s0912758806p/agentic-sop-to-work/plugin-forge
Claude Code and agent skill by s0912758806p/agentic-sop-to-work
- community
Checking that the SKILL.md file is still in the repository.
Use when creating, scaffolding, or linting a Claude Code plugin — generate a grammar-conformant plugin skeleton, or validate a plugin / whole marketplace against house invariants (manifest, frontmatter, stdlib-only, hook protocol, test harness). | 要新建 / scaffold 一個 Claude Code plugin,或 lint 既有 plugin / 整個 marketplace 是否符合房規時使用。
Install
npx vskill@latest install s0912758806p/agentic-sop-to-work/plugin-forgeSKILL.md
plugin-forge — lint + scaffold Claude Code plugins
Invoked as /plugin-forge:plugin-forge [args] — arguments: $ARGUMENTS. Let ROOT="${CLAUDE_PLUGIN_ROOT}" (the sections below show the repo-relative paths used inside this marketplace's checkout; the installed plugin's are under $ROOT):
lint <plugin-dir>→python3 "$ROOT/pluginforge/lint.py" <plugin-dir> [--strict]lint --all→python3 "$ROOT/pluginforge/lint.py" --all --strict(from the marketplace root)new <name>→python3 "$ROOT/pluginforge/scaffold.py" <name>
Present the lint findings (HARD then SOFT) verbatim; for scaffold, report the new dir + next steps.
Lint
- One plugin:
python3 plugins/plugin-forge/pluginforge/lint.py <plugin-dir> - Whole marketplace:
python3 plugins/plugin-forge/pluginforge/lint.py --all --strict --strictadds house invariants (stdlib-only, verify.py, test_no_third_party). Exits 1 on any HARD.- Always on:
vendored-core-drift(HARD) — a vendored_core/or other GENERATED file was hand-edited, or is out of date withshared/sopcore/. Fix: edit the source, runpython3 tools/sync_core.py.
Scaffold
python3 plugins/plugin-forge/pluginforge/scaffold.py <name>→ a skeleton that passeslint --strict, shipping the shared core as<pkg>/_core/.- Then add it to
marketplace.json+ CI and flesh out the TODOs.
The lint report is a DRAFT; a human decides. HARD = fails CI; SOFT = advisory.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/plugin-forge/skills/plugin-forge/SKILL.md
Popularity
- Repository stars
- 210
- Repository forks
- 21
- 7-day trend score
- 27
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/s0912758806p/agentic-sop-to-work/plugin-forge)