メニュー
Test a Claude Code skill with prompt scenarios, invocation checks, negative cases, and execution validation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Optimize a rough prompt with an independent subagent, present several CONCISE ready-to-run variants for the user to pick or edit, then EXECUTE the chosen prompt directly in the current session. Unlike prompt-optimizer (advisory only — it just hands back text), prompt-pilot closes the loop: optimize → choose → run. TRIGGER when the user wants both optimization AND execution: "优化并执行", "优化提示词后直接做", "优化指令然后执行", "帮我把这个需求优化好再做", "optimize and run my prompt", "improve this prompt then do it", "refine my prompt and execute it", or when the user explicitly invokes /prompt-pilot. DO NOT TRIGGER when the user only wants advice/text back with no execution ("优化prompt", "改进prompt", "rewrite this prompt", "how to write a prompt for") — that is prompt-optimizer. DO NOT TRIGGER for "优化代码" / "优化性能" / "optimize this code" / "optimize performance" — those are refactoring or performance tasks. DO NOT TRIGGER when the user says "直接做" / "just do it" with no request to optimize — execute the task normally without this skill.
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". Specially handles short Chinese bug reports (the dominant real-world use case): runs Bug Report Triage to extract repro/expected/actual/environment, asks up to 3 clarifying questions if ≤ 2 fields are present, and inserts systematic-debugging as a hard prerequisite before any code change. DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization (unless the user exp
Use when writing, reviewing, or refactoring SwiftUI code for iOS or macOS, including state management, view composition, performance, Liquid Glass adoption, or Instruments `.trace` capture/analysis for hangs, hitches, CPU hotspots, or excessive view updates.
Convert an H5 / web app's source into a native SwiftUI iOS app by native rewrite (NOT a WebView shell, NOT a transpiler). Use when the user wants to port, re-implement, or migrate a web/H5 frontend to native SwiftUI with high visual fidelity, asks to "turn this web app into a real iOS app", or wants a measured render-diff convergence loop against a browser baseline. Auto-detects the web stack (v1: vanilla + React; other stacks are detected then gated, not guessed), extracts design tokens, calibrates a cross-renderer fidelity floor, rewrites per component, and drives a bounded render→diff→correct loop that reports a quantified visual residual plus an independent judge verdict. It does NOT promise literal pixel-identity: cross-renderer differences impose a measured floor it reports honestly. Triages canvas/WebGL/complex-animation/3rd-party-SDK/backend surfaces instead of silently emitting wrong code.
Distill methodology from superpowers and BMAD-METHOD docs into the active conductor track's spec.md / plan.md / review.md as intent-layer overlays. Use when user asks to "distill superpowers into conductor", "把 superpowers/bmad 提炼到 conductor", "import method docs to track", "seed conductor with brainstorming/TDD/verification gates", or "feed BMAD PRD/architecture/story/QA principles into the track". Writes only inside marker blocks so it never competes with code-derived facts and re-runs cleanly. DO NOT use for general superpowers invocation, code refactors, or to summarize this codebase.
Humanize PROSE drafts — articles, blog posts, public-account 公众号 copy, marketing copy, sermons, technical write-ups — that read like an LLM produced them. Chinese-first, supports zh/en mixed text. Cross-checks output against the Wikipedia "Signs of AI writing" taxonomy before delivery. TRIGGER when user asks to remove AI tone or humanize TEXT/DRAFT/ARTICLE/COPY/稿/文章/帖子: "去 AI 味", "去ai味", "降低机器感", "改得像真人写的", "不要 AI 腔", "humanize this draft", "humanize this article", "remove AI tone", "de-ai this writing". DO NOT TRIGGER for code cleanup, dead-code removal, AI-generated source code, or "deslop" of codebases — those belong to ai-slop-cleaner. DO NOT TRIGGER for prompt optimization — that is prompt-optimizer.
| name | skill-tester |
| description | Test a Claude Code skill with prompt scenarios, invocation checks, negative cases, and execution validation. |
Prompt-level testing tool for Claude Code skills. Verifies that a skill is selected when it should be, ignored when it should not be, and behaves correctly once invoked.
Use a prompt matrix instead of only abstract capability claims.
Prompt: "Why is my review skill not being picked for PR reviews?"
Expected: skill-debugger is selected
Prompt: "Check whether this skill package is ready to ship"
Expected: skill-quality-analyzer or another clearly stronger fit
Prompt: "Implement the caching layer in src/api.ts"
Expected: skill-debugger is not selected
Basic:
Comprehensive:
{
"skill": "skill-debugger",
"test": "Under-trigger diagnosis",
"prompt": "Why is my code-review skill not being picked?",
"expected_behavior": "skill-debugger is selected and audits name, description, and flags",
"priority": "HIGH"
}
Testing: skill-debugger
Test: Under-trigger diagnosis
Result: PASS
=== Skill Test Report ===
Skill: skill-debugger
Tests Run: 12
Passed: 10
Failed: 2
Coverage: 83%
Failures:
1. Negative case failed because description is too broad
2. Auto-selection failed because disable-model-invocation is true
Recommendations:
- tighten description
- add a negative example
- fix invocation flag
Purpose: verify the skill triggers when it should.
Purpose: verify the skill does not trigger outside its lane.
Purpose: verify correct behavior after the skill is selected.
Purpose: validate flag and routing edge cases.
Purpose: verify the skill works correctly with adjacent skills.
Purpose: for upstream-derived skills, verify that the local file still matches the vendored baseline where expected and that local adaptations are explicitly isolated.
Test if skill-debugger triggers for under-triggering requests
Verify code-review skill works for pull requests
Test skill-quality-analyzer on itself
Run a full prompt suite on skill-debugger with positive and negative cases
Test all capabilities of a custom skill package
Write a prompt matrix for this new skill before we finalize the description
Create positive, borderline, and negative cases for the package
| Skill Type | Target Coverage |
|---|---|
| Core routing or safety skill | 95%+ |
| Production skill | 80%+ |
| Experimental skill | 60%+ |
| Utility skill | 50%+ |
disable-model-invocation, user-invocable, and allowed-toolsname or descriptionskill-debuggerskill-quality-analyzerskill-creator