skill-new
Scaffold a new Clade skill end-to-end — interview for use cases and trigger phrases, generate SKILL.md + prompt.md with spec-validated frontmatter (bilingual triggers, NOT-for disambiguation), wire golden-set routing tests, and run the lint gate before committing
- License 许可
- MIT
- 所属仓库
- shenxingy/Clade
- 最近更新
- 2026-11-13
- Stars
- ★ 10
- Forks
- 6
01 前言 Front Matter
- name
- skill-new
- description
- Scaffold a new Clade skill end-to-end — interview for use cases and trigger phrases, generate SKILL.md + prompt.md with spec-validated frontmatter (bilingual triggers, NOT-for disambiguation), wire golden-set routing tests, and run the lint gate before committing
- when_to_use
- create a new skill, scaffold a skill, add a skill, write a new slash command, build a skill for X, 新建技能, 创建技能, 写个新技能 — NOT for hook generation (use /generate-hook), NOT for absorbing external skill repos (use /equip)
- argument-hint
- [skill-name or one-line description of what it should do]
- user_invocable
- true
02 资源文件 1
- 参考文档prompt.md5.6 KB
03 SKILL.md 正文
Skill New
Scaffolds a new skill for the Clade skill registry (configs/skills/),
encoding the Agent Skills spec rules (agentskills.io) and Clade's own
conventions so every new skill is born consistent, discoverable, and tested.
What it does
- Checks the existing 127+ skills for overlap first (extend beats duplicate)
- Interviews for the missing pieces: use cases, trigger phrases (EN + 中文), sibling disambiguation, invocability, arguments
- Generates
SKILL.md(discovery layer) +prompt.md(execution body) following the frontmatter hard rules enforced byvalidate-skills.py - Adds golden-set routing test cases to
orchestrator/tests/test_routing_eval.pyso triggering is CI-guarded - Runs the full validation gate: skill lint + routing eval
- Commits via
committerand reminds about./install.shdeploy
Usage
/skill-new # full interview
/skill-new pdf-extract # name known, interview the rest
/skill-new "summarize meeting notes into action items"
Frontmatter hard rules (validated, don't fight them)
name= directory name, kebab-case, no "claude"/"anthropic"description≤ 1024 chars, single line, WHAT + key capabilities, no<>when_to_usecarries trigger phrases users would actually type (EN + 中文), ending withNOT for X (use /y)clauses when siblings could confuse routingSKILL.mdbody under 500 lines (Agent Skills spec); execution detail lives inprompt.md, bulky reference material inreferences/- No
README.mdinside the skill folder
04 同仓库更多 Skills
worktree
Create or inspect runtime-adaptive isolated Git workspaces with explicit ownership and delivery routing
web-search
Route online research and URL reading to native tools or TinyFish MCP/API; prepare targeted requests, handle progress and failures, and check returned evidence. Applies to web search, fetching, and bulk collection; excludes repository/file search.
verify
Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Codex built-in /verify (which runs the app to observe a single change working) — this one walks the AGENTS.md "Features (Behavior Anchors)" list.
tasks
Coordinate dependency-aware project tasks across independent Codex, Codex, Kimi and human sessions using Beads. Use for shared plans, claiming work, task handoffs, acceptance and agent monitoring snapshots.
sync
End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)
status
Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.