Menu

Not in the top 1,000 by GitHub stars

ZSeven-W/craft-skills

Research-backed, eval-driven skills for AI agents

DesignResearch

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

skills/logo-semantic-fusion/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 01c8ffe0bc94

No earlier version was observed for comparison.

Compare on GitHub

skills/native-transparent-imagegen/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 01c8ffe0bc94

No earlier version was observed for comparison.

Compare on GitHub

skills/qwen-image-gen/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 01c8ffe0bc94

No earlier version was observed for comparison.

Compare on GitHub

skills/recurring-character-diary-comic/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 01c8ffe0bc94

No earlier version was observed for comparison.

Compare on GitHub

skills/single-path-process-diorama/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 01c8ffe0bc94

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 01c8ffe0bc94cfe1dbfc7e1de537399253d04f39

240GitHub stars
4stars in 7 days
5skills in this repository
0commits in 30 days

Heat

3.1
  • 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

Oct 25, 2026Nov 5, 2026240

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

logo-semantic-fusion

When your agent uses it

Develop and evaluate logo concepts when the explicit design problem is semantic fusion: two or more brand meanings must share a contour, stroke, negative space, glyph skeleton, or shape system. Use for fusion-focused design or redesign, critique, comparison, or prompt-only work on a logo, symbol, app icon, monogram, or wordmark. Do not use for generic logo creation, general identity systems, illustration, packaging, or type selection unless semantic fusion is a stated or clearly central requirement.

What it loads into context

Frontmatter

109 tokens

Always available to the agent

SKILL.md

1,296 tokens

When the skill is activated

Reference documents

2,876 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Route the references
  2. Choose one mode
  3. Run the applicability gate
  4. Establish the brief
  5. Inventory semantics and screen prior art
  6. Generate distinct concept families
  7. Select before polishing
  8. Render in controlled passes
  9. Verify the actual artifact
  10. Hand off proportionately
  11. Deliver by mode

Files

  • README.en.mddoc687 bytes
  • README.mddoc854 bytes
  • SKILL.mdcore6,723 bytes
  • SKILL.mdcore6,723 bytes
  • agents/openai.yamlasset289 bytes
  • references/concept-methods.mddoc5,143 bytes
  • references/review-checklist.mddoc5,924 bytes
  • references/source-notes.mddoc1,364 bytes
Read SKILL.md

# Logo Semantic Fusion

Build one structurally shared idea. Do not force fusion when a simpler wordmark, single symbol, or broader identity system serves the brand better.

## Route the references

- Read [references/concept-methods.md](references/concept-methods.md) before designing or substantially redesigning a mark.
- Read [references/review-checklist.md](references/review-checklist.md) before scoring, comparing, or accepting a visual result.
- Read [references/source-notes.md](references/source-notes.md) only to explain provenance or resolve an ambiguous method.

## Choose one mode

- **Design or redesign:** Run the full workflow. Preserve stated redesign invariants before exploring.
- **Critique:** Inspect the supplied artifact and report evidence, hard-gate failures, and the smallest useful revisions. Do not redesign unless asked.
View the complete source on GitHub

Skills included

  • logo-semantic-fusion
  • native-transparent-imagegen
  • qwen-image-gen
  • recurring-character-diary-comic
  • single-path-process-diorama

Repository facts

License
Apache-2.0
Created
Aug 3, 2026
Last pushed
Sep 22, 2026
Forks
35
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 5 notes
  • skills/logo-semantic-fusion/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/native-transparent-imagegen/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/native-transparent-imagegen/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/recurring-character-diary-comic/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/recurring-character-diary-comic/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 38 signals by file

skills/logo-semantic-fusion/references/source-notes.md

  • Network accessline 7
    - <https://www.douyin.com/video/7662579006969005233>
  • Network accessline 8
    - <https://www.douyin.com/video/7663327822182056165>
  • Network accessline 9
    - <https://www.douyin.com/video/7664821149108509819>
  • Network accessline 10
    - <https://www.douyin.com/video/7665168753902645669>
  • Network accessline 11
    - <https://www.douyin.com/video/7665546888943006713>
  • Network accessline 12
    - <https://www.douyin.com/video/7661837486923013489>

skills/native-transparent-imagegen/README.en.md

  • Network accessline 70
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/native-transparent-imagegen/README.md

  • Network accessline 63
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/native-transparent-imagegen/scripts/validate_alpha.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/qwen-image-gen/README.en.md

  • Network accessline 36
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/qwen-image-gen/README.md

  • Network accessline 36
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/qwen-image-gen/references/tested-behavior.md

  • Network accessline 27
    - [PE-T2I](https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I)：模板revision `f3ed7985c788ad75b3ab7223e0c4c51e2a43545b`；SHA256 `a77c9a06c59b120741141d9514b95682bb8761d02bec49ca61def7b2b3d9fb99`。
  • Network accessline 28
    - [PE-I2I](https://huggingface.co/Qwen/Qwen-Image-2.1-PE-I2I)：模板revision `72927bc08afc99b7888ceb7d7d51a12db3700bbd`；SHA256 `e378fea686a1431581ba4c654d332ae96adad633f144ae738ec8ce9c4fd66439`。
  • Network accessline 29
    - [官方prompt_rewrite实现](https://github.com/QwenLM/Qwen-Image-2.1/tree/main/prompt_rewrite)：公开输出契约及解析逻辑。官方模板/权重按其Qwen Research许可使用；本Skill不附带这些原文或权重。

skills/qwen-image-gen/runtime/core.mjs

  • Executable scriptline 1
    Executable file

skills/qwen-image-gen/scripts/prepare_workbench_request.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/qwen-image-gen/tests/test_prepare_request.py

  • Executable scriptline 1
    Executable file
  • Possible obfuscationline 49
    raw = base64.b64decode('iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO+jFocAAAAASUVORK5CYII=')
  • Possible obfuscationline 53
    self.assertEqual(base64.b64decode(body['image'].split(',')[1]), raw)
  • Access to secretsline 76
    [Credential-related source omitted]

skills/qwen-image-gen/tests/test_runtime.mjs

  • Executable scriptline 1
    Executable file

skills/recurring-character-diary-comic/README.en.md

  • Network accessline 39
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/recurring-character-diary-comic/README.md

  • Network accessline 63
    git clone https://github.com/ZSeven-W/craft-skills.git

skills/recurring-character-diary-comic/references/visual-task-contract.md

  • Network accessline 4
    identity, cross-panel continuity, directional objects, or physical causality. It applies the useful part of [Context Scaling](https://heheyas.github.io/context-scaling/)—a small set of
  • Network accessline 5
    It applies the useful part of [Context Scaling](https://heheyas.github.io/context-scaling/)—a small set of addressable facts connected to rendered evidence—without introducing a
  • Network accessline 6
    [Context Scaling](https://heheyas.github.io/context-scaling/)—a small set of
  • Network accessline 7
    addressable facts connected to rendered evidence—without introducing a universal design schema. See also the [research paper](https://arxiv.org/abs/2607.29679).
  • Network accessline 9
    [research paper](https://arxiv.org/abs/2607.29679).

skills/recurring-character-diary-comic/scripts/compose_panels.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/recurring-character-diary-comic/scripts/self_test_compositor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/single-path-process-diorama/LICENSE

  • Network accessline 1
    Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/
  • Network accessline 3
    http://www.apache.org/licenses/
  • Network accessline 195
    http://www.apache.org/licenses/LICENSE-2.0

skills/single-path-process-diorama/README.en.md

  • Network accessline 44
    git clone https://github.com/ZSeven-W/craft-skills.git craft-skills-diorama

skills/single-path-process-diorama/README.md

  • Network accessline 63
    git clone https://github.com/ZSeven-W/craft-skills.git craft-skills-diorama

skills/single-path-process-diorama/scripts/verify_delivery.py

  • Executable scriptline 1
    #!/usr/bin/env python3

skills/single-path-process-diorama/tests/test_verify_delivery.py

  • Executable scriptline 1
    Executable file
  • Possible obfuscationline 34
    palette = chunk(b"PLTE", b"\x00\x00\x00\xff\xff\xff") if color == 3 else b""

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.

Signal confidence: 35 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/logo-semantic-fusion/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/logo-semantic-fusion/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/logo-semantic-fusion/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/logo-semantic-fusion/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/logo-semantic-fusion/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/logo-semantic-fusion/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.

You might also use

tw93/Waza

🥷 Engineering habits you already know, turned into skills AI assistants like Claude Code, Codex and Cursor can run.

7.5kGitHub stars

FrancyJGLisboa/agent-skills-platform

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

2.4kGitHub stars

adityareddy-dev/deskstudio

Your own design studio inside the coding agent you already use.

43GitHub stars

Illyism/dev-skills

Developer and product skills for Claude Code, Cursor and Codex: 1-file AI evals and Chrome extension store assets.

21GitHub stars

aiopshwang/goal-to-proof

Make AI agents finish authorized, non-trivial work and prove the requested outcome with direct, scope-matched evidence.

11GitHub stars

Leonxlnx/taste-skill

tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals rese…

111.3kGitHub stars