lip-corner puller (smile), `AU6` is the cheek raiser, `AU4` is the
brow lowerer. Put those codes in a Seedance 2.0 prompt and the model renders the
corresponding action. It is the highest-resolution facial control available on
the platform, and it is where forced smiles, uncanny faces, mixed emotions, and
honest micro-performance in close-up dialogue come from.
> **This skill is a facial-control layer on top of `../higgsfield-seedance/SKILL.md`.**
> Every FACS prompt is still a Seedance prompt — six-slot formula, Prompt-Craft
> Laws, preflight linter. FACS only changes *how you specify the face*: AU codes
> instead of (or alongside) emotion words. It is the muscle-level case of thehiggsfield-gpt-image-2
When your agent uses it
Use when the user mentions GPT Image 2.0 or GPT Image 2.5, gpt-image-2, gpt-image-2.5, gpt_image_2_5, GPT-Image-2 prompts, the Flare / Sunburst variants, a transparent-background image, or wants to generate an image with GPT Image 2.0 or 2.5. Covers when to prefer GPT Image 2.5 over 2.0 (transparent background, xhigh/max quality, extra aspect ratios — from platform and OpenAI facts), the CLI-vs-MCP disagreement on gpt_image_2, the three-format prompt taxonomy (Format A structured JSON for UI mockups and layout-dense images; Format B dense cinematic prose for single-subject scenes; Format C auto-derive meta-prompt for theme-only concepts), per-format craft patterns, output conventions, the 6-item pre-delivery checklist, and cross-surface workflow context (companion static-ads-workflow.md for ad recreation; higgsfield-marketing-studio cross-surface-workflow.md §3 for ms_image / DTC Ads Higgsfield-native alternative).
What it loads into context
Frontmatter
358 tokensAlways available to the agent
SKILL.md
6,896 tokensWhen the skill is activated
Reference documents
57,578 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- GPT Image 2.5
- 1. What GPT Image 2.0 is
- 2. Three prompt formats
- 3. Format A — Structured JSON
- 4. Format B — Dense cinematic prose
- 5. Format C — Auto-derive meta-prompt
- 6. Routing decision
- 7. Output format conventions
- 8. Pre-delivery checklist
- 9. Example routings
- 10. Cross-surface workflow context
- 11. Source acknowledgment
Scripts executed separately
../../scripts/build_index.py
Files
../../DISCIPLINE.mddoc18,447 bytes../../SKILL.mddoc47,686 bytes../../image-models.mddoc49,861 bytes../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesSKILL.mdcore27,879 bytesreference-sheet-workflow.mddoc18,364 bytesstatic-ads-workflow.mddoc25,727 bytes../higgsfield-marketing-studio/cross-surface-workflow.mddoc32,118 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield GPT Image 2.0
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [GPT Image 2.5](#gpt-image-25)
- [Surface](#surface)
- [When to prefer 2.5 vs 2.0](#when-to-prefer-25-vs-20)
- [CLI ↔ MCP disagreement on `gpt_image_2`](#cli--mcp-disagreement-on-gpt_image_2)
- [Prompting status on 2.5](#prompting-status-on-25)
- [1. What GPT Image 2.0 is](#1-what-gpt-image-20-is)
- [2. Three prompt formats](#2-three-prompt-formats)
- [Tie-break](#tie-break)
- [3. Format A — Structured JSON](#3-format-a--structured-json)higgsfield-image-shots
When your agent uses it
Use when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type (close-up, wide shot, cowboy shot, etc.), or is working with [img] reference-based image generation. Covers distance & size shots, camera angles, and camera movement keywords optimized for AI image models (Soul 2.0, Nano Banana, Seedream, GPT Image, Flux, etc.).
What it loads into context
Frontmatter
182 tokensAlways available to the agent
SKILL.md
4,834 tokensWhen the skill is activated
Reference documents
4,790 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- How to Use This Reference
- Distance & Size — Shot Framing
- Distance & Size — Quick Reference
- Angles
- Angles — Quick Reference
- Camera Movements (Implied in Still Images)
- Combining Shot + Angle + Movement
- Image Prompt Formula (for Cinematic Stills)
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore20,595 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Cinematic Image Prompting
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- Scope: still-image composition only; `[img 1]` is the Soul ID / uploaded reference token — replace with a character description or @ Element when no reference is used [→](#how-to-use-this-reference)
- Base pattern: [Shot keyword] of [img 1 or character description] + [pose/action] + [environment detail] + [lighting/atmosphere] [→](#how-to-use-this-reference)
- 10 framing sizes, EWS → Macro: EWS tiny-in-landscape, Wide full body, Full head-to-toe, MLS knees up, Cowboy mid-thigh up, Medium waist up, MCU chest up, CU face, ECU single detail, Macro texture [→](#distance--size--quick-reference)
- Framing keywords: "EWS, Vast, Landscape" / "Wide Shot, Full Body" / "Cowboy Shot" / "MCU" / "Close-Up" / "ECU" / "Macro" [→](#distance--size--quick-reference)
- 10 angles: Eye-Level, Low Angle, High Angle, Overhead, Worm's Eye, Dutch/Canted, OTS, POV, Selfie, Ground Level [→](#angles--quick-reference)
- Angle = emotional read: Low = power, High = vulnerability, Dutch = unease/chaos, Worm's Eye = extreme power/surreal [→](#angles--quick-reference)
- Multi-word angle keywords: "POV, First Person Perspective" / "Selfie Angle, Arm's Length" / "Ground Level, Surface View" [→](#angles--quick-reference)
- OTS = looking past one person's shoulder at another — essential for dialogue [→](#over-the-shoulder-ots)
- Movement keywords create the FEELING of motion in a single frame — motion blur, implied movement, frozen mid-movement [→](#camera-movements-implied-in-still-images)
- Static/Basic movements: Static, Pan, Tilt, Zoom In / Zoom Out, Pedestal Up/Down [→](#static--basic)higgsfield-marketing-studio
When your agent uses it
Use when the user mentions Marketing Studio, DTC Ads, ad video, UGC video, the marketing_studio_video MCP model, or wants to generate one of the 9 Marketing Studio ad presets (UGC, Tutorial, Unboxing, Hyper Motion, Product Review, TV Spot, Wild Card, UGC Virtual Try On, Pro Virtual Try On). Also triggers on hook+setting picklist questions, preset-avatar / custom-avatar / text-generated-avatar handling, 4–15s ad video questions, or any reference to Higgsfield's ad-video product surface. Cross-surface workflow handoffs (GPT Image 2.0 / Soul Cinema / Nano Banana Pro / ms_image image gen → Marketing Studio video) covered in the companion cross-surface-workflow.md. Also use for Ad Multiplier (`ad_multiplier` — 'multiply my ad', many independently edited versions of one supplied 4–30s ad) and for Genjutsu one-off edits of a finished ad (swap one object / product / garment → `hf_mult_replace_object`; transfer motion → `hf_mult_motion_control`).
What it loads into context
Frontmatter
319 tokensAlways available to the agent
SKILL.md
14,763 tokensWhen the skill is activated
Reference documents
45,302 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- 1. What Marketing Studio is
- 2. Two access surfaces — and three MS models
- 3. The 9 presets
- 4. Hook + setting picklists
- 5. Avatar handling
- 6. Reference media — 4 slots
- 7. Generation parameters
- 8. Output prompt style — flowing OR sectioned (NOT a hard rule)
- 9. What Marketing Studio cannot do
- 10. Worked examples — production reference library
- 11. Cross-surface workflow context
- 12. Pricing characteristics
- 13. Source acknowledgment
- 14. Ad Multiplier and Genjutsu — editing a finished ad
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytesSKILL.mdcore60,125 bytescross-surface-workflow.mddoc32,118 bytes../higgsfield-repurpose/SKILL.mddoc15,669 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-stack/SKILL.mddoc35,193 bytes../../specs/model-specs.jsonasset62,693 bytes
Read SKILL.md
# Higgsfield Marketing Studio
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- Hard duration cap: 4–15s per clip; out-of-range values get clamped; longer narrative = multi-clip sequence edited externally [→](#7-generation-parameters)
- 9 presets: UGC, Tutorial, Unboxing (`ugc_unboxing`), Hyper Motion, Product Review, TV Spot, Wild Card, UGC Virtual Try On, Pro Virtual Try On [→](#3-the-9-presets)
- Pro Virtual Try On slug is `virtual_try_on`, NOT `pro_virtual_try_on` [→](#slug-naming-is-canonical-routing-mode-lives-on-a-different-mcp-call)
- Preset routing happens via `show_marketing_studio.mode` — `generate_video` has NO `mode` parameter at all [→](#slug-naming-is-canonical-routing-mode-lives-on-a-different-mcp-call)
- Hook + setting picklists on FIVE presets only: UGC, Tutorial, Unboxing, Product Review, UGC Virtual Try On (NOT Pro Virtual Try On) [→](#4-hook--setting-picklists)
- 9 hooks (4 stunt / 5 subtle) as of 2026-05-18 — picklists drift; enumerate live for current UUIDs [→](#hooks-9-entries-as-of-2026-05-18--visual-scene-templates-not-verbal-copy)
- 14 settings (8 realistic / 6 unrealistic) as of 2026-05-18, passed by UUID as `setting_id` [→](#settings-14-entries-as-of-2026-05-18--environment-templates)
- `avatars` array MUST contain exactly one entry; empty `avatars: []` substitutes a random face per render — always pass one [→](#avatar-field-constraints--consolidated)
- Two-person scenes: primary in `avatars`, secondary as a reference image in `medias` [→](#avatar-field-constraints--consolidated)
- `avatars` and `medias` are top-level siblings of `params` — NOT nested under `params`; wrong nesting rejects [→](#avatars-is-a-separate-top-level-media-slot--not-a-nested-parameter)higgsfield-mixed-media
When your agent uses it
Use when the user asks about Mixed Media, wants to apply artistic preset styles to an image (Noir, Sketch, Paper, Canvas, Particles, Neon, etc.), combine multiple artistic treatments, or create stylized non-photorealistic outputs.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,366 tokensWhen the skill is activated
Reference documents
4,790 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Is Mixed Media?
- The Full Mixed Media Preset Library
- How to Use Mixed Media in Prompts
- Stacking Presets (Layer Mixed Media)
- Mixed Media vs Visual Styles
- Mixed Media for Social Content
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore9,951 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Mixed Media
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [What Is Mixed Media?](#what-is-mixed-media)
- [The Full Mixed Media Preset Library](#the-full-mixed-media-preset-library)
- [Textural / Surface Presets](#textural--surface-presets)
- [Light & Atmosphere](#light--atmosphere)
- [Geometric & Digital](#geometric--digital)
- [Organic & Elemental](#organic--elemental)
- [Vintage & Film](#vintage--film)
- [Social / Trend](#social--trend)
- [Surreal / Dark](#surreal--dark)higgsfield-models
When your agent uses it
Use when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Wan (incl. Wan 3.0), Seedance (incl. 2.5), Veo 3, Minimax Hailuo / MiniMax H3, FLUX 3 Video, Gemini Omni Flash, Soul, Nano Banana, GPT Image 2.5, or other Higgsfield engines — including which lane edits existing footage (video_edit, Kling 3.0 Omni Edit, FLUX 3 Video Edit, Genjutsu, Ad Multiplier) and which models make one clip longer than 15s.
What it loads into context
Frontmatter
257 tokensAlways available to the agent
SKILL.md
9,136 tokensWhen the skill is activated
Reference documents
50,487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Decision Flowchart
- Video Models — Comparison
- Decision Flowchart
- Image Models — Quick Selection
- Budget Tiers
- Unique Feature Matrix
- Key Model Notes
- Cinema Studio 3.0 (Business/Team Plan)
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../image-models.mddoc49,861 bytes../../model-guide.mddoc44,140 bytes../../photodump-presets.mddoc5,015 bytes../../scripts/build_index.pyruns17,846 bytesMODELS-DEEP-REFERENCE.mddoc78,991 bytesSKILL.mdcore30,632 bytesSKILL.mdcore30,632 bytesSKILL.mdcore30,632 bytesSKILL.mdcore30,632 bytesSKILL.mdcore30,632 bytes../../specs/MODEL-SPECS.mddoc6,406 bytes
Read SKILL.md
# Higgsfield Model Selection Guide
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Quick Decision Flowchart](#quick-decision-flowchart)
- [Video Models — Comparison](#video-models--comparison)
- [Decision Flowchart](#decision-flowchart)
- [Image Models — Quick Selection](#image-models--quick-selection)
- [Budget Tiers](#budget-tiers)
- [Unique Feature Matrix](#unique-feature-matrix)
- [Key Model Notes](#key-model-notes)
- [Cinema Studio 3.0 (Business/Team Plan)](#cinema-studio-30-businessteam-plan)
- [Related skills](#related-skills)higgsfield-moodboard
When your agent uses it
Use when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash editorial, Street photography, Asian nostalgia, Retro BW, Surreal solarization, etc.
What it loads into context
Frontmatter
161 tokensAlways available to the agent
SKILL.md
2,404 tokensWhen the skill is activated
Reference documents
13,365 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Moodboard Does
- Curated Moodboard Presets
- Building a Custom Moodboard
- Soul Hex — Color Transfer
- Moodboard + Soul ID: The Power Combination
- Moodboard as a Prompt Modifier
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../image-models.mddoc49,861 bytes../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore10,259 bytes
Read SKILL.md
# Higgsfield Moodboard
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [What Moodboard Does](#what-moodboard-does)
- [Curated Moodboard Presets](#curated-moodboard-presets)
- [Building a Custom Moodboard](#building-a-custom-moodboard)
- [Upload Requirements](#upload-requirements)
- [Building the Moodboard](#building-the-moodboard)
- [Applying to Generation](#applying-to-generation)
- [Soul Hex — Color Transfer](#soul-hex--color-transfer)
- [Named Color Palettes](#named-color-palettes)
- [Custom Color Reference Upload](#custom-color-reference-upload)higgsfield-motion
When your agent uses it
Use when the user wants to apply a named Higgsfield motion preset, asks about VFX presets, transformation effects, elemental effects, or transition presets. Contains the full named preset library with descriptions and prompt usage.
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
4,991 tokensWhen the skill is activated
Reference documents
36,057 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Transformation & Body Effects
- Elemental Effects
- Transitions
- Action & Motion Effects
- Surreal / Artistic
- Nature / Environment
- Horror / Dark
- Social / Fun
- How to Request a Preset in a Prompt
- Intent-First Choreography (Cinema Studio 3.0 / Seedance 2.0 Best Practices)
- Related skills
- Kling 3.0 Motion Control — When and How to Run It
- Motion Reference Input Checklist
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytes../higgsfield-camera/SKILL.mddoc28,856 bytesSKILL.mdcore21,460 bytesSKILL.mdcore21,460 bytesSKILL.mdcore21,460 bytesSKILL.mdcore21,460 bytesSKILL.mdcore21,460 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Named Motion Presets
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Transformation & Body Effects](#transformation--body-effects)
- [Elemental Effects](#elemental-effects)
- [Transitions](#transitions)
- [Action & Motion Effects](#action--motion-effects)
- [Surreal / Artistic](#surreal--artistic)
- [Nature / Environment](#nature--environment)
- [Horror / Dark](#horror--dark)
- [Social / Fun](#social--fun)
- [How to Request a Preset in a Prompt](#how-to-request-a-preset-in-a-prompt)higgsfield-motion-design
When your agent uses it
End-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion', 'motion design', 'animate this', 'make a video from my logo', 'animated brand', 'motion graphics', 'brand motion', 'kinetic graphics', 'promo video', or 'ad video'. Drives a storyboard-first pipeline: brief → storyboard sheet (GPT Image 2) → video (Seedance 2.0) — an AI-generated pixel video clip. Distinct from higgsfield-motion (the named camera/motion preset library) and from higgsfield-vibe-motion (deterministic Remotion code with crisp text); use vibe-motion instead when the text/logo must stay perfectly crisp, editable, and deployable as code.
What it loads into context
Frontmatter
271 tokensAlways available to the agent
SKILL.md
2,329 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- STEP 0 — Determine the flow type
- STEP 1 — Brief intake (one message)
- STEP 2 — Asset handling
- STEP 3 — Generate the storyboard
- STEP 4 — Generate the video
- STEP 5 — Review & iterate
- Notes & rules
- Related skills
Files
SKILL.mdcore9,421 bytes
Read SKILL.md
# Higgsfield Motion Design
A full motion-design creation flow run through the Higgsfield MCP connector. Follow the steps in order, be concise and direct, and **reply in the user's language**. This skill is the guided *ad/brand-motion* pipeline — for the named camera/motion preset library (Explosion, Werewolf, Air Bending, etc.) use `higgsfield-motion` instead.
> **Not a spec sheet.** Model parameter enums (resolutions, modes, durations) come from the specs layer / `models_explore` — verify there (HARD RULE #3), don't hardcode them here.
## QUICK FACTS
- Two flows: **classicMD** (smooth, elegant, cinematic) vs **highMD** (fast cuts, extreme dynamics, CGI energy) — pick before anything else [→](#step-0--determine-the-flow-type)
- Ask **all** brief questions in ONE message — never split intake into rounds [→](#step-1--brief-intake-one-message)
- Storyboard = **one** image: a single grid sheet with all N panels via GPT Image 2 — never N separate images [→](#step-3--generate-the-storyboard)
- Final video = **Seedance 2.0** (`seedance_2_0`); confirm the model id with `models_explore` if unsure [→](#step-4--generate-the-video)
- highMD rule: no realistic humans — silhouettes, chrome figures, or 3D abstract shapes only [→](#notes--rules)
- highMD rule: the logo lock is a static hold proportional to clip length (~1s / ~2s / ~2–3s for 5 / 10 / 15s) [→](#step-4--generate-the-video)
higgsfield-pipeline
When your agent uses it
Use when the user wants to create a complete multi-shot video, asks how to chain Higgsfield tools together, wants to build a short film or branded content series, asks "what's the full workflow", needs to connect Popcorn → image → video → Recast → audio → assembly, or wants to understand how the platform works as a production system rather than isolated tools.
What it loads into context
Frontmatter
158 tokensAlways available to the agent
SKILL.md
12,337 tokensWhen the skill is activated
Reference documents
111,079 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- The Core Insight
- Building Complete AI Projects — The 10-Step Methodology
- The Master Production Chain
- Pipeline A: Cinematic Short Film (Full Chain)
- Pipeline B: Social Content Series (Streamlined Chain)
- Pipeline C: Product Campaign (Commercial Chain)
- Pipeline D: Fast Iteration / Social Speed Run
- Pipeline E: Multi-Style Short Film (Soul Cinema + Seedance 2.0 Chain)
- The Edit — five stages to picture lock
- Working Practices
- Continuation & Extension Handoff
- Spatial Blocking — Top-Down Schema for Multi-Character Scenes
- Pipeline Decision Guide
- Pipeline Pitfalls
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytes../higgsfield-assist/SKILL.mddoc12,691 bytes../higgsfield-cinema/SKILL.mddoc108,850 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytesSKILL.mdcore52,656 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../higgsfield-troubleshoot/SKILL.mddoc35,106 bytes../shared/negative-constraints.mddoc21,447 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Production Pipeline
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- 8-stage Master Chain: Popcorn → Seedream/Soul → Animate → Recast → Lipsync → Vibe Motion → Upscale → Assemble; most good short-form uses 3–5 stages [→](#the-master-production-chain)
- Lock 9 project fields before touching any tool; "what must stay consistent" is the load-bearing one [→](#step-01--start-with-the-project-not-the-prompt)
- One job per scene — six scene purposes; a good scene prompt answers six questions [→](#step-06--give-every-scene-one-job)
- 7 reusable prompt-module types: character identity, camera, lighting, style, motion, negative prompt, continuity [→](#step-07--use-prompt-modules)
- 80% rule: keep what worked, fix only the mistake; every diagnosed failure becomes a new negative rule [→](#step-0809--fix-failures--protect-what-worked)
- Build in 8 passes: Concept → Project script → Scene breakdown → Shot list → Image prompts → Video prompts → Review → Fix [→](#step-10--build-the-project-in-passes)
- Use the EXACT same character description (copy-paste) in every Popcorn prompt — continuity without Soul ID [→](#stage-1--storyboard-with-popcorn)
- Seedream edits the image, not the video — always edit the Hero Frame before animating, never after [→](#stage-2--image-editing-with-seedream)
- Model by scene type: Seedance 2.0 / Minimax Hailuo 2.3 for stunts/epic ("one continuous shot, no cuts"), Kling 2.6 portraits, Seedance quiet interiors [→](#stage-3--animate-by-scene-type)
- Recast swaps identity while preserving motion, camera, and lighting; the "prompt" is the reference image you upload [→](#stage-4--recast-character-swap)higgsfield-prompt
When your agent uses it
Use when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
9,881 tokensWhen the skill is activated
Reference documents
74,496 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- The MCSLA Formula
- Prompt Types
- Narrative Structure
- High-Performing Prompt Patterns
- The Pre-Prompt Checklist
- One Action Per Scene
- Generic-Emotion Decomposition — Which kind of X?
- Identity vs. Motion Separation Rule
- Conflict resolution between sub-skills
- Common Prompt Mistakes
- Before You Iterate — Is the Miss Systematic or Stochastic?
- The Iteration Rule — Change One Variable at a Time
- Seedance 2.0 Prompting Best Practices
- Seedance 2.0 Scene Archetype Router
- Seedance 2.0 Engine Constraints
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytes../higgsfield-camera/SKILL.mddoc28,856 bytesSKILL.mdcore42,594 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../higgsfield-troubleshoot/SKILL.mddoc35,106 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes../../specs/model-specs.yamlasset47,604 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Prompt Engineering
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- MCSLA = Model, Camera, Subject, Look, Action — the five layers of every prompt [→](#the-mcsla-formula)
- I2V: describe ONLY what moves or changes, never what's already in the image [→](#image-to-video-i2v)
- Keep prompts under 200 words — **short-form MCSLA regime only**; block-scaffold production prompts replace the cap with structural lint (HARD RULE 8 carve-out); Cinema Studio has a hard 512-character cap [→](#high-performing-prompt-patterns)
- 1 primary action per clip, 1–2 secondary max; Fast Motion Trick: render in Slow Mo, speed up in post [→](#one-action-per-scene)
- Never leave a generic emotion ("sad"/"angry") in a prompt — decompose into muscle movements, breath, eyes, skin [→](#generic-emotion-decomposition--which-kind-of-x)
- Soul ID / recurring characters: split every prompt into Identity Block + Motion Block — never mix them [→](#identity-vs-motion-separation-rule)
- Conflict order when sub-skills disagree: explicit user direction > scene archetype > emotion-sync [→](#conflict-resolution-between-sub-skills)
- Aspect ratio is a per-model enum set in the UI/header, never in the prompt body — verify via `../../specs/model-specs.yaml` [→](#common-prompt-mistakes)
- Never combine Dolly In + Dolly Out in one shot; @ Elements for static scenes, plain text for action [→](#common-prompt-mistakes)
- Iterate by changing exactly ONE variable per regeneration [→](#the-iteration-rule--change-one-variable-at-a-time)higgsfield-recall
When your agent uses it
Use this skill AUTOMATICALLY before writing any Higgsfield prompt. Query the memory databases for relevant past failures and pre-apply known fixes before the user even hits generate. Triggers include: any request to write a Higgsfield prompt, any use of the higgsfield-prompt skill, any mention of generating a video or image on Higgsfield, any MCSLA prompt construction. This skill should run SILENTLY in the background — don't announce it, just apply what's known. If the databases are empty, skip silently and proceed with normal prompt generation.
What it loads into context
Frontmatter
230 tokensAlways available to the agent
SKILL.md
2,811 tokensWhen the skill is activated
Reference documents
20,341 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Run
- Recall Workflow
- Manual Recall (User-Initiated)
- Pre-Generation Checklist (run mentally before every prompt)
- Log the Generation Result — One Question, One Command
- Database Status Check
- Related skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/sync_specs.py
Files
../../SKILL.mddoc47,686 bytes../../db/ledger/README.mddoc8,538 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/sync_specs.pyruns41,231 bytesSKILL.mdcore11,999 bytesSKILL.mdcore11,999 bytesSKILL.mdcore11,999 bytesSKILL.mdcore11,999 bytesSKILL.mdcore11,999 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Recall — Pre-Generation Memory Check
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Purpose](#purpose)
- [When to Run](#when-to-run)
- [Recall Workflow](#recall-workflow)
- [Step 1: Extract search terms from the prompt intent](#step-1-extract-search-terms-from-the-prompt-intent)
- [Step 2: Query both databases](#step-2-query-both-databases)
- [Step 3: Evaluate relevance](#step-3-evaluate-relevance)
- [Step 4: Apply findings silently](#step-4-apply-findings-silently)
- [Step 5: Surface findings only when material](#step-5-surface-findings-only-when-material)
- [Manual Recall (User-Initiated)](#manual-recall-user-initiated)higgsfield-recipes
When your agent uses it
Use when the user wants a genre-specific scene template, starting point for a type of video (action, horror, romance, product ad, documentary, sci-fi, dance, etc.), or asks for prompt examples for a specific style of content.
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
3,322 tokensWhen the skill is activated
Reference documents
38,045 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Recipe 1: Action / Chase
- Recipe 2: Emotional Drama / Character Moment
- Recipe 3: Product Advertisement
- Recipe 4: Sci-Fi / Futuristic
- Recipe 5: Horror / Supernatural
- Recipe 6: Romance / Intimate
- Recipe 7: Documentary / Nature
- Recipe 8: Dance / Music Video
- Recipe 9: Transformation / Before & After
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore13,575 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Genre Recipe Templates
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Recipe 1: Action / Chase](#recipe-1-action--chase)
- [Recipe 2: Emotional Drama / Character Moment](#recipe-2-emotional-drama--character-moment)
- [Recipe 3: Product Advertisement](#recipe-3-product-advertisement)
- [Recipe 4: Sci-Fi / Futuristic](#recipe-4-sci-fi--futuristic)
- [Recipe 5: Horror / Supernatural](#recipe-5-horror--supernatural)
- [Recipe 6: Romance / Intimate](#recipe-6-romance--intimate)
- [Recipe 7: Documentary / Nature](#recipe-7-documentary--nature)
- [Recipe 8: Dance / Music Video](#recipe-8-dance--music-video)
- [Recipe 9: Transformation / Before & After](#recipe-9-transformation--before--after)higgsfield-repurpose
When your agent uses it
Use when the user already has a FINISHED video and wants Higgsfield to repurpose, restyle, clip or analyze it: Shorts Studio (restyle one 4–120s source video into a set of short-form clips from a style preset), Clipify (turn one YouTube video into subtitled clips), Virality Predictor (predict virality, hook strength, attention, retention risk with a dashboard), or Video Analysis (scene-by-scene breakdown of an uploaded video or a YouTube link). Also use when the user asks which of these cost credits and which are free, 'turn my video into shorts', 'will this go viral', 'score my ad', 'break this video down scene by scene'. Names: shorts_studio_create, shorts_studio_create_preset, shorts_studio_list_presets, shorts_studio_status, clipify, virality_predictor, brain_activity, video_analysis_create, video_analysis_status.
What it loads into context
Frontmatter
277 tokensAlways available to the agent
SKILL.md
4,173 tokensWhen the skill is activated
Reference documents
91,590 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- What this sub-skill is for
- Paid or free — read this before calling anything
- Shorts Studio
- Clipify
- Virality Predictor
- Video Analysis
- Where the neighbouring jobs live
- Provenance
- Related skills
Files
../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-cinema/SKILL.mddoc108,850 bytes../higgsfield-content-factory/SKILL.mddoc15,152 bytes../higgsfield-marketing-studio/SKILL.mddoc60,125 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytesSKILL.mdcore15,669 bytes../higgsfield-scene-engine/SKILL.mddoc12,007 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance-vfx/SKILL.mddoc27,368 bytes../higgsfield-shotlist-director/SKILL.mddoc24,200 bytes../higgsfield-stack/SKILL.mddoc35,193 bytes../../specs/models_explore_snapshot_2026-09-26.jsonasset41,131 bytes
Read SKILL.md
# Higgsfield Repurpose — Shorts, Clips, and Analysis of Finished Video
## QUICK FACTS
*Routing aids — read the linked sections for the full rules. Nothing in this sub-skill is field-tested.*
- Four surfaces take a video that already exists: Shorts Studio (restyle → shorts), Clipify (YouTube → subtitled clips), Virality Predictor (a score), Video Analysis (a scene breakdown) [→](#what-this-sub-skill-is-for)
- Paid vs free is per tool — `shorts_studio_create` is **PAID**; its `get_cost` estimate and preset creation state they are free; list / status calls state no cost [→](#paid-or-free--read-this-before-calling-anything)
- Shorts Studio: source 4–120s, output **720p only**, 9:16 default (16:9 optional); preflight with `get_cost: true` + `duration_seconds` — no preset or upload needed for the estimate [→](#shorts-studio)
- Shorts Studio presets store a STYLE (≤10 media, videos ≤30s, public https URLs) — write the preset prompt as laws, not adjectives [→](#style-presets-free)
- Clipify: exactly ONE YouTube URL per job; 1–20 clips; 9:16 / 1:1 / 16:9; subtitle font, case, position and highlight colour are parameters [→](#clipify)
- Virality Predictor: input is a confirmed uploaded video or a completed generated video; it is a PREDICTION — compare variants with it, don't treat it as audience data [→](#virality-predictor)
- Video Analysis: exactly one of uploaded video / YouTube URL; ~3–5 min; **warn up front: the longer the video, the less accurate the breakdown** [→](#video-analysis)
- Burned-in captions, cuts, soundtrack, voice swaps are other surfaces — hand-off map [→](#where-the-neighbouring-jobs-live)
---higgsfield-scene-engine
When your agent uses it
Tests whether a scene is structurally worth generating before any shot is prompted — a five-element engine of Goal, Obstacle, Tactic, Reversal, and Value Shift. Use when the user has a scene, sequence, beat outline, or script and wants it audited or strengthened; when a sequence generates cleanly but lands flat and nobody can say why; when shots look good individually but the run of them does not build; or when the user asks 'is this scene working', 'what's weak here', or 'why doesn't this land'. Upstream of prompting — it decides WHICH shots deserve the credits, not how to write them. Pairs with higgsfield-character-design (who the characters are) and higgsfield-shotlist-director (turning the settled scene into shots).
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
2,937 tokensWhen the skill is activated
Reference documents
66,965 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The five-element engine
- The causal chain
- Audit procedure
- Where this sits before prompting
- Related Skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytes../higgsfield-acting/SKILL.mddoc40,993 bytes../higgsfield-character-design/SKILL.mddoc26,041 bytesSKILL.mdcore12,007 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-shotlist-director/SKILL.mddoc24,200 bytes../shared/house-rulings.mddoc31,836 bytes
Read SKILL.md
# Higgsfield Scene Engine — is this scene worth generating?
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [The five-element engine](#the-five-element-engine)
- [1. Goal](#1-goal)
- [2. Obstacle](#2-obstacle)
- [3. Tactic](#3-tactic)
- [4. Reversal](#4-reversal)
- [5. Value Shift](#5-value-shift)
- [The causal chain](#the-causal-chain)
- [Audit procedure](#audit-procedure)
- [Audit output](#audit-output)higgsfield-seedance
When your agent uses it
Rewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance 2.0 / Seedance Pro prompt, describes a scene for Seedance generation, mentions Seedance, reports a Seedance generation failure or flagged prompt, or is burning credits on Seedance regenerations.
What it loads into context
Frontmatter
172 tokensAlways available to the agent
SKILL.md
24,667 tokensWhen the skill is activated
Reference documents
194,362 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- The Filter Model — Read This First
- Instant Fail vs. Delayed Fail — the Diagnostic
- The Seedance Prompt Formula
- Prompt-Craft Laws
- Official Prompt Architecture — the Block Scaffold
- Seedance 2.0 Prompt Modes
- Continuation Prompt Formula
- Working Modes vs Prompt Modes — Two Taxonomies
- Reference Roles
- Frame Coordinate System
- Spatial Layout Block
- Working Modes
- Two-Layer Prompt Authoring
- Keyframe Workflow
- Pre-flight Linter
- Drafts Validate the Prompt, Not the Take
- The Rewrite Playbook
- Voice Rewrite — the "Filmmaker not Friend" Pass
- Output Format for Seedance Prompts
- Post-Clip Decisions
- When the User Is Already in a Failure Loop
- Multi-Language Prompt Workarounds
- Related Skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../SKILL.mddoc47,686 bytes../../db/filter-memory.jsonasset3,705 bytes../../production-benchmarks.mddoc16,174 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-acting/SKILL.mddoc40,993 bytes../higgsfield-assist/SKILL.mddoc12,691 bytes../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-camera/SKILL.mddoc28,856 bytes../higgsfield-cinema/SKILL.mddoc108,850 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-recipes/SKILL.mddoc13,575 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance-vfx/SKILL.mddoc27,368 bytes../higgsfield-seedance-vfx/references/first-frame.mddoc3,402 bytesENGINE-RULES.mddoc5,711 bytesFAILURE-MODES.mddoc31,734 bytesHELL-GRIND.mddoc34,478 bytesPRODUCTION-PATTERNS.mddoc10,667 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytesSKILL.mdcore105,815 bytes../higgsfield-shotlist-director/SKILL.mddoc24,200 bytes../higgsfield-soul/SKILL.mddoc56,318 bytes../higgsfield-style/SKILL.mddoc16,665 bytes../higgsfield-troubleshoot/SKILL.mddoc35,106 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes../shared/provenance.mddoc7,237 bytes../../specs/model-specs.jsonasset62,693 bytes../../specs/model-specs.yamlasset47,604 bytes../../templates/seedance/global-style-prefix.mddoc10,521 bytes../../templates/seedance/staging-reference.mddoc14,904 bytes../../templates/seedance/top-down-map.mddoc5,533 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Seedance Director
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- The filter is an LLM reading full-scene intent, not a keyword blacklist — describe a SCENE, not a subject; fix the voice first [→](#the-filter-model--read-this-first)
- Instant fail (<10s) = filter rejection; delayed fail (>30s) = infra/complexity — never regenerate an instant fail unchanged [→](#instant-fail-vs-delayed-fail--the-diagnostic)
- Six slots, in order: Camera + Subject + Action + Setting + Style + Lighting; missing 3+ slots is where flags come from [→](#the-seedance-prompt-formula)
- Empirical prompt-craft laws: 50–80-word attention sweet spot (front-load the load-bearing element), name a director/lens not "cinematic", "fast" degrades motion, no negative prompts in the body, unidirectional motion chains + named camera endpoint + detail scale follows shot size [→](#prompt-craft-laws)
- Five prompt modes: Reference-Based / Continuation / Expand Shot / Edit Shot / Transformation — pick the mode before writing [→](#seedance-20-prompt-modes)
- [OFFICIAL] block scaffold for production prompts: SCENE CONTEXT → … → POSITIVE LOCKS, distributed style on standalone briefs (connected shotlists glue the compiled Style Prefix verbatim instead), FOV in degrees only, CAMERA block 3rd, cut ladder oner / CUT n / timed / freestyle [→](#official-prompt-architecture--the-block-scaffold)
- [FIELD] 13-project corpus calibration: word length scales with register (218w → 2,059w medians — the 50–80w sweet spot is single-shot-only), video briefs hand-authored (`enhance_prompt` off), Style Prefix = per-project constant compiled into home blocks [→](#field-calibration--the-13-project-production-corpus)
- [FIELD] Three "helpful-instinct" drift sources, each with a standing lock: environment invention (#1, above character drift), character-height equalization, scale drift on wides [→](#positive-locks)
- Build-safe construction for crowds/destruction/creatures: evacuated cities, contained fights ("stays at the sea surface"), the safe benchmark scene [→](#build-safe-construction--crowds-destruction-creatures)
- Extend an existing clip: attach it as a video reference + open with "The scene continues." — match source resolution AND duration; chain cap ~2 (hard 3), then re-anchor from ORIGINAL references [→](#extension-prompting--video-reference-continuation)higgsfield-seedance-2-5
When your agent uses it
Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omni_reference / video_edit / video_extension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video editing, forward/backward extension, first-last-frame and multi-keyframe control, storyboard grids, blockout rendering, and seamless transitions. Use whenever the user asks for a Seedance 2.5 prompt, mentions Seedance 2.5 / Dreamina / Jimeng, wants a clip longer than 15s on Seedance, wants to EDIT or EXTEND an existing video rather than generate a new one, or supplies more than a handful of image/video/audio references. For Seedance 2.0 (4K, `mode=fast`, or a genre hint) use higgsfield-seedance instead.
What it loads into context
Frontmatter
284 tokensAlways available to the agent
SKILL.md
11,620 tokensWhen the skill is activated
Reference documents
122,722 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Provenance
- The Mode Router
- The Higgsfield Parameter Surface
- The Core Prompt Formula
- Reference Roles — Say What to Use *and* What Not to Use
- Multi-Reference — the Five-Step Workflow
- Long Video — Stages and End States
- Audio and Text — Bracket Syntax
- First-Last Frame and Multi-Keyframe Control
- Editing, Extension, and the Composite Modes
- Emotional Direction and Camera Terms
- The Real-Person Character Formula
- Choosing 2.0 vs 2.5
- Hard Limits — Do Not Over-Promise These
- Dreamina-Only — What Higgsfield Does Not Expose
- Pre-Submission Checklist
- Related Skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-acting/SKILL.mddoc40,993 bytes../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-models/SKILL.mddoc30,632 bytes../higgsfield-pipeline/SKILL.mddoc52,656 bytesMODE-PLAYBOOKS.mddoc25,864 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesSKILL.mdcore46,557 bytesVFX-PIPELINE.mddoc33,799 bytes../higgsfield-seedance-vfx/SKILL.mddoc27,368 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../shared/house-rulings.mddoc31,836 bytes../shared/provenance.mddoc7,237 bytes../../specs/model-specs.jsonasset62,693 bytes../../templates/ad-asset-prep.mddoc18,459 bytes../../templates/seedance/global-style-prefix.mddoc10,521 bytes
Read SKILL.md
# Higgsfield Seedance 2.5 Director
Seedance 2.5 is a **different dialect from Seedance 2.0**, not a version bump you can
prompt through by habit. 2.0 is a reference-driven shot generator with a 4K lane and a
genre hint. 2.5 is an **omni-reference production model**: up to 50 reference
materials, 30-second native runtime, and three non-generation modes — it can edit a video
you already have, and extend one forward or backward from its boundary frame.
The prompt grammar changes with it. Reference roles are declared in prose (`@Image 1
defines …`), audio and text get bracket syntax, long videos are staged with explicit end
states, and first/last frames live inside `omni_reference` — either as the platform's
`start_image` / `end_image` roles or announced **inside the prompt** — never as a separate
mode.
higgsfield-seedance-vfx
When your agent uses it
Writes, improves, or rewrites Seedance 2.0 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch. Use whenever a real clip is the starting point and they want to: add a VFX element (set a head or hair on fire, transform a hand, make a limb invisible), swap the environment around a preserved subject (desert, clouds, lava, a neon city), drop a giant photoreal creature behind or onto a subject/landmark, relight or regrade so subject and added elements read as one shot, sync a crash-zoom or push-in to a spoken line or timecode, or generate a matching transformed start frame to animate from. Also use when they paste such a prompt and ask to change its lighting, timing, creature, or runtime, or say 'make a Seedance prompt for this video' with a clip attached. This is the video-to-video specialization; for a brand-new scene from image references with no source clip to preserve, higgsfield-seedance applies instead.
What it loads into context
Frontmatter
314 tokensAlways available to the agent
SKILL.md
6,652 tokensWhen the skill is activated
Reference documents
87,226 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- The core idea: preserve, then change one thing
- Resolution: run it in 4K
- Prompt anatomy (transform variant)
- Three levels
- Two transformation modes
- Lighting integration (the part that makes or breaks it)
- Photoreal creature / element integration
- Timed camera moves synced to dialogue
- Duration discipline
- First / start-frame workflow
- Iterating
- Output format
- Voice (match the user)
- Seedance 2.0 input limits (reference)
- Structure patterns to internalize (style reference only — do not reproduce)
- Related Skills
Files
../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-camera/SKILL.mddoc28,856 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-gpt-image-2/SKILL.mddoc27,879 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance-2-5/VFX-PIPELINE.mddoc33,799 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesSKILL.mdcore27,368 bytesreferences/dialogue-timing.mddoc3,365 bytesreferences/first-frame.mddoc3,402 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../../specs/model-specs.jsonasset62,693 bytes../../templates/seedance/footage-vfx-transform.mddoc8,741 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Seedance VFX — Footage Transformation
This skill is for **editing a clip the user already has**: keep a real subject and the
real camera move, change only what they ask for. It is the video-to-video sibling of
`../higgsfield-seedance/SKILL.md` (the general Seedance director). It **reuses that skill's
grammar verbatim** — the six-slot formula, the Prompt-Craft Laws, the preflight linter —
and adds the transformation layer below. Do not contradict the parent skill; when a shot
needs filter-safety, mode selection, or engine rules, defer to it.
> **This file is the Seedance 2.0 v2v lane.** It stays the right choice when the job needs
> **4K**, `mode=std`, or a `genre` hint. If the plate job is running on **Seedance 2.5** —
> up to 1080p, up to 30 s, many references, platform start/end frames in `omni_reference` —
> the lane is
> `omni_reference` with the clip attached as a video reference, and its production doctrinehiggsfield-shotlist-director
When your agent uses it
Turns a brief, script, scene breakdown, treatment, or story idea into ONE connected director's shotlist for Seedance 2.0 — a single editable HTML artifact with a global Style Prefix, an @-asset glossary, and named per-scene prompts (1a, 1b, 2a…) each in Style → Characters → Scene → CUT 1..N form. Use whenever the user says 'make a shotlist', 'break this script into prompts', 'generate Seedance prompts for this ad/film', 'turn this brief into a shot list', 'director's shotlist', or wants many connected scene prompts rather than one. Also use to revise an existing shotlist (edit-once-propagates: 'change the style prefix everywhere', 'rewrite scene 4', 'split prompt 6'). Each prompt targets 15s; longer scenes split across 1a/1b/1c under one scene number.
What it loads into context
Frontmatter
276 tokensAlways available to the agent
SKILL.md
6,211 tokensWhen the skill is activated
Reference documents
76,303 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- What you produce
- The three layers
- Per-scene prompt law
- Prompt density — grouping shot rows into 15s envelopes
- Sequence tempo and variety
- Edit-once and per-scene override
- What makes this outclass a bare generator
- Workflow
- HTML skeleton
- Related skills
Scripts executed separately
../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-audio/SKILL.mddoc46,358 bytes../higgsfield-camera/SKILL.mddoc28,856 bytes../higgsfield-seedance-2-5/SKILL.mddoc46,557 bytes../higgsfield-seedance/ENGINE-RULES.mddoc5,711 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytesSKILL.mdcore24,200 bytes../higgsfield-style/SKILL.mddoc16,665 bytes../../templates/10-dance-music-performance.mddoc7,098 bytes../../templates/seedance/global-style-prefix.mddoc10,521 bytes../../templates/seedance/staging-reference.mddoc14,904 bytes../../templates/seedance/top-down-map.mddoc5,533 bytes
Read SKILL.md
# Higgsfield Shotlist Director
Turn a brief into **one connected shotlist** — not a pile of separate prompts.
The deliverable is a single editable HTML artifact the user opens in a browser,
ticks scenes off as they shoot, and comes back to you to revise. This is the
artifact-shaped workflow a fully-AI commercial actually runs on: lock a global
look once, declare the cast/props/locations once, then emit named per-scene
prompts that all inherit both.
> **This skill is the connected layer on top of `higgsfield-seedance`.** It does
> not reinvent the prompt grammar — every per-scene prompt obeys the six-slot
> formula and the Prompt-Craft Laws in `../higgsfield-seedance/SKILL.md`, and
> every prompt is preflight-linted before delivery. What this skill adds is the
> *document*: the global Style Prefix, the `@`-glossary, the per-scene numbering,higgsfield-soul
When your agent uses it
Creates and manages reusable character profiles (Soul IDs) for consistent facial and stylistic identity across multiple image and video generations. Provides identity-vs-motion prompt separation, character sheet creation workflows, micro-expression direction, and Soul Cast AI actor configuration. Use when the user wants to maintain character consistency across multiple generations, asks about Soul ID, creating reusable characters, or generating consistent people across different scenes and shots.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
12,990 tokensWhen the skill is activated
Reference documents
116,688 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- What Is Soul ID?
- How It Works
- When to Use Soul ID
- Prompting With Soul ID
- Identity vs. Motion Separation — Hard Rule
- Creating a Strong Soul ID Reference
- A sheet is not a menu — everything on it is a request
- The Untouched Base — build a character in two passes
- The Reference Plate — the two axes
- Character Sheet Creation
- Character Anchor Block
- Two-Tool Refinement Pipeline
- Micro-Expressions — Nuanced Performance Direction
- Multi-Character Consistency
- Variety Sheets — Crowds Without Clones
- AI Influencer Workflow
- Cinema Studio 3.0 Soul Cast (Business/Team Plan)
- Soul Cinema as the CS 3.0/3.5 Default Image Model
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../image-models.mddoc49,861 bytes../../production-benchmarks.mddoc16,174 bytes../../scripts/build_index.pyruns17,846 bytes../higgsfield-cinema/SKILL.mddoc108,850 bytes../higgsfield-facs/SKILL.mddoc27,393 bytes../higgsfield-seedance-2-5/VFX-PIPELINE.mddoc33,799 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytesSKILL.mdcore56,318 bytesSKILL.mdcore56,318 bytesSKILL.mdcore56,318 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes../../templates/ad-asset-prep.mddoc18,459 bytes
Read SKILL.md
# Higgsfield Soul ID — Character Consistency
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- Hard rule: every Soul ID prompt splits into Identity Block (static descriptors only) + Motion Block (temporal/camera only) [→](#identity-vs-motion-separation--hard-rule)
- Don't re-describe the face or core features — only describe what differs from the base character [→](#prompting-with-soul-id)
- Reference image rules: front or 3/4 angle, even lighting, neutral-to-slight expression, no blur, solo subject [→](#creating-a-strong-soul-id-reference)
- Reference generators: Soul 2.0 (fashion-forward), Nano Banana Pro (max sharpness), Seedream 4.5 (style range) [→](#creating-a-strong-soul-id-reference)
- Character sheet angles: front face, 3/4, side profile, optional full body + optional embedded prop sheets [→](#character-sheet-creation)
- Two-image floor per character: one clear face + one full body, on neutral grey — never a single image; the grey law's shade and mechanism live once in `../../templates/ad-asset-prep.md` [→](#character-sheet-creation)
- **The Untouched Base**: face pass in close-up, then a looks pass; the base close-up is never run through a model again — changes go on with masks, and a new state is a new named asset [→](#the-untouched-base--build-a-character-in-two-passes)
- **Reference plates**: biological realism ON, photographic capture behaviour OFF (no key direction, cast shadow, bokeh, flare); the background is a field, not a room; lean prompts once a reference carries identity [→](#the-reference-plate--the-two-axes)
- Prefer the single-prompt 3×2 six-panel sheet (one 16:9 generation) — identity locks better than multi-step assembly [→](#single-prompt-6-panel-character-sheet-32-grid)
- Outfit change without identity drift: split-panel sheet — ghost-mannequin outfit LEFT + "face matches input 100%" close-up RIGHT [→](#split-panel-outfit-change-sheet-ghost-mannequin--identity-panel)higgsfield-stack
When your agent uses it
Use when the user mentions the Higgsfield CLI (binaries `higgsfield` / `higgs` / `hf`, `higgsfield auth login`, `higgsfield generate create`, `higgsfield workflow`, the `@higgsfield/cli` npm package), the Higgsfield MCP custom connector (`mcp.higgsfield.ai/mcp`) or its bundled workflows (`get_workflow_instructions` — character-sheet, thumbnail-generation, ugc-* videos, faceless-video, narrator, subtitles, product-photoshoot, brand-asset-creation, ad-multiplier, video-editing / Higgsedit, website-builder-flow), Higgsfield's bundled skills repo (`higgsfield-ai/skills` — `higgsfield-generate`, `higgsfield-soul-id`, `higgsfield-product-photoshoot`, `higgsfield-brandkit`, `higgsfield-marketplace-cards`, `higgsfield-websites`, `higgsfield-video-explainer`, `higgsfield-youtube-thumbnail`, invoked as `/higgsfield:generate` etc.), or asks how this skill coexists with those tools (`do I need both`, `how does this work with the CLI/MCP/skills`, `should Higgsfield's workflow do this or you`).
What it loads into context
Frontmatter
345 tokensAlways available to the agent
SKILL.md
8,519 tokensWhen the skill is activated
Reference documents
119,249 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this sub-skill is for
- The three official surfaces
- Preflight discipline — check cost and balance before generating
- How our skill fits in
- Coexistence rules
- Higgsfield's bundled workflows
- Naming overlap — `higgsfield-soul-id` (theirs) vs `higgsfield-soul` (ours)
- Detection guidance
- Handoff templates
- Seedance preflight integration
- What this sub-skill does NOT do
- Related sub-skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../image-models.mddoc49,861 bytes../../model-guide.mddoc44,140 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-3d/SKILL.mddoc27,627 bytes../higgsfield-assist/SKILL.mddoc12,691 bytes../higgsfield-cinema/references/reference-sheet-types.mddoc11,255 bytes../higgsfield-marketing-studio/SKILL.mddoc60,125 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-repurpose/SKILL.mddoc15,669 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytes../higgsfield-soul/SKILL.mddoc56,318 bytesSKILL.mdcore35,193 bytesSKILL.mdcore35,193 bytes../higgsfield-workspaces/SKILL.mddoc19,203 bytes../../vocab.mddoc37,690 bytes
Read SKILL.md
# Higgsfield Stack — Coexistence With Official Tooling
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [What this sub-skill is for](#what-this-sub-skill-is-for)
- [The three official surfaces](#the-three-official-surfaces)
- [The bundled skills at 0.12.0](#the-bundled-skills-at-0120)
- [Preflight discipline — check cost and balance before generating](#preflight-discipline--check-cost-and-balance-before-generating)
- [Two-step preflight](#two-step-preflight)
- [Verified preflight surfaces](#verified-preflight-surfaces)
- [Plan tier, not surface, controls queue priority](#plan-tier-not-surface-controls-queue-priority)
- [When to surface preflight in this skill's output](#when-to-surface-preflight-in-this-skills-output)
- [Iteration-budget projection (production-benchmarks tie-in)](#iteration-budget-projection-production-benchmarks-tie-in)higgsfield-style
When your agent uses it
Use when the user asks about visual styles, aesthetics, color grades, film looks, or how to set the tone and atmosphere of a Higgsfield generation.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
4,081 tokensWhen the skill is activated
Reference documents
36,109 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Platform Styles
- Color Grade Vocabulary
- Lighting Vocabulary
- Cinematic Lighting Techniques
- Aspect Ratio Guide
- Style Best Practices (Cinema Studio 3.0 / Seedance 2.0)
- Register Poles — the style dial has opposite ends
- Style Recipes — eight proven shapes
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytes../higgsfield-seedance-vfx/SKILL.mddoc27,368 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytesSKILL.mdcore16,665 bytesSKILL.mdcore16,665 bytesSKILL.mdcore16,665 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Visual Styles
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Core Platform Styles](#core-platform-styles)
- [Cinematic](#cinematic)
- [VHS](#vhs)
- [Super 8MM](#super-8mm)
- [Anamorphic](#anamorphic)
- [Abstract](#abstract)
- [Color Grade Vocabulary](#color-grade-vocabulary)
- [Lighting Vocabulary](#lighting-vocabulary)
- [Cinematic Lighting Techniques](#cinematic-lighting-techniques)higgsfield-troubleshoot
When your agent uses it
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
8,298 tokensWhen the skill is activated
Reference documents
105,067 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- QUICK FACTS
- Common Problems & Fixes
- Motion Control Failures (Kling 3.0)
- Pre-Generation Checklist
- Cinema Studio 3.0 / Seedance 2.0 Diagnostic Tree
- Take Triage — Five Verdicts for a Delivered Take
- Sequence & Continuation Failure Atlas
- Retry Ladder — a failed take edits the plan, not just the dice
- Stop-Rule Ladder — which number governs
- Log the Outcome — Always
- Vision-Grounded Diagnosis — Classify the Rejected Still, Don't Guess
- Related skills
Scripts executed separately
../../scripts/build_index.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/higgsfield_memory.py../../scripts/preflight.py../../scripts/seedance_lint.py../../scripts/seedance_lint.py../../scripts/sync_specs.py
Files
../../SKILL.mddoc47,686 bytes../../production-benchmarks.mddoc16,174 bytes../../scripts/build_index.pyruns17,846 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/higgsfield_memory.pyruns90,379 bytes../../scripts/preflight.pyruns61,890 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/seedance_lint.pyruns69,846 bytes../../scripts/sync_specs.pyruns41,231 bytes../higgsfield-motion/SKILL.mddoc21,460 bytes../higgsfield-pipeline/SKILL.mddoc52,656 bytes../higgsfield-prompt/SKILL.mddoc42,594 bytes../higgsfield-seedance-2-5/VFX-PIPELINE.mddoc33,799 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytes../higgsfield-seedance/HELL-GRIND.mddoc34,478 bytes../higgsfield-seedance/SKILL.mddoc105,815 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytesSKILL.mdcore35,106 bytes../shared/house-rulings.mddoc31,836 bytes../shared/negative-constraints.mddoc21,447 bytes
Read SKILL.md
# Higgsfield Troubleshooting Guide
## QUICK FACTS
*Generated-checked block (scripts/build_index.py verifies anchors). Read the linked sections for full context — these lines are routing aids, not the rules themselves.*
- Face inconsistency, dead camera moves, ignored prompts, static i2v, blocked dark content — the per-problem fix list [→](#common-problems--fixes)
- Kling 3.0 Motion Control failures are almost always upstream of the prompt: reference clip, character image, or orientation/scene-source settings [→](#motion-control-failures-kling-30)
- Pre-generation checklist: subject, action, named camera preset, style, grade, aspect, <200 words (short-form regime) [→](#pre-generation-checklist)
- Seedance/Cinema Studio symptom table + diagnostic flowchart: blurry = overspecified; chaotic camera = One-Move Rule violated; wrong character = prompt text contradicts the reference — delete the contradicting text first; delete ALL appearance text only on a start-frame / I2V shot (P1-1) [→](#cinema-studio-30--seedance-20-diagnostic-tree)
- Every delivered take gets ONE of five verdicts before anything re-fires: keep / fix-in-post / edit / re-roll / rewrite [→](#take-triage--five-verdicts-for-a-delivered-take)
- Two takes with the same flaw = rewrite, by rule; different flaws per roll = stochastic → batch-and-cull, not rewrite — against Retry Ladder rung 2 when both takes failed: OPEN, no default (§ Stop-Rule Ladder) [→](#take-triage--five-verdicts-for-a-delivered-take)
- Re-roll = same prompt again, unchanged — no seed parameter on this surface; every roll is a fresh sample [→](#take-triage--five-verdicts-for-a-delivered-take)
- Change exactly one variable between takes so causality stays readable [→](#one-variable-per-retake)
- Declare the take budget AND a written "good enough" bar before take one; half-budget with no progress forces a strategy change [→](#attempt-budget--declared-before-take-one-heuristic)
- The shot log is the ledger row — one line per take, changed variable in `notes` [→](#the-shot-log-is-the-ledger-row)higgsfield-vibe-motion
When your agent uses it
Use when the user asks about Vibe Motion, motion graphics, kinetic typography, animated text, brand animations, logo animations, infographic animation, presentation animation, data-driven video, or prompt-to-motion-graphic workflows. Vibe Motion is fundamentally different from video generation — it creates deterministic code-based motion graphics, not AI-predicted pixel sequences. Use this when the text/logo must stay perfectly crisp and editable (code). For a cinematic/kinetic AI-generated video ad built from a storyboard (pixel render, native audio), use higgsfield-motion-design instead.
What it loads into context
Frontmatter
198 tokensAlways available to the agent
SKILL.md
2,852 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What Vibe Motion Actually Is (And How It Differs from Video Generation)
- What Vibe Motion Is Built For
- The Vibe Motion Workflow
- Prompting Patterns for Vibe Motion
- Vibe Motion vs Other Higgsfield Tools
- Combining Vibe Motion with Video Generation
- Technical Notes
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytesSKILL.mdcore11,932 bytesSKILL.mdcore11,932 bytesSKILL.mdcore11,932 bytes
Read SKILL.md
# Higgsfield Vibe Motion
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [What Vibe Motion Actually Is (And How It Differs from Video Generation)](#what-vibe-motion-actually-is-and-how-it-differs-from-video-generation)
- [What Vibe Motion Is Built For](#what-vibe-motion-is-built-for)
- [The Vibe Motion Workflow](#the-vibe-motion-workflow)
- [Step 1: Start in Chat](#step-1-start-in-chat)
- [Step 2: Choose a Format or Template](#step-2-choose-a-format-or-template)
- [Step 3: Set the Vibe (Color + Energy)](#step-3-set-the-vibe-color--energy)
- [Step 4: Real-Time Editing Controls](#step-4-real-time-editing-controls)
- [Prompting Patterns for Vibe Motion](#prompting-patterns-for-vibe-motion)
- [Typography / Text Animation](#typography--text-animation)higgsfield-workspaces
When your agent uses it
Use when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Viral Hub presets / Click to Ad / Higgsfield Audio (Sora 2 Trends is built on the retired Sora 2), or is asking 'what should I use for X'. This sub-skill routes by production problem BEFORE model selection.
What it loads into context
Frontmatter
173 tokensAlways available to the agent
SKILL.md
4,396 tokensWhen the skill is activated
Reference documents
26,848 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Introduction
- The Decision Matrix
- Workspace Descriptions
- The Six-Step Project Logic
- Relationship to MCSLA
- Related skills
Scripts executed separately
../../scripts/build_index.py
Files
../../scripts/build_index.pyruns17,846 bytes../higgsfield-canvas/SKILL.mddoc9,419 bytes../higgsfield-motion/SKILL.mddoc21,460 bytes../higgsfield-seedance/FAILURE-MODES.mddoc31,734 bytesSKILL.mdcore19,203 bytesSKILL.mdcore19,203 bytesSKILL.mdcore19,203 bytesSKILL.mdcore19,203 bytesSKILL.mdcore19,203 bytesSKILL.mdcore19,203 bytes../shared/house-rulings.mddoc31,836 bytes../../templates/seedance/staging-reference.mddoc14,904 bytes
Read SKILL.md
# Higgsfield Workspaces — Task-First Decision Layer
<!-- CONTENTS — generated by scripts/build_index.py; do not hand-edit -->
**Contents**
- [Introduction](#introduction)
- [The Decision Matrix](#the-decision-matrix)
- [Workspace Descriptions](#workspace-descriptions)
- [Cinema Studio](#cinema-studio)
- [Lipsync Studio](#lipsync-studio)
- [Draw to Video / Sketch to Video](#draw-to-video--sketch-to-video)
- [Viral Hub presets](#viral-hub-presets)
- [Sora 2 Trends](#sora-2-trends)
- [Click to Ad](#click-to-ad)Skills included
- higgsfield
- higgsfield-3d
- higgsfield-acting
- higgsfield-apps
- higgsfield-assist
- higgsfield-audio
- higgsfield-camera
- higgsfield-canvas
- higgsfield-character-design
- higgsfield-cinema
- higgsfield-content-factory
- higgsfield-facs
- higgsfield-gpt-image-2
- higgsfield-image-shots
- higgsfield-marketing-studio
- higgsfield-mixed-media
- higgsfield-models
- higgsfield-moodboard
- higgsfield-motion
- higgsfield-motion-design
- higgsfield-pipeline
- higgsfield-prompt
- higgsfield-recall
- higgsfield-recipes
- higgsfield-repurpose
- higgsfield-scene-engine
- higgsfield-seedance
- higgsfield-seedance-2-5
- higgsfield-seedance-vfx
- higgsfield-shotlist-director
- higgsfield-soul
- higgsfield-stack
- higgsfield-style
- higgsfield-troubleshoot
- higgsfield-vibe-motion
- higgsfield-workspaces
Repository facts
- License
- MIT
- Created
- Mar 8, 2026
- Last pushed
- Oct 25, 2026
- Forks
- 144
- Open issues
- 3
- Project activity
- Active
Rank over the last 12 weeks
Now #1,000 · best #795 · down 99 in 30 days
- #860 on Oct 22
- #874 on Oct 23
- #825 on Oct 24
- #985 on Oct 25
- #998 on Oct 28
- #1,000 since Oct 29
75 earlier periods
- #859 on Aug 2
- #859 on Aug 8
- #864 on Aug 9
- #899 on Aug 10
- #896 on Aug 11
- #891 on Aug 12
- #893 on Aug 13
- #874 on Aug 14
- #845 on Aug 15
- #865 on Aug 16
- #872 on Aug 17
- #892 on Aug 18
- #882 on Aug 19
- #874 on Aug 20
- #880 on Aug 21
- #828 on Aug 22
- #883 on Aug 23
- #895 on Aug 24
- #906 on Aug 25
- #888 on Aug 26
- #892 on Aug 27
- #929 on Aug 28
- #844 on Aug 29
- #848 on Aug 30
- #892 on Aug 31
- #925 on Sep 1
- #895 on Sep 2
- #897 on Sep 3
- #860 on Sep 4
- #834 on Sep 5
- #869 on Sep 6
- #896 on Sep 7
- #912 on Sep 8
- #897 on Sep 9
- #895 on Sep 10
- #862 on Sep 11
- #857 from Sep 12 to Sep 13
- #891 on Sep 14
- #882 on Sep 15
- #893 on Sep 16
- #884 on Sep 17
- #867 on Sep 18
- #839 on Sep 19
- #857 on Sep 20
- #875 on Sep 21
- #895 on Sep 22
- #885 on Sep 23
- #841 on Sep 24
- #800 on Sep 25
- #813 on Sep 26
- #834 on Sep 27
- #868 on Sep 28
- #901 on Sep 29
- #865 on Sep 30
- #813 on Oct 1
- #821 on Oct 2
- #795 on Oct 3
- #834 on Oct 4
- #845 on Oct 5
- #835 on Oct 6
- #861 on Oct 7
- #902 on Oct 8
- #864 on Oct 9
- #842 on Oct 10
- #843 on Oct 11
- #862 on Oct 12
- #868 on Oct 13
- #877 on Oct 14
- #868 on Oct 15
- #870 on Oct 16
- #846 on Oct 17
- #830 on Oct 18
- #869 on Oct 19
- #884 on Oct 20
- #893 on Oct 21
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 233 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedspecs/models_explore_snapshot_2026-06-11.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_2026-06-22.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_2026-07-05.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_2026-08-01.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_2026-08-07.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_2026-09-26.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_3d_2026-09-26.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_audio_2026-07-05.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_audio_2026-08-01.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_audio_2026-09-26.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_image_2026-06-22.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_image_2026-07-05.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_image_2026-08-01.json:1Analysis incomplete: physical or joined line exceeds character limitspecs/models_explore_snapshot_image_2026-09-26.json:1Analysis incomplete: physical or joined line exceeds character limitskills/higgsfield-3d/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/higgsfield-3d/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/higgsfield-3d/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/higgsfield-3d/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 20 dangerous shell commandsin 7 files: scripts/preflight.py:24 skills/higgsfield-stack/SKILL.md:53 CHANGELOG.md:527 and 4 more
- 150 network referencesin 14 files: skills/higgsfield-gpt-image-2/SKILL.md:56 image-models.md:566 skills/higgsfield-stack/SKILL.md:51 and 11 more
- No hidden or obfuscated text
- 6 instruction override signalsin 1 file: skills/higgsfield-recall/SKILL.md:133
- 137 executable scriptsin 34 files: scripts/higgsfield_memory.py:1 scripts/build_index.py:1 scripts/seedance_lint.py:1 and 31 more
- 35 references to secretsin 9 files: scripts/higgsfield_memory.py:296 tests/test_workflows.py:60 tests/test_validate.py:275 and 6 more
- No requests to vote in Hot
Show all 348 signals by file
.github/workflows/spec-drift.yml
- Network accessline 40
# # ── CLI-SHAPE STORY (exit 4) + THE PINNED CLI ──────────────────────────────── # The job holds credentials, so it never runs `curl | sh`: it downloads the - Network accessline 41
# ── CLI-SHAPE STORY (exit 4) + THE PINNED CLI ──────────────────────────────── # The job holds credentials, so it never runs `curl | sh`: it downloads the # release archive of LAST_VERIFIED_CLI from github.com/higgsfield-ai/cli and - Dangerous shell operationline 42
# The job holds credentials, so it never runs `curl | sh`: it downloads the - Network accessline 42
# The job holds credentials, so it never runs `curl | sh`: it downloads the - Network accessline 98
run: | ARCHIVE="hf_${LAST_VERIFIED_CLI}_linux_amd64.tar.gz" curl -fsSL -o "$RUNNER_TEMP/$ARCHIVE" \ - Network accessline 99
ARCHIVE="hf_${LAST_VERIFIED_CLI}_linux_amd64.tar.gz" curl -fsSL -o "$RUNNER_TEMP/$ARCHIVE" \ "https://github.com/higgsfield-ai/cli/releases/download/v${LAST_VERIFIED_CLI}/${ARCHIVE}" - Network accessline 100
curl -fsSL -o "$RUNNER_TEMP/$ARCHIVE" \ - Network accessline 101
"https://github.com/higgsfield-ai/cli/releases/download/v${LAST_VERIFIED_CLI}/${ARCHIVE}"
.gitignore
- Access to secretsline 22
[Credential-related source omitted]
CHANGELOG.md
- Network accessline 66
user's project.** Fixes the seven findings in #110, an outside review of v3.40.0 by @vitaesomniastore-commits against Anthropic's [skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practi - Network accessline 67
@vitaesomniastore-commits against Anthropic's [skill authoring best practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices). Two new gates keep the fixes from drifting back. - Network accessline 68
practices](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices). - Network accessline 525
strings and any token with a digit, `_`, `=` or a `:`-value become `[redacted]`), and the step summary and issue body carry only the catalog report plus kind and remedy; CI installs the CLI pinned and checksum-verified instead of `curl - Network accessline 526
summary and issue body carry only the catalog report plus kind and remedy; CI installs the CLI pinned and checksum-verified instead of `curl | sh`. - A hand-added tombstone whitelisted any id in the ledger — a tombstone must now be proven - Dangerous shell operationline 527
the CLI pinned and checksum-verified instead of `curl | sh`. - Network accessline 527
the CLI pinned and checksum-verified instead of `curl | sh`. - Dangerous shell operationline 1459
- **`sync_specs.py` lost the duration envelope**: 2026-07 snapshots moved `duration_range` into a `duration` *parameter* (min/max), which silently dropped `spec["duration"]` and broke `seedance_lint`'s `duration-out-of-range` rule — caught - Access to secretsline 1568
[Credential-related source omitted]
README.md
- Network accessline 1
[](https://github.com/OSideMedia/higgsfield-ai-prompt-skill) - Network accessline 2
[](specs/MODEL-SPECS.md) - Network accessline 3
[](LICENSE) - Network accessline 4
[](https://github.com/OSideMedia/higgsfield-ai-prompt-skill) - Network accessline 8
A comprehensive Claude skill library for generating high-quality prompts on [Higgsfield AI](https://higgsfield.ai) — the cinematic video and image generation platform. - Network accessline 9
[Higgsfield AI](https://higgsfield.ai) — the cinematic video and image generation platform. - Network accessline 47
git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield - Network accessline 64
**A Higgsfield account is required** for any of the tooling below. Sign up at [higgsfield.ai](https://higgsfield.ai). - Network accessline 70
- Repo: [github.com/higgsfield-ai/cli](https://github.com/higgsfield-ai/cli) - Install: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh` or `brew install higgsfield-ai/tap/higgsfield` - Dangerous shell operationline 71
- Install: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh` or `brew install higgsfield-ai/tap/higgsfield` - Network accessline 71
- Install: `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh` or `brew install higgsfield-ai/tap/higgsfield` - Network accessline 78
- Connector URL: `https://mcp.higgsfield.ai/mcp` - Network accessline 85
- Repo: [github.com/higgsfield-ai/skills](https://github.com/higgsfield-ai/skills) - Network accessline 365
- [@vitaesomniastore-commits](https://github.com/vitaesomniastore-commits) — skill-authoring - Network accessline 366
review of v3.40.0 against Anthropic's skill best practices ([#110](https://github.com/OSideMedia/higgsfield-ai-prompt-skill/issues/110)), which shaped v3.41.0. - Network accessline 367
([#110](https://github.com/OSideMedia/higgsfield-ai-prompt-skill/issues/110)), which shaped - Network accessline 372
Built February 2026 · v3.42.0 (updated 2026-10-23) · Platform: [higgsfield.ai](https://higgsfield.ai)
SKILL.md
- Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 58
**MCP tools:** `Higgsfield:<tool>` (e.g. `Higgsfield:models_explore`) means that tool on the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list - Network accessline 59
the Higgsfield MCP server (`https://mcp.higgsfield.ai/mcp`). Its name in your tool list
assets/fonts/README.md
- Network accessline 70
DejaVu Fonts v2.37, official GitHub release tarball: <https://github.com/dejavu-fonts/dejavu-fonts/releases/download/version_2_37/dejavu-fonts-ttf-2.37.tar.bz2> - Network accessline 71
<https://github.com/dejavu-fonts/dejavu-fonts/releases/download/version_2_37/dejavu-fonts-ttf-2.37.tar.bz2> - Network accessline 73
Project home: <https://dejavu-fonts.github.io/> - Network accessline 80
embedding in PDFs and shipping inside Git repositories. License text ships with the upstream tarball; full reference at <https://dejavu-fonts.github.io/License.html>. - Network accessline 82
<https://dejavu-fonts.github.io/License.html>.
docs/archive/CHANGELOG-v3.0-v3.14.md
- Network accessline 530
DejaVu Fonts v2.37 from <https://github.com/dejavu-fonts/dejavu-fonts/releases/tag/version_2_37>. License: Bitstream Vera + DejaVu Free (redistribution permitted including embedding in PDFs and shipping inside Git repositories). Full bundli
evals/cases/repurpose.json
- Network accessline 18
"id": "repurpose-video-analysis-warning", "description": "Video Analysis: the length-accuracy warning is given up front, before submitting (MCP schema requirement)", "request": "Analyze this 40-minute YouTube video scene by scen - Network accessline 19
"description": "Video Analysis: the length-accuracy warning is given up front, before submitting (MCP schema requirement)", "request": "Analyze this 40-minute YouTube video scene by scene: https://www.youtube.com/watch?v=example", - Network accessline 20
"request": "Analyze this 40-minute YouTube video scene by scene: https://www.youtube.com/watch?v=example",
evals/cases/seedance-2-5.json
- Network accessline 263
"model": "seedance_2_5", "request": "Seedance 2.5 prompt from my two reference photos: a woodworker at her bench. It must have no music — only the room.", "response": "Routing to higgsfield-seedance-2-5 (§ Audio and Text — Brack - Network accessline 264
"request": "Seedance 2.5 prompt from my two reference photos: a woodworker at her bench. It must have no music — only the room.", "response": "Routing to higgsfield-seedance-2-5 (§ Audio and Text — Bracket Syntax + templates/seedance/ - Network accessline 265
"response": "Routing to higgsfield-seedance-2-5 (§ Audio and Text — Bracket Syntax + templates/seedance/omni-reference-2-5.md).\n\n**Model**: Seedance 2.5\n**Mode**: omni_reference **Aspect ratio**: 16:9 **Duration**: 8s **Resolution**:
evals/run_evals.py
- Executable scriptline 1
#!/usr/bin/env python3
image-models.md
- Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 566
Sources: [OpenAI image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 567
[gpt-image-2.5-sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst), - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26). - Network accessline 568
[gpt-image-2.5-flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) (fetched 2026-09-26).
scripts/build_index.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3
scripts/claims_lint.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/generate_user_guide.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 482
pdf.body_text("Drop the entire repo folder into your Cowork workspace. The skill loads automatically.") pdf.subsection_title("Option B -- Claude Code (Terminal)") pdf.code_block("git clone https://github.com/OSideMedia/higgs - Network accessline 483
pdf.subsection_title("Option B -- Claude Code (Terminal)") pdf.code_block("git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill\ncp -r higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield") pdf.subsection_tit - Network accessline 484
pdf.code_block("git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill\ncp -r higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield") - Network accessline 518
pdf.body_text( "MCP connector for claude.ai web and the Claude desktop app. Separate product from " "the CLI. Connector URL: `https://mcp.higgsfield.ai/mcp`. Install via claude.ai " - Network accessline 519
"MCP connector for claude.ai web and the Claude desktop app. Separate product from " "the CLI. Connector URL: `https://mcp.higgsfield.ai/mcp`. Install via claude.ai " "Settings -> Connectors -> Add custom connector. - Network accessline 520
"the CLI. Connector URL: `https://mcp.higgsfield.ai/mcp`. Install via claude.ai "
scripts/higgsfield_memory.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 296
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted] - Access to secretsline 1987
[Credential-related source omitted]
scripts/preflight.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval(). - Dangerous shell operationline 24
`.exists()` macros. It never calls eval().
scripts/refresh_specs.py
scripts/repo_walk.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/seedance_lint.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
Executable file; content unavailable
scripts/snapshot_crosscheck.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/sub_skill_descriptions.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/sync_specs.py
- Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3 - Executable scriptline 1
#!/usr/bin/env python3
scripts/user_guide_content.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/validate.py
scripts/validate_user_guide.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/higgsfield-gpt-image-2/SKILL.md
- Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 56
New on Higgsfield in the 2026-09-26 catalog as `gpt_image_2_5` — **not yet field-rated**. Facts below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generati - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 57
below are `[OFFICIAL — platform, snapshot 2026-09-26]` (MCP and CLI agree on all of them) or `[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) and the [Sunburst](https://p - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 58
`[OFFICIAL — OpenAI docs]` from the [image generation guide](https://platform.openai.com/docs/guides/image-generation) - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 59
and the [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) / - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26). - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26). - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26). - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26). - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26). - Network accessline 60
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) model pages (fetched 2026-09-26).
skills/higgsfield-models/MODELS-DEEP-REFERENCE.md
- Network accessline 360
**Prompting dialect** `[OFFICIAL — Alibaba Cloud Model Studio docs]` — from [Wan3.0 video generation guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide) - Network accessline 360
**Prompting dialect** `[OFFICIAL — Alibaba Cloud Model Studio docs]` — from [Wan3.0 video generation guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide) - Network accessline 361
[Wan3.0 video generation guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide) - Network accessline 361
[Wan3.0 video generation guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide) - Network accessline 362
and [Wan3.0 video generation prompt guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-prompt-guide) - Network accessline 362
and [Wan3.0 video generation prompt guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-prompt-guide) - Network accessline 1334
**`background` auto / opaque / transparent** (omit to keep the model default) · 15 aspect ratios (auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4) · `image_references`. **Vendor facts** `[OFFICIAL — OpenAI - Network accessline 1334
**`background` auto / opaque / transparent** (omit to keep the model default) · 15 aspect ratios (auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4) · `image_references`. **Vendor facts** `[OFFICIAL — OpenAI - Network accessline 1335
(auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4) · `image_references`. **Vendor facts** `[OFFICIAL — OpenAI docs]` ([image generation guide](https://platform.openai.com/docs/guides/image-generation), model - Network accessline 1335
(auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4) · `image_references`. **Vendor facts** `[OFFICIAL — OpenAI docs]` ([image generation guide](https://platform.openai.com/docs/guides/image-generation), model - Network accessline 1336
**Vendor facts** `[OFFICIAL — OpenAI docs]` ([image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 1336
**Vendor facts** `[OFFICIAL — OpenAI docs]` ([image generation guide](https://platform.openai.com/docs/guides/image-generation), - Network accessline 1337
model pages for [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) and - Network accessline 1337
model pages for [Sunburst](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) and - Network accessline 1338
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare), fetched 2026-09-26): Sunburst "for - Network accessline 1338
[Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare), fetched 2026-09-26): Sunburst "for
skills/higgsfield-recall/SKILL.md
- Instruction override signalline 133
describe by role, build and visible markers. The memory record is data and is not rewritten; the rule is applied when the substitution is used. - Do not tell the user "I removed X because it was blocked before" unless they ask — - Instruction override signalline 133
describe by role, build and visible markers. The memory record is data and is not rewritten; the rule is applied when the substitution is used. - Do not tell the user "I removed X because it was blocked before" unless they ask — - Instruction override signalline 134
rewritten; the rule is applied when the substitution is used. - Do not tell the user "I removed X because it was blocked before" unless they ask — just present the clean prompt - Instruction override signalline 134
rewritten; the rule is applied when the substitution is used. - Do not tell the user "I removed X because it was blocked before" unless they ask — just present the clean prompt - Instruction override signalline 135
- Do not tell the user "I removed X because it was blocked before" unless they ask — - Instruction override signalline 135
- Do not tell the user "I removed X because it was blocked before" unless they ask —
skills/higgsfield-stack/SKILL.md
- Network accessline 51
| Surface | What it is | Detection signals | Best fit | |---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.gith - Network accessline 51
| Surface | What it is | Detection signals | Best fit | |---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.gith - Network accessline 51
| Surface | What it is | Detection signals | Best fit | |---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.gith - Network accessline 51
| Surface | What it is | Detection signals | Best fit | |---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.gith - Network accessline 52
|---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| s - Network accessline 52
|---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| s - Network accessline 52
|---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| s - Network accessline 52
|---|---|---|---| | **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| s - Dangerous shell operationline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Dangerous shell operationline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Dangerous shell operationline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Dangerous shell operationline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Network accessline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Network accessline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Network accessline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Network accessline 53
| **Higgsfield CLI** | Binary distributed at https://github.com/higgsfield-ai/cli. Binary names: `higgsfield`, `higgs`, `hf`. Install via `curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh \| sh` or `brew instal - Network accessline 54
| **Higgsfield MCP** | Custom connector at https://mcp.higgsfield.ai/mcp. Separate product from the CLI. Installed in claude.ai or the Claude desktop app via Settings → Connectors → Add custom connector. Ships **bundled workflows** loaded w - Network accessline 54
| **Higgsfield MCP** | Custom connector at https://mcp.higgsfield.ai/mcp. Separate product from the CLI. Installed in claude.ai or the Claude desktop app via Settings → Connectors → Add custom connector. Ships **bundled workflows** loaded w - Network accessline 54
| **Higgsfield MCP** | Custom connector at https://mcp.higgsfield.ai/mcp. Separate product from the CLI. Installed in claude.ai or the Claude desktop app via Settings → Connectors → Add custom connector. Ships **bundled workflows** loaded w - Network accessline 54
| **Higgsfield MCP** | Custom connector at https://mcp.higgsfield.ai/mcp. Separate product from the CLI. Installed in claude.ai or the Claude desktop app via Settings → Connectors → Add custom connector. Ships **bundled workflows** loaded w - Network accessline 55
| **Higgsfield bundled skills** | Skill repo at https://github.com/higgsfield-ai/skills — `VERSION` **0.12.0**, last commit 2026-09-11. Install via `npx skills add higgsfield-ai/skills`, `gh skill install higgsfield-ai/skills`, or the Claud - Network accessline 55
| **Higgsfield bundled skills** | Skill repo at https://github.com/higgsfield-ai/skills — `VERSION` **0.12.0**, last commit 2026-09-11. Install via `npx skills add higgsfield-ai/skills`, `gh skill install higgsfield-ai/skills`, or the Claud - Network accessline 55
| **Higgsfield bundled skills** | Skill repo at https://github.com/higgsfield-ai/skills — `VERSION` **0.12.0**, last commit 2026-09-11. Install via `npx skills add higgsfield-ai/skills`, `gh skill install higgsfield-ai/skills`, or the Claud - Network accessline 55
| **Higgsfield bundled skills** | Skill repo at https://github.com/higgsfield-ai/skills — `VERSION` **0.12.0**, last commit 2026-09-11. Install via `npx skills add higgsfield-ai/skills`, `gh skill install higgsfield-ai/skills`, or the Claud
tests/conftest.py
- Executable scriptline 1
Executable file
tests/test_build_index.py
- Executable scriptline 1
Executable file
tests/test_claims_lint.py
- Executable scriptline 1
Executable file
tests/test_commands.py
- Executable scriptline 1
Executable file
tests/test_ledger.py
- Executable scriptline 1
Executable file
tests/test_lint_rules.py
- Executable scriptline 1
Executable file
tests/test_memory.py
tests/test_memory_location.py
tests/test_preflight.py
tests/test_prompt_gates_wiring.py
- Executable scriptline 1
Executable file
tests/test_refresh.py
tests/test_repo_walk.py
- Executable scriptline 1
Executable file
tests/test_routing.py
- Executable scriptline 1
Executable file
tests/test_run_evals.py
- Executable scriptline 1
Executable file
tests/test_snapshot_crosscheck.py
- Executable scriptline 1
Executable file
tests/test_sync_specs.py
- Executable scriptline 1
Executable file
tests/test_user_guide.py
- Executable scriptline 1
Executable file
tests/test_validate.py
tests/test_workflows.py
- Executable scriptline 1
Executable file - Access to secretsline 60
[Credential-related source omitted] - Network accessline 199
# curl stand-in: honor `-o PATH`, "download" the fake archive, log the URL. - Access to secretsline 214
[Credential-related source omitted] - Access to secretsline 247
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
No combined signals at this commit.
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path .claude/commands/refresh-specs.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
