qiaomu-meta-skill
Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs, SOPs, runbooks, scripts, or notes. Use for new or existing skills, prior-art synthesis, routing/trigger boundaries, trigger or output evals, Skill IR, release gates, README/Profile preparation, GitHub repository and pull-request publication, versioned Releases, clean npx installation, team reuse, and create-and-publish flows. The publication path is self-contained and forbids direct default-branch pushes. Exclude one-off summaries, translations, ordinary docs, non-skill package publishing, and tasks that explicitly should not become a skill.
joeseesun · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add joeseesun/qiaomu-meta-skill --skill qiaomu-meta-skill技能说明
name: qiaomu-meta-skill description: | Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs, SOPs, runbooks, scripts, or notes. Use for new or existing skills, prior-art synthesis, routing/trigger boundaries, trigger or output evals, Skill IR, release gates, README/Profile preparation, GitHub repository and pull-request publication, versioned Releases, clean npx installation, team reuse, and create-and-publish flows. The publication path is self-contained and forbids direct default-branch pushes. Exclude one-off summaries, translations, ordinary docs, non-skill package publishing, and tasks that explicitly should not become a skill. metadata: author: Qiaomu version: "2.8.1" upstream_inspiration: yaojingang/yao-meta-skill; joeseesun/qiaomu-skill-publisher
Qiaomu Meta Skill
Build reusable Qiaomu skill packages, not long prompts.
Router Rules
- Route by frontmatter
descriptionfirst. - Once selected,
qiaomu-meta-skillis the single authoring authority. Do not also invoke a genericskill-creatorunless the user explicitly requests comparison or this skill is unavailable. - Built-in prior-art discovery belongs to this skill. Do not install, load, or delegate to a separate discovery skill.
- Built-in GitHub publishing belongs to this skill. Do not require or invoke a separate publisher skill after this package is selected.
- Keep the package root
SKILL.mdto routing and the minimal workflow. Put judgment inreferences/, deterministic behavior inscripts/, regression cases inevals/, and evidence inreports/. - A package has one discoverable root
SKILL.md; embedded examples and fixtures useSKILL.example.mdorSKILL.fixture.md. - Do not turn one-off summaries, translations, explanations, or brainstorming into skills.
- Match the user's action: create/refactor/package requests may edit; audit/evaluate/diagnose-only requests remain read-only; publish only when explicitly requested.
- Default to concise Chinese-first
qiaomu-names with no more than three preferred hyphen parts. - Add
Copyright (c) 向阳乔木, Xhttps://x.com/vista8, and GitHubhttps://github.com/joeseesun/unless another owner is requested.
Modes
Scaffold: exploratory or personal; minimum useful files.Production: team reuse; README, interface, trigger eval, output contract, and install evidence.Library: shared infrastructure; Production plus Skill IR, portability, trust, and review cadence.Governed: public or high-trust; Library plus permission, rollback, secret, release, and claim gates.
Choose proportionally with Operating Modes, Gate Selection, and QA Ladder.
Built-In Prior-Art Discovery
Before a new skill or substantial redesign:
- Derive 2–4 intent-shaped queries covering outcome, domain action, quality mechanism, and an adjacent synonym when useful.
- Prefer the unified runner:
python3 scripts/research_prior_art.py "<query 1>" "<query 2>" --strict --summary --output reports/prior-art-candidates.json
Its underlying catalog calls remain:
npx --yes skills find "<query>"
python3 scripts/search_skillsmp.py "<query>" --limit 20 --sort stars
- Keep metrics separate: skills.sh installs measure adoption; SkillsMP stars belong to the source repository; neither is a user rating or quality score.
- Deduplicate by canonical GitHub repository and skill path. Collapse translations, mirrors, and obvious forks without adding metrics together.
- Shortlist genuinely relevant popularity, trust, and complementary anchors. Inspect source
SKILL.md, maintenance, license, permissions, security signals, and available rating evidence; never execute untrusted candidate code just to study it. - Synthesize
keep / adapt / reject / invent. Map each adopted mechanism to the new package instead of collaging prose. - Preserve dated sources, metrics, failures, deduplication, lessons, rejections, and missing evidence in
reports/prior-art-research.mdfor Production+ or materially researched work.
If a catalog fails, continue with the other sources, record missing evidence, and lower the claim. Full method: Prior-Art Research.
Generalization Gate
Before promoting one failure into a core rule:
- restate it as a domain-neutral behavior
- classify it as core mechanism, optional adapter, or eval-only fixture
- promote only safety/factual/permission invariants or behavior repeated across unrelated domains
- keep one-off details in fixtures or specialist references
- rerun the original and unrelated boundary cases
Prefer intent fidelity, source fidelity, and decision rules over an expanding topic encyclopedia.
Qiaomu Skill OS
Intent: recurring job, users, inputs, output, exclusions, standards, references.Skill IR: platform-neutral meaning and evidence boundary.Package: lean root instructions, interface, README, and earned resources.Eval: trigger boundaries first; output/runtime/human eval when risk justifies it.Review: package, context, trust, install, README, and public claims.Operate: explicit feedback, failures, drift, and next-iteration proposals without raw private content.
Compact Workflow
- Decide whether the request deserves a reusable skill; otherwise answer directly and create no package.
- Capture job, finished output, target users, inputs, exclusions, permissions, standards, existing assets, platforms, and publication intent.
- Pass prior-art discovery or record why it is not applicable or missing evidence.
- Pass the generalization gate for sample-driven core changes.
- Choose the lightest valid mode.
- Write the
descriptionearly; runevals/trigger_cases.jsonbefore expanding structure. - Create only earned resources. Never cre