메뉴
Review local staged and unstaged changes before committing. Outputs an overall summary and per-file line-level findings with severity levels. Use when asked to review code before a commit, check local changes, or suggest improvements on uncommitted work.
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
Generate a PR title and description following the WCC repo template, infer change types from the diff, and print the GitHub URL to open the PR in the browser. Use when asked to open a PR or create a pull request.
Safely commit changes. Reviews staged/modified files for sensitive data, writes a commit message with body. Never adds co-author lines.
Review pull requests using GitHub CLI. Use when asked to check a PR, perform code review, or leave review comments. Focus on bugs, regressions, security, code quality, best practices, and missing tests; post comments inline on the relevant changed lines and avoid top-level summary comments unless explicitly requested.
Create a GitHub issue in the Women-Coding-Community/wcc-frontend upstream repository, add it to the Frontend Platform project board, and set Epic, Status, and other project fields. Use when the user asks to create a GitHub issue, ticket, or task for this project.
Interactively create a well-structured GitHub issue (bug or feature) for Women-Coding-Community/wcc-frontend with Scrum user story, acceptance criteria, test scenarios, and code examples derived from the codebase. Adds the issue to the Frontend Platform project board.
| name | pre-commit-review |
| description | Review local staged and unstaged changes before committing. Outputs an overall summary and per-file line-level findings with severity levels. Use when asked to review code before a commit, check local changes, or suggest improvements on uncommitted work. |
Canonical runbook:
.ai/skills/pre-commit-review.mdThis file is the Claude Code adapter. The workflow logic is defined in the canonical skill so it can be shared with other agents (Codex, Copilot, Cursor). Any changes to the workflow should be made in.ai/skills/pre-commit-review.mdfirst.
Run quality checks — execute and capture output:
pnpm lint:fix && pnpm format && pnpm type-check
Report errors/warnings. Flag type-check failures as [CRITICAL]; unfixable lint/format violations as [WARNING].
Gather local changes:
git status --shortgit diff HEAD — all changes (staged + unstaged) vs last commitgit diff --staged — staged-only changesgit log --oneline -5 — recent contextReview with a code-review mindset — same priority order as PR review:
Check conventions and quality for changed technologies only:
@DisplayName format, mocks only where appropriate.Output the review in two parts:
Overall Summary — 2-5 sentences: what the change does, key risks, and whether it is safe to commit as-is.
Per-file findings — for each file, list findings anchored to the changed line number:
**<file-path>**
Line <N>: [SEVERITY] <short title>
Risk: <what could go wrong>
Scenario: <exact condition where it fails>
Suggestion: <minimal fix direction>
```suggestion
<concrete code snippet>
Severity levels:
- `[CRITICAL]` — must fix before committing
- `[WARNING]` — should fix
- `[INFO]` — optional improvement
**What looks good** — call out 1-3 positive things to keep the developer motivated.