#728 by GitHub stars
AI-Builder-Club/skills
Codebase harness + loop engineer
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/agent-context-audit/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/crabbox-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/dev-local-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/e2e-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/karaoke-captions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/new-loop/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/open-agent-teams/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/seo-growth/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/setup-codebase-harness/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/verifier-setup/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/visual-flow-gif/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
917780c39259 → 917780c39259
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Verified commit 917780c3925919fb2a4ba7b1ac2439a3f4ab5d17
git clone --filter=blob:none --no-checkout https://github.com/AI-Builder-Club/skills.git .hotskills/ai-builder-club-skills && git -C .hotskills/ai-builder-club-skills checkout --detach 917780c3925919fb2a4ba7b1ac2439a3f4ab5d17
# Copy each selected skill directory from .hotskills/ai-builder-club-skills into .claude/skills/<skill-name>/Heat
1.5- Star growth, last 7 daysAhead of 36% of tracked repositories
- Star growth, last 24 hoursAhead of 3% of tracked repositories
- Rank movement, last 7 daysAhead of 4% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- agent-context-audit
skills/agent-context-audit - crabbox-setup
skills/crabbox-setup - dev-local-setup
skills/dev-local-setup - e2e-setup
skills/e2e-setup - karaoke-captions
skills/karaoke-captions - new-loop
skills/new-loop - open-agent-teams
skills/open-agent-teams - seo-growth
skills/seo-growth - setup-codebase-harness
skills/setup-codebase-harness - verifier-setup
skills/verifier-setup - visual-flow-gif
skills/visual-flow-gif
How it works
agent-context-audit
When your agent uses it
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting instructions, redundancy, stale facts, and missing "unknown knowns"; produces a scored findings report with concrete rewrites, then applies approved fixes. Use when someone says "audit my CLAUDE.md", "context audit", "unhobble this repo", "review our agent docs/skills/tools", or after upgrading to Claude 5-generation models.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
2,084 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
- The six shifts (the audit rubric)
- Step 0 — Inventory the context surface
- Step 1 — Audit each artifact against the rubric
- Step 2 — Probe for unknowns (the gaps docs don't show)
- Step 3 — Report
- Step 4 — Apply (with approval)
- Anti-patterns for the auditor
Files
../../.claude-plugin/marketplace.jsonasset645 bytes../../.claude-plugin/plugin.jsonasset918 bytesSKILL.mdcore8,784 bytesSKILL.mdcore8,784 bytesSKILL.mdcore8,784 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcrabbox-setup
When your agent uses it
Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state. Sets up the snapshot image, .crabbox.yaml, an idempotent setup.sh (also boots the stack locally), and a cbx.sh wrapper. Use when the user says "set up crabbox", "give each agent its own box", "add cloud testing", "make this repo testable in the cloud / on Daytona", "parallel-test this", or when setup-codebase-harness needs true per-agent isolation.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
2,146 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
- Step 0 — Discover (reuse dev-local, don't re-derive)
- Step 1 — `devbox/Dockerfile`
- Step 2 — Build the snapshot (user runs `daytona login` first)
- Step 3 — `.crabbox.yaml`
- Step 4 — `setup.sh` (boots the stack on the box AND locally)
- Step 5 — `cbx.sh` + browser config
- Step 6 — gitignore + commit (required for fast sync)
- Step 7 — Verify (run the e2e suite on the box)
- Gotchas — each cost a debugging round
- Optional (advanced) — pre-bake service images
- Other providers (brief)
Scripts executed separately
assets/Dockerfileassets/cbx.shassets/setup.sh
Files
SKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesSKILL.mdcore7,856 bytesassets/Dockerfileruns3,301 bytesassets/cbx.shruns4,519 bytesassets/cli.config.jsonasset192 bytesassets/crabbox.yamlasset745 bytesassets/setup.shruns4,446 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdev-local-setup
When your agent uses it
Scaffold a one-command `dev-local` launcher for ANY codebase. Investigates the repo to find its services, ports, and infra dependencies, then generates a single `scripts/dev-local.sh` (up/down/status/logs/restart) that runs every dev server in one tmux session, plus a short skill doc describing it. Use when someone says "set up dev-local", "make a one-command dev launcher", "I want one script to start this repo", "scaffold dev-local for this project".
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
1,313 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
- Step 1 — Investigate the repo (don't guess)
- Step 2 — Generate `scripts/dev-local.sh`
- Step 3 — Write a short skill doc
- Step 4 — Hand off
- Principles
Scripts executed separately
assets/dev-local.template.sh
Files
SKILL.mdcore5,130 bytesSKILL.mdcore5,130 bytesassets/dev-local.template.shruns6,012 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHube2e-setup
When your agent uses it
Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add end-to-end tests", "scaffold a test gate".
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
987 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
- Where it lives
- The recipe
- Practices that make e2e trustworthy
- When a test fails: triage before "fixing"
- External services (payments, email, 3rd-party)
Files
SKILL.mdcore3,846 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubkaraoke-captions
When your agent uses it
Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass. Use when burning word-level highlight captions into a video, matching caption style from a screenshot, rendering ASS karaoke subtitles, or when the user runs /karaoke-captions.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
844 tokensWhen the skill is activated
Reference documents
1,331 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Requirements
- File Architecture
- Standard Workflow
- References & Presets
Scripts executed separately
scripts/extract_words.pyscripts/gen_ass.pyscripts/match_style_from_image.pyscripts/render.sh
Files
.gitignoreasset269 bytesREADME.mddoc1,771 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytesSKILL.mdcore3,400 bytespresets/style.jsonasset369 bytespresets/yellow.jsonasset369 bytesreferences/style-guide.mddoc2,762 bytesrequirements.txtdoc25 bytesscripts/extract_words.pyruns2,046 bytesscripts/gen_ass.pyruns7,515 bytesscripts/match_style_from_image.pyruns4,351 bytesscripts/render.shruns1,328 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubnew-loop
When your agent uses it
Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop>/README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new loop", "create a domain", "start a new beat/workstream", or names a recurring job they want the agent to own.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
1,282 tokensWhen the skill is activated
Reference documents
5,444 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Inputs to gather (ask only what's missing)
- Procedure
- Notes
Files
SKILL.mdcore4,981 bytesreferences/ARCHITECTURE.mddoc7,309 bytesreferences/CLAUDE.template.mddoc5,324 bytesreferences/KNOWLEDGE_SETUP.mddoc7,354 bytesreferences/LOG.mddoc988 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubopen-agent-teams
When your agent uses it
Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate to codex/aider", or when executor work should run in an observable background terminal instead of the Agent tool.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
1,383 tokensWhen the skill is activated
Reference documents
403 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Initial setup (once per repo)
- Workflow
- Harness reference
- Rules
Scripts executed separately
scripts/tdel
Files
SKILL.mdcore5,507 bytesSKILL.mdcore5,507 bytesreferences/CLAUDE.delegation-template.mddoc1,829 bytesscripts/tdelruns5,623 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubseo-growth
When your agent uses it
Use when deciding WHERE to point SEO effort, not how to write a page. Triggers: a new site or brand with no rankings and no authority ("cold start", "starting from zero", "nobody knows us"), deciding what to double down on, a page or cluster that ranks but earns nothing, hunting emerging or newly-coined keywords before competitors arrive, "should we build a cluster or one page", "what do we write next", "we get impressions but no clicks", "our traffic plateaued despite publishing", whether to chase a head term at all, or turning any of it into recurring automation. Also use when asked why an SEO effort stalled despite consistent output. NOT for writing an article, keyword expansion mechanics, or auditing a single tactic for penalty risk.
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
1,802 tokensWhen the skill is activated
Reference documents
11,047 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The two playbooks
- Read alongside either playbook
- Before advising anything: get three numbers
- The five laws
- Quick reference
- Common mistakes
- Scope honesty
- What this skill deliberately does not cover
- Companion skills in this plugin
Files
SKILL.mdcore7,699 bytesassets/seo-loop-template.mddoc7,055 bytesreferences/cold-start.mddoc5,599 bytesreferences/emerging-terms.mddoc6,700 bytesreferences/measurement.mddoc6,110 bytesreferences/operationalize.mddoc4,029 bytesreferences/why-these-rules.mddoc8,175 bytesreferences/with-data.mddoc9,307 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsetup-codebase-harness
When your agent uses it
Master skill — set up the full agent harness for any repo so an agent can work it reliably: legible (map-not-manual docs + custom lints), executable (one-command dev stack), verifiable (e2e gate + a verify-before-ship loop), plus commit hygiene and entropy control. Use when onboarding a new/unfamiliar codebase to agent-driven development — "set up the harness", "make this repo agent-ready", "harness this codebase".
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
1,438 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
- 0. Assess
- 1. Legible — the agent can reason about the repo
- 2. Executable — the agent can run & drive the app
- 3. Verifiable — the agent can prove it works
- 4. Others — keep it coherent over time
- Order & what you leave behind
Files
SKILL.mdcore5,723 bytesSKILL.mdcore5,723 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubverifier-setup
When your agent uses it
Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-local` skill + script, and the installed driver skill. Use when someone says "set up verification", "make this repo verifiable", "scaffold a verify skill", "set up the verifier".
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
2,116 tokensWhen the skill is activated
Reference documents
1,253 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What this produces (the outputs)
- Step 0 — Inventory what already exists (check before you add ANYTHING)
- Step 1 — Investigate the repo (don't guess)
- Step 2 — Ensure the prerequisites exist (reuse-or-provide, per the Step 0 inventory)
- Step 3 — Ask the user: local or sandbox?
- Step 4 — Confirm the driver
- Step 5 — Generate `.claude/skills/verify/SKILL.md`
- Step 6 — Hand off
- Principles
Files
SKILL.mdcore8,426 bytesSKILL.mdcore8,426 bytesSKILL.mdcore8,426 bytesassets/verify.template.mddoc4,896 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvisual-flow-gif
When your agent uses it
Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
759 tokensWhen the skill is activated
Reference documents
1,107 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Style Guide
- Quality Bar
Scripts executed separately
scripts/render_animated_gif.py
Files
SKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesSKILL.mdcore3,377 bytesassets/dark-spec.jsonasset6,983 bytesassets/default-spec.jsonasset6,984 bytesreferences/spec-format.mddoc3,791 bytesrequirements.txtdoc15 bytesscripts/render_animated_gif.pyruns26,262 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- agent-context-audit
- crabbox-setup
- dev-local-setup
- e2e-setup
- karaoke-captions
- new-loop
- open-agent-teams
- seo-growth
- setup-codebase-harness
- verifier-setup
- visual-flow-gif
Repository facts
- License
- No license detected
- Created
- Jun 14, 2026
- Last pushed
- Sep 15, 2026
- Forks
- 155
- Open issues
- 0
- Project activity
- Active
Rank over the last 12 weeks
Now #728 · best #501 · down 118 in 30 days
- #708 on Nov 1
- #713 on Nov 2
- #716 on Nov 3
- #721 from Nov 4 to Nov 5
- #725 on Nov 6
- #728 since Nov 7
67 earlier periods
- #493 on Aug 2
- #491 on Aug 8
- #493 on Aug 9
- #513 on Aug 10
- #510 on Aug 11
- #508 on Aug 12
- #511 from Aug 13 to Aug 14
- #493 on Aug 15
- #502 on Aug 16
- #505 on Aug 17
- #522 on Aug 18
- #515 from Aug 19 to Aug 20
- #501 on Aug 22
- #523 on Aug 23
- #527 on Aug 24
- #536 on Aug 25
- #525 on Aug 26
- #536 on Aug 27
- #534 on Aug 28
- #517 on Aug 29
- #508 on Aug 30
- #534 on Aug 31
- #539 on Sep 1
- #534 on Sep 2
- #540 on Sep 3
- #522 on Sep 4
- #533 on Sep 6
- #538 on Sep 7
- #555 on Sep 8
- #538 on Sep 9
- #547 on Sep 10
- #540 on Sep 11
- #537 on Sep 13
- #557 on Sep 14
- #543 on Sep 15
- #551 on Sep 17
- #555 on Sep 18
- #542 on Sep 19
- #552 on Sep 20
- #560 on Sep 21
- #568 on Sep 22
- #564 on Sep 23
- #550 on Sep 24
- #545 on Sep 25
- #546 on Sep 26
- #565 on Sep 27
- #590 on Sep 29
- #580 on Sep 30
- #562 on Oct 4
- #571 on Oct 5
- #586 on Oct 7
- #610 on Oct 8
- #582 on Oct 10
- #585 on Oct 11
- #600 on Oct 12
- #615 on Oct 14
- #620 on Oct 16
- #602 on Oct 18
- #630 on Oct 19
- #638 on Oct 20
- #645 on Oct 21
- #626 on Oct 23
- #692 on Oct 25
- #698 on Oct 28
- #700 on Oct 29
- #701 on Oct 30
- #705 on Oct 31
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 40 notes
skills/agent-context-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/agent-context-audit/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/crabbox-setup/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 11 dangerous shell commandsin 4 files: crabbox-setup/assets/Dockerfile:14 crabbox-setup/assets/setup.sh:33 crabbox-setup/assets/cbx.sh:67 and 1 more
- 33 network referencesin 9 files: crabbox-setup/assets/Dockerfile:14 .claude-plugin/plugin.json:5 crabbox-setup/assets/setup.sh:70 and 6 more
- No hidden or obfuscated text
- 3 instruction override signalsin 1 file: open-agent-teams/SKILL.md:50
- 10 executable scriptsin 10 files: crabbox-setup/assets/Dockerfile:1 crabbox-setup/assets/cbx.sh:1 crabbox-setup/assets/setup.sh:1 and 7 more
- 11 references to secretsin 4 files: crabbox-setup/assets/setup.sh:43 crabbox-setup/assets/cbx.sh:23 crabbox-setup/assets/crabbox.yaml:15 and 1 more
- No requests to vote in Hot
Show all 68 signals by file
.claude-plugin/marketplace.json
- Network accessline 3
"owner": { "name": "AI Builder Club (Jason Zhou)", "url": "https://www.aibuilderclub.com/lp/loop-engineer" - Network accessline 4
"name": "AI Builder Club (Jason Zhou)", "url": "https://www.aibuilderclub.com/lp/loop-engineer" }, - Network accessline 5
"url": "https://www.aibuilderclub.com/lp/loop-engineer"
.claude-plugin/plugin.json
- Network accessline 5
"author": { "name": "Jason Zhou (AI Jason)", "url": "https://www.aibuilderclub.com/lp/loop-engineer" - Network accessline 6
"name": "Jason Zhou (AI Jason)", "url": "https://www.aibuilderclub.com/lp/loop-engineer" }, - Network accessline 7
"url": "https://www.aibuilderclub.com/lp/loop-engineer" - Network accessline 8
}, "homepage": "https://github.com/AI-Builder-Club/skills", "license": "MIT", - Network accessline 9
"homepage": "https://github.com/AI-Builder-Club/skills",
skills/crabbox-setup/SKILL.md
- Network accessline 92
bash cbx.sh up demo # → ✓ STACK READY # run the repo's e2e specs against the box's stack (from e2e-setup): bash cbx.sh pw demo -- open http://localhost:<APP_PORT> # smoke, or: - Network accessline 93
# run the repo's e2e specs against the box's stack (from e2e-setup): bash cbx.sh pw demo -- open http://localhost:<APP_PORT> # smoke, or: # sync an e2e runner and: crabbox run --id $(cat .cbx-demo.id) -- <your e2e cmd> - Network accessline 94
bash cbx.sh pw demo -- open http://localhost:<APP_PORT> # smoke, or:
skills/crabbox-setup/assets/Dockerfile
- Executable scriptline 1
Executable file - Dangerous shell operationline 14
RUN apt-get update && apt-get install -y --no-install-recommends ca-certificates curl gnupg git jq lsof procps sudo iptables - Network accessline 14
RUN apt-get update && apt-get install -y --no-install-recommends \ ca-certificates curl gnupg git jq lsof procps sudo iptables \ - Dangerous shell operationline 15
ca-certificates curl gnupg git jq lsof procps sudo iptables \ - Network accessline 15
ca-certificates curl gnupg git jq lsof procps sudo iptables \ - Dangerous shell operationline 16
&& rm -rf /var/lib/apt/lists/* - Network accessline 23
ARG DOCKER_VERSION=27.0.3 RUN curl -fsSL "https://download.docker.com/linux/static/stable/x86_64/docker-${DOCKER_VERSION}.tgz" -o /tmp/docker.tgz \ - Dangerous shell operationline 24
RUN curl -fsSL "https://download.docker.com/linux/static/stable/x86_64/docker-${DOCKER_VERSION}.tgz" -o /tmp/docker.tgz && tar -xzf /tmp/docker.tgz -C /usr/local/bin --strip-components=1 && rm /tmp/docker.tgz - Network accessline 24
RUN curl -fsSL "https://download.docker.com/linux/static/stable/x86_64/docker-${DOCKER_VERSION}.tgz" -o /tmp/docker.tgz \ - Dangerous shell operationline 26
&& rm /tmp/docker.tgz \ - Network accessline 36
# EDIT/DROP: service CLI your stack needs, e.g. the Supabase CLI: # ARG SUPABASE_CLI_VERSION=v2.105.0 # RUN curl -fsSL "https://github.com/supabase/cli/releases/download/${SUPABASE_CLI_VERSION}/supabase_linux_amd64.tar.gz" \ - Network accessline 37
# ARG SUPABASE_CLI_VERSION=v2.105.0 # RUN curl -fsSL "https://github.com/supabase/cli/releases/download/${SUPABASE_CLI_VERSION}/supabase_linux_amd64.tar.gz" \ # | tar xz -C /usr/local/bin && supabase --version - Network accessline 38
# RUN curl -fsSL "https://github.com/supabase/cli/releases/download/${SUPABASE_CLI_VERSION}/supabase_linux_amd64.tar.gz" # | tar xz -C /usr/local/bin && supabase --version
skills/crabbox-setup/assets/cbx.sh
- Executable scriptline 1
#!/usr/bin/env bash - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 24
[Credential-related source omitted] - Network accessline 64
[ -n "$SSH" ] || { echo "✗ no ssh command for $ID"; exit 1; } L=""; for p in $TUNNEL_PORTS; do L="$L -L $p"; done echo "▸ tunneling$L (Ctrl-C to stop) → open http://localhost:${APP_PORT}" - Network accessline 65
L=""; for p in $TUNNEL_PORTS; do L="$L -L $p"; done echo "▸ tunneling$L (Ctrl-C to stop) → open http://localhost:${APP_PORT}" eval "$SSH -N$L" - Network accessline 66
echo "▸ tunneling$L (Ctrl-C to stop) → open http://localhost:${APP_PORT}" - Dangerous shell operationline 67
eval "$SSH -N$L" - Dangerous shell operationline 77
down) ID="$(resolve_id)"; crabbox stop --provider "$PROVIDER" "$ID" 2>&1 | tail -1; rm -f "$IDFILE" ".cbx-${NAME}.sandbox" ;;
skills/crabbox-setup/assets/crabbox.yaml
skills/crabbox-setup/assets/setup.sh
- Executable scriptline 1
#!/usr/bin/env bash - Dangerous shell operationline 33
sudo dockerd >/tmp/dockerd.log 2>&1 & - Dangerous shell operationline 37
sudo chmod 666 /var/run/docker.sock 2>/dev/null || true - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 49
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Dangerous shell operationline 59
# docker ps -aq --filter "name=supabase_" | xargs -r docker rm -f >/dev/null 2>&1 || true - Network accessline 70
if curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1; then - Network accessline 73
echo "[setup] starting dev server on :${APP_PORT}…" nohup $DEV_CMD >/tmp/dev.log 2>&1 & for i in $(seq 1 60); do curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1 && break; sleep 2; done - Network accessline 74
nohup $DEV_CMD >/tmp/dev.log 2>&1 & for i in $(seq 1 60); do curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1 && break; sleep 2; done curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1 || { echo "[setup] dev server not up"; - Network accessline 75
for i in $(seq 1 60); do curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1 && break; sleep 2; done - Network accessline 76
curl -sf "http://127.0.0.1:${APP_PORT}" >/dev/null 2>&1 || { echo "[setup] dev server not up"; tail -20 /tmp/dev.log; exit 1; }
skills/dev-local-setup/assets/dev-local.template.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/karaoke-captions/README.md
skills/karaoke-captions/SKILL.md
skills/karaoke-captions/scripts/extract_words.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/karaoke-captions/scripts/gen_ass.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/karaoke-captions/scripts/match_style_from_image.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/karaoke-captions/scripts/render.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/new-loop/references/CLAUDE.template.md
- Access to secretsline 37
[Credential-related source omitted]
skills/open-agent-teams/SKILL.md
- Instruction override signalline 50
| Harness | agent-cmd for `tdel start` | Busy-pane signature | Exit | Interrupt | |---|---|---|---|---| | claude | `claude --dangerously-skip-permissions` (`--model`, `--effort low..max`) | `esc to interrupt` | `/exit` | Escape | - Instruction override signalline 51
|---|---|---|---|---| | claude | `claude --dangerously-skip-permissions` (`--model`, `--effort low..max`) | `esc to interrupt` | `/exit` | Escape | | codex | `codex --dangerously-bypass-approvals-and-sandbox` (`--model`, `-c 'model_reasonin - Instruction override signalline 52
| claude | `claude --dangerously-skip-permissions` (`--model`, `--effort low..max`) | `esc to interrupt` | `/exit` | Escape |
skills/open-agent-teams/scripts/tdel
skills/setup-codebase-harness/SKILL.md
- Network accessline 51
inject the fix** ("X isn't allowed here — do Y") so the remediation lands in agent context. Wire them into the repo's linter + CI. - **c) Queryable code graph.** Index the repo with [`codebase-memory-mcp`](https://github.com/DeusData/code - Network accessline 52
context. Wire them into the repo's linter + CI. - **c) Queryable code graph.** Index the repo with [`codebase-memory-mcp`](https://github.com/DeusData/codebase-memory-mcp) so the agent traces callers, data flow, and architecture from a kn - Network accessline 53
- **c) Queryable code graph.** Index the repo with [`codebase-memory-mcp`](https://github.com/DeusData/codebase-memory-mcp)
skills/visual-flow-gif/scripts/render_animated_gif.py
- Executable scriptline 1
#!/usr/bin/env python3
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 | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/agent-context-audit/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/agent-context-audit/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/agent-context-audit/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/agent-context-audit/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/agent-context-audit/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.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/ai-builder-club-skills/)