Skill Open Sourcer

Skill Open Sourcer

Publish every public Skill from the single canonical repository: https://github.com/zjp1997720/zhijian-skills.

Hard publishing boundary

• A SKILL.md path or Skill directory is an import candidate, not a request to create a repository.
• Put the complete agent payload in skills//, human docs in docs/skills//, and release notes in docs/changelogs/.md.
• Register the Skill in registry/skills.json. Never add mirror, mirror_tag, standalone repository, redirect workflow, or mirror-export metadata.
• Publish commits, per-Skill Tags, and install instructions only from zjp1997720/zhijian-skills.
• Stop on secrets, private paths, client data, unpublished proprietary material, unclear asset ownership, or an unverified canonical remote.

Read [Portfolio mode](references/portfolio-mode.md), [Registry contract](references/registry-contract.md), [Release package](references/release-package.md), and [README design](references/readme-design.md) before writing.

Workflow

1. Resolve the input to a real Skill directory. Accept a SKILL.md, its containing directory, or a symlink from a local Skill root.
2. Resolve the canonical checkout from the current repository, ZHIJIAN_SKILLS_REPO, or ~/Documents/GitHub/zhijian-skills. Verify origin resolves to zjp1997720/zhijian-skills; never guess another destination.
3. Follow the canonical repository's Git synchronization rules, then run:

SKILL_OPEN_SOURCER_DIR="/skills/skill-open-sourcer"
python3 "$SKILL_OPEN_SOURCER_DIR/scripts/check_release_env.py" \
  --repo-dir  --check-npx-skills
python3 "$SKILL_OPEN_SOURCER_DIR/scripts/scan_skill_release.py" \
  /path/to/skill-or-SKILL.md

1. Inspect SKILL.md and directly referenced agents/, references/, scripts/, and assets/. Copy only the complete, sanitized install payload into skills//; preserve required license and third-party notices.
2. Write the eight-field release story from [README design](references/readme-design.md), choose clean-doc or proof-led, then create or update bilingual docs, Changelog, Registry record, Portfolio catalog, and project-native visuals. A proof-led Hero must use a composition derived from the Skill's real mechanism or output; changing only the title and motif inside a shared layout fails review. Never expose a root-level SKILL.md or add human README files inside the Skill payload.
3. Choose the version with [version-contract.md](references/version-contract.md). Use only the canonical Tag /v.
4. Validate the Skill, declared tests, full Portfolio, documentation, and repository contracts:

python3 "$SKILL_OPEN_SOURCER_DIR/scripts/portfolio.py" \
  validate-skill /skills/
python3 "$SKILL_OPEN_SOURCER_DIR/scripts/portfolio.py" \
  audit --repo  --strict
python3 "$SKILL_OPEN_SOURCER_DIR/scripts/audit_release_readme.py" \
  --repository-root  \
  /docs/skills//README.md \
  /docs/skills//README.zh-CN.md --strict
python3 -m unittest discover -s /tests -v

When README assets are generated by the Portfolio, regenerate them and run the asset tests before accepting the diff. Render every changed Hero at 900px and 360px; deterministic checks do not replace visual inspection.

1. Verify local npx skills discovery and one isolated copy install from the canonical repository. Inspect the installed tree; listing success alone is insufficient. Use top-level help only: npx --no-install skills --help. Never run npx skills add --help; skills CLI 1.5.x may perform a real installation because `` is already a valid add request.
2. Commit and push canonical main only when publishing is authorized. Never call gh repo create or publish to /.
3. Verify the remote Portfolio listing and isolated install, then create the canonical Tag and launch copy.

Output contract

Return:

• canonical Skill URL under zjp1997720/zhijian-skills
• the canonical commit, version, and /v Tag
• install command using npx skills add zjp1997720/zhijian-skills
• Skill validation, Portfolio audit, remote listing, and isolated-install results
• README presentation tier and deliberate visual assets
• the eight-field release story, unique composition choice, and rendered desktop/mobile inspection result
• safety summary and residual assumptions
• at least one X/Twitter launch post, plus a Chinese version for Chinese users

If blocked, return the file paths, reasons, sanitization steps, and safest next action.

Safety rules

Hard stop on:

• API keys, tokens, private keys, cookies, credentials, .env, or auth config
• personal absolute paths, local vault paths, or machine-only caches
• client data, private URLs, unpublished prompts, or assets without redistribution rights
• escaping symlinks, databases, logs, browser profiles, .DS_Store, dependency caches, or unexplained binaries
• a dirty or unverified canonical repository that cannot be reconciled safely

Never force-push, rewrite published Tags, create a standalone repository, or treat missing evidence as passed.

Packaging rules

• Every Skill lives at skills//, including a single-file Skill.
• Keep SKILL.md lean; put detailed agent guidance in references/ only when needed.
• Preserve agents/openai.yaml; create it when absent with a $ default prompt.
• Include deterministic scripts and licensed agent-facing assets only.
• Put human docs in docs/skills// and README visuals in its assets/readme/ directory.
• Update registry/skills.json, root README catalogs, and deterministic asset generators together. Every generated proof-led Hero needs a unique, stable data-composition value and a matching project-specific generator branch; Portfolio tests must reject duplicate composition IDs.

Publication verification

npx --no-install skills --help
npx --no-install skills add zjp1997720/zhijian-skills --list
npx skills add zjp1997720/zhijian-skills \
  -g -a codex --skill  --copy -y

Use the Portfolio's pinned skills CLI for deterministic checks. In an empty isolated HOME, invoke the recorded version explicitly with npx --yes skills@. Never use npx skills add --help as a help probe. It may perform a real installation and create .agents/ plus skills-lock.json in the current directory.

Launch copy

After all gates pass, explain the repeated problem, what the Skill automates, the canonical install command, one concrete example request, and any relevant safety boundary. Never link a standalone Skill repository.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: zjp1997720
• Source: zjp1997720/zhijian-skills
• License: MIT

Install and usage instructions live in the source repository linked above.