跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

Skill Conductor

A meta-skill that creates, evaluates, and improves other AI agent skills with multiple modes and evidence-based validation.

smixs · 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 smixs/skill-conductor

技能说明


name: skill-conductor description: > Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skill, fixing a skill that never triggers or fires unreliably, running evals to test a skill, benchmarking skill performance, optimizing a skill's description, reviewing third-party skills for quality, or packaging skills for distribution — even if the user doesn't explicitly say "skill" (e.g. "teach Claude to do X", "make the agent always follow Y"). Not for using skills or general coding tasks.

Skill Conductor

Full lifecycle management for agent skills: draft → test → review → improve → repeat.

One skill to rule them all — from architecture to packaging. The core loop is always the same: write something, test it, see what fails, fix it, test again.

Runtime requirements (pre-flight)

Before any mode that touches scripts (CREATE, IMPROVE, VALIDATE, OPTIMIZE, PACKAGE), run the pre-flight block → references/runtime-setup.md (checks uv, sets UV_BIN/SKILL_CONDUCTOR_DIR, verifies LLM access). If uv is absent, stop and tell the user.

How to communicate

Read context cues. If the user is a skill author iterating on their own work, be direct and technical. If they're new to skills, explain the why behind each step — not just what to do, but why it matters. Default to conversational, not robotic.

  • Explain trade-offs when there's a real choice to make
  • Use concrete examples over abstract rules
  • When something fails, explain the root cause, not just the fix
  • Imperative voice in instructions: "Extract the data", not "You should extract"

Modes

Detect mode from context. If ambiguous, ask.

ModeWhenWhat happens
1. CREATE"build a skill", "new skill for..."Full lifecycle: intent → architecture → scaffold → write → test
2. IMPROVE"fix this skill", "it doesn't trigger"Diagnose → eval loop → gated self-update → iterate
3. VALIDATE"test this skill", "run evals"Structural checks + trigger testing + BinEval scoring
4. REVIEW"review this skill", third-party assessment11-point quality gate, quick and focused
5. OPTIMIZE"improve triggering", "description optimization"Automated description optimization with train/test split
6. PACKAGE"package for distribution"Validate + bundle into .skill file

Mode 1: CREATE

Step 1: Capture Intent

Before writing anything, extract 2–3 concrete scenarios.

Ask:

  • "What specific task should this skill handle?"
  • "What would a user say to trigger it?"
  • "What should NOT trigger it?"

Don't move on until you have a clear picture of what the skill does, for whom, and when. This prevents the most common failure: a skill that does something but triggers for the wrong things.

Step 2: Baseline (TDD RED)

Before writing the skill, verify the agent fails without it:

  1. Take one scenario from Step 1
  2. Run it in a clean session without the skill
  3. Document what went wrong — what the agent guessed, what it missed

If the agent already handles it perfectly, the skill is unnecessary. This sounds obvious, but it's the most skipped step and the most valuable one.

Step 3: Architecture

Choose a primary pattern from references/patterns.md (can combine):

PatternUse when
Sequential workflowclear step-by-step process
Iterative refinementoutput improves with cycles
Context-aware selectionsame goal, different tools by context
Domain intelligencespecialized knowledge beyond tool access
Multi-MCP coordinationworkflow spans multiple services

Choose degrees of freedom — this determines how much control vs. flexibility the skill gives the agent:

FreedomWhenExample
Low (scripts)fragile, error-prone, must be exactPDF rotation, API calls
Medium (pseudocode)preferred pattern exists, some variation okdata processing
High (text)multiple valid approaches, judgment neededdesign decisions

Freedom test: ask "if the agent makes a mistake here, what is the consequence?" High consequence → low freedom (an exact script it must not modify). Low consequence → high freedom (prose, let it judge). Calibrate per step, not per skill — one skill can hold both.

Golden rule: read references/sop-practices.md before authoring or reviewing ANY skill. It holds the canonical 10 authoring principles (universal): pre-flight, no-process-in-description, MOC (SKILL.md = map, not prose), fresh-practitioner author, TWI "why", blind-agent test, inline checklists, one-term-per-concept, cut-the-fat (env/keys OUT of SKILL.md), match-the-form-to-the-failure. For procedural skills (business process with branching: request, quote, onboarding, escalation) the same file also has the deep SOP methodology — format selection, 7-step process, procedural checklist.

Step 4: Scaffold

uv run scripts/init_skill.py <skill-name> --path <output-dir> [--resources scripts,references,assets]

Or create manually:

skill-name/
├── SKILL.md          # required — the brain
├── scripts/          # deterministic operations (executed, not loaded)
├── references/       # detailed docs (load
阅读完整来源 ↗