소스 정보
- 저장소
- kapilvirenahuja/garura
- 최근 소스 활동
- 2026년 5월 31일 16:28
- 감지된 SKILL.md 언어
- 영어
- 스타
- 3
- 포크
- 0
설치 방법
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
소스 파일 검토
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
메뉴
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/kapilvirenahuja/garura --skill analyze-pr명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Install Garura into a target project or repository so its skills, agents, and plays become discoverable by a host coding tool — Claude Code or the OpenAI Codex CLI. Reads this garura checkout's core/components and runs a per-tool ADAPTER that lays them down in the host's native shape: for claude, .claude/ skills + agents with model tiers resolved to Claude models; for codex, .agents/skills Agent Skills plus AGENTS.md and ~/.codex model/sandbox/approval profiles. Always writes a .garura/ tooling tree (config + STM scaffold) and copies shared memory to the machine-global ~/.garura, and records an install manifest so uninstall-garura can reverse exactly what was placed. Use when the user wants to install, set up, bootstrap, add, or enable Garura in another folder or repo for claude or codex — "install garura into X", "set up garura in this repo for codex", "bootstrap garura", "make codex see the garura skills". Takes the target path, an optional --tool, and an optional --scope (full = everything, the default; ha
Compile a deterministic "play" (a multi-step, gated workflow recipe) from an intent. Interviews for the intent triple, generates the expectation, identifies the skills, scripts, and agents the play needs, selects a workflow structure, generates evals, and emits a compiled play (a SKILL.md plus bundled scripts for its mechanical work). Use this whenever the user wants to create, build, compile, or review a play — or says "create a play", "new play", "compile this into a play", "play-creator", "turn this intent into a play", or "review my play for gaps" — even if they don't say the word "play" explicitly but are describing a repeatable, multi-step, checkpoint-gated workflow they want captured as a runnable recipe.
Modify an existing compiled play — change its goal, a constraint, a failure condition, a success scenario, a step, the workflow shape, or the agents/skills it uses — by editing the play's ICE source and recompiling, never by hand-patching the output into disagreement with its intent. This is the companion to play-creator (which makes new plays). Use this whenever the user wants to edit, change, modify, update, tweak, extend, or fix an existing play — or says "edit the play", "change this play", "add a constraint to the play", "the play needs a new failure condition / step / scenario", "play-editor", or "recompile the play after I changed its intent" — even if they don't say "play" outright but are clearly reshaping a workflow recipe that already exists.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | analyze-pr |
| description | Analyze branch and generate context-aware quality checklist |
| user-invocable | false |
| model | sonnet |
| allowed-tools | Bash, Read |
Model-invocable skill for analyzing PR readiness with dynamic quality checklists.
Analyze the current branch against base and produce a context-aware quality checklist.
You DO the analysis work. You do NOT make decisions about what to do with the results.
Receive from agent:
main)If pr_number was provided in the input:
If pr_number was not provided:
Invoke the platform-adapter skill with verb: diff-pr and args: {pr_number: {pr_number}} to fetch the unified diff.
Invoke the platform-adapter skill with verb: view-pr and args: {pr_number: {pr_number}} to fetch PR metadata (number, title, body, files, commits, baseRefName/target_branch, headRefName/source_branch).
If the adapter returns a non-zero exit code, halt with error: "PR-scoped mode requires a configured platform CLI. Check platform configuration and authentication."
Use the files list from the view-pr response as the changed files list (equivalent of git diff --name-only). Use the diff from the diff-pr response for content analysis. Use commit messages from the commits array for commit type analysis. Access the target branch via baseRefName (GitHub) or target_branch (GitLab) as appropriate for the active platform.
Proceed to Step 2 with the PR-derived data.
This step is skipped when pr_number is provided — PR-scoped mode uses Step 0a instead.
git diff --stat main..HEAD
git diff --name-only main..HEAD
git log --oneline main..HEAD
git branch --show-current
Using the changed files list (from Step 0a in PR-scoped mode, or Step 1 in branch-diff mode), determine which file patterns are affected:
*.ts, *.js, *.py, *.java, *.go)**/api/**, **/routes/**, **/controllers/**)**/auth/**, **/security/**, *.pem, *.key)**/migrations/**, *.sql, **/schema/**)**/components/**, *.tsx, *.vue)**/*.test.*, **/*.spec.*, **/test/**)*.md, **/docs/**)Determine branch pattern using: reference/branch-patterns.md
Determine commit types from commit messages using: ~/.garura/core/memory/standards/rules/commits.md
Load quality rules from: reference/quality-rules.md
For each rule in the loaded ruleset:
For items with automated verification:
git merge-tree --write-tree main HEADMark manual items as REVIEW status requiring human sign-off.
Generate the context-specific checklist with:
Produce output using template: templates/analysis-output.md
IMPORTANT: This skill produces analysis data. The calling agent receives this output and decides what to do next. Do NOT instruct the agent to return or stop.
| Field | Value |
|---|---|
| Version | 1.0.0 |
| Category | analysis |