원클릭으로
validate-git
Validates Git branch naming, commit messages, and protection rule compliance
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Validates Git branch naming, commit messages, and protection rule compliance
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Plan-then-execute sprint orchestrator. Works like a real delivery team: split work into sprints (~1 human-week each), plan them all up front WITH the user, then autonomously run each sprint through a full cycle (research→plan→design→do→QA→fix→deploy) to completion. Multiple sprints can run at once (concurrent dispatch). The leader (main session) dynamically scaffolds project-local agents for whatever domain — not dev-only (marketing, research, ops, data all fit). bkit-aware: borrows bkit agents/skills internally when present, runs fully standalone otherwise. Not for single-file edits, one-shot bug fixes, or work under ~a few hours.
Invoke for "/cowork-insights" command or when the user asks to summarize, review, or report on past Claude Code sessions. Analyzes sessions to show key prompts (verbatim), structured assessments (goal/outcome/friction), tool usage patterns, and actionable insights. Produces HTML report + shareable Markdown for Jira/Notion/Slack. Three report formats — full (deep narrative), standard (core insights), minimal (quick team share). Supports --from/--to with absolute (2026-03-01) or relative (7d, 2w, 1m) dates. Trigger on phrases like weekly status update, sprint recap, what did I do with Claude, AI usage patterns, session history, minimal recap, what I worked on today, share with team, cowork-insights. DO NOT invoke for active tasks (debugging, refactoring, code review, project setup) or for commit-time recaps (use cowork-commit instead).
Trigger whenever the user asks to commit AND wants the commit message enriched with AI collaboration history. Creates a lightweight commit message (key decision highlights + link) and a full directive-log file with conversation transcript + recap. The key signal is the combination of (1) making a commit with (2) capturing how AI contributed. Trigger on phrases like commit with AI recap, attach collaboration history to commit, record AI work in commit, cowork-commit. DO NOT trigger for plain commits without AI documentation, standalone time-period recaps (use cowork-insights instead), PR reviews, or general git operations.
One-time bootstrap of an existing project's docs/ and source into the cowork-doc-sync taxonomy structure. After a detailed gap analysis, relocate docs to match the standard. Phase 1 = relocation only (no new creation, includes moving content between docs), Phase 2 = analyze source to create new docs (only after user approval). For ongoing maintenance use /cowork-doc-sync. Triggers: cowork-doc-init, /cowork-doc-init, init doc structure, relocate docs, organize existing docs, doc init, doc bootstrap
Ongoing doc-sync skill that aligns a project's docs/ with the current code/decision state. Call once at the very end, after implementation/refactoring is complete. Enforces a numbered taxonomy (00-reference~99-misc) + status model (LIVING/ACTIVE/FROZEN) + migration rules. To fit an existing project into this structure for the first time, use /cowork-doc-init. Triggers: cowork-doc-sync, /cowork-doc-sync, sync docs, align docs, organize docs, doc sync, doc alignment
Compare DevMD files against actual source code. Measures coverage, accuracy, and consistency with deterministic counting and evidence-backed findings.
| name | validate-git |
| description | Validates Git branch naming, commit messages, and protection rule compliance |
| triggers | ["validate git","check git"] |
| user-invocable | true |
| allowed-tools | ["Read","Write","Glob","Grep","Bash"] |
Corresponding rule: docs/specs/git.md
Requires read-only git commands such as git branch and git log. Only queries Git history; no modification commands are executed.
Check current branch (git branch --show-current)
main, master, developValidate branch naming
feature/, fix/, hotfix/, refactor/, chore/, docs/Validate the last 5 commit messages (git log -5 --format="%s")
{type}({scope}): {subject} formatfeat, fix, refactor, docs, style, test, chore, perf{type}: {subject} form without scope is accepted (with warning)Check for committed secret files (git log --all --diff-filter=A --name-only)
.env, .env.*, credentials*, *.pem, *.key, secrets*Output the following matrix before generating the final report. Do not proceed until every item has been checked.
| Item | Status | Result | Detail | Evidence |
|---|---|---|---|---|
| Current branch | ? | PASS/WARN | branch name | {Bash: git branch} |
| Branch naming | ? | PASS/WARN | prefix check | {Bash: git branch -a} |
| Commit 1 | ? | PASS/WARN/FAIL | message | {Bash: git log -5} |
| Commit 2 | ? | PASS/WARN/FAIL | message | |
| Commit 3 | ? | PASS/WARN/FAIL | message | |
| Commit 4 | ? | PASS/WARN/FAIL | message | |
| Commit 5 | ? | PASS/WARN/FAIL | message | |
| Secret files | ? | PASS/FAIL | detection result | {Bash: git log --diff-filter=A} |
Status values: PASS (verified clean), NOT_APPLICABLE (not a git repository), SKIPPED (git not used), SHALLOW (partial check)
Verify every item before drafting the report. If any item is unchecked, go back and complete it.
Verify the JSON output before writing to .ww-w-ai/standards/validate-git/:
Produce the validation report in the user's conversation language.
Output the validation results in the following format:
Git Rule Compliance Report
==================================================
| Item | Status | Detail |
|------|:------:|--------|
| Current branch | PASS | feature/user-auth |
| Branch prefix | PASS | feature/ prefix confirmed |
| Commit message 1 | PASS | feat(auth): add token renewal logic |
| Commit message 2 | WARN | fix: bug fix -- scope missing |
| Commit message 3 | FAIL | fixed stuff -- does not follow Conventional Commits |
| Secret files | PASS | no secret files detected |
--------------------------------------------------
Total: 4/6 passed | 1 warning | 1 failure
After generating the Git validation report, persist results to .ww-w-ai/standards/validate-git/:
.ww-w-ai/standards/validate-git/ directory if it does not existlatest.json -- structured result following templates/schema.jsonlatest.md -- human-readable report following templates/report.template.mdhistory/ -- copy latest.json to .ww-w-ai/standards/validate-git/history/{timestamp}.jsonlatest.md is produced in the user's conversation language. JSON field names remain in English regardless of language.
The JSON output enables machine-parseable history tracking and cross-run comparison.
The history/ directory preserves prior runs for trend analysis.
.ww-w-ai/standards/ output persistence. No modification of project source.Detailed verification criteria, evidence tables, examples:
../../docs/specs/git.md../../docs/evidence/evidence-registry.md