메뉴
Natural language skill discovery — describe what you want to do and get matched to the right skill.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/joris887/exosuit --skill help-me명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | help-me |
| version | 1.0.0 |
| description | Natural language skill discovery — describe what you want to do and get matched to the right skill. |
| trigger | manual |
| depends-on | [] |
| references | [] |
| disable-model-invocation | true |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep |
| argument-hint | "I want to..." |
Finding the right skill for: $ARGUMENTS
Map the user's natural language request to the most appropriate skill(s):
| User Says | Skill | Why |
|---|---|---|
| "start working", "begin", "new sprint" | /sprint-start | Creates a clean feature branch |
| "build", "implement", "add feature", "create", "deliver" | /story-cycle <description> | Full story delivery with TDD |
| "ship", "finish sprint", "create PR", "merge" | /sprint-end | Quality gates → PR → merge |
| "resume", "pick up where I left off", "continue" | /continue | Smart session resumption |
| "done for today", "end session", "save progress" | /handoff | Structured session handoff |
| User Says | Skill | Why |
|---|---|---|
| "plan", "break down", "decompose", "stories" | /ideate <idea> | Decompose into backlog stories |
| "explore design", "compare approaches", "architect" | /brainstorm <idea> | Design exploration with alternatives |
| "research", "investigate", "compare technologies" | /research <topic> | Deep online research with citations |
| User Says | Skill | Why |
|---|---|---|
| "test plan", "prepare for testing" | /manual-test | Generate test plan from changes |
| "found a bug", "test feedback", "this doesn't work" | /testing-cycle <feedback> | Classify and process test findings |
| "run UAT", "acceptance test" | /UAT-cycle <test-case-id> | Execute formal UAT test case |
| "verify UAT logic", "sense check" |
/claude-sense-check |
| Batch UAT code verification |
| "check code quality" | /code-quality | Complexity, duplication, patterns |
| "security review", "audit security" | /security-audit | CWE checklist, secrets, injection |
| "check architecture" | /architecture-check | Module boundaries, drift |
| User Says | Skill | Why |
|---|---|---|
| "debug", "error", "broken", "fix bug" | /debug-session <error> | 5-phase structured debugging |
| "fix issue", "fix #42", "github issue" | /fix-issue <number> | GitHub issue → TDD fix → PR |
| "undo", "revert", "go back", "start over" | /undo-work | Safe rollback (3 levels) |
| User Says | Skill | Why |
|---|---|---|
| "health check", "is framework ok" | /doctor | Framework health validation |
| "weekly check", "maintenance" | /weekly-maintenance | Comprehensive weekly review |
| "retrospective", "what worked" | /retrospective | Sprint review with 4Ls |
| "backlog health", "review stories" | /backlog-review | Backlog quality analysis |
| "PR status", "check PRs" | /pr-status | Open PR status + actions |
| "upgrade framework" | /framework-upgrade | Update to newer version |
| User Says | Skill | Why |
|---|---|---|
| "commit" | /commit | Conventional commit |
| "parallel", "worktree", "multiple stories" | /parallel-work | Manage concurrent worktrees |
| "improve iteratively", "refine" | /refine-loop "<task>" | Iterative self-improvement |
| "optimize metric", "increase coverage" | /optimize "<goal>" | Metric-driven optimization |
| "create skill" | /skill-create | Generate tech-specific skills |
| "test a skill" | /skill-eval | Skill testing and comparison |
| "remove framework" | /uninstall | Clean framework removal |
| "status", "dashboard" | /dashboard | Sprint status overview |
| User Says | Skill | Why |
|---|---|---|
| "review security of file" | /review-security <file> | Quick security review |
| "explain this pattern" | /explain-pattern <pattern> | Code pattern explanation |
| "suggest tests for file" | /suggest-tests <file> | Test case suggestions |
Based on the user's input, present the top 1-3 matching skills:
### Recommended
**`/skill-name <arguments>`** — [one-line description of what it does and when to use it]
### Also Consider
- `/other-skill` — [why this might also apply]
If the user's intent is ambiguous, present options using AskUserQuestion with descriptions explaining the workflow implications of each choice.
If no skill matches, suggest:
/brainstorm for complex open-ended exploration/research for information gathering