Use after making changes to run the project's quality gates and report pass or fail for each relevant check.
Use after making changes to run the project's quality gates and report pass or fail for each relevant check.
npx skills add https://github.com/JHostalek/dotclaude --skill qgこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストール
| name | qg |
| description | Use after making changes to run the project's quality gates and report pass or fail for each relevant check. |
| argument-hint | ["path"] |
Run the project's quality gates — format, lint (auto-fix), typecheck, tests, build — scoped to $ARGUMENTS when provided, else to the touched package/workspace by default (e.g. pnpm --filter <pkg> typecheck), NOT the whole tree. Whole-tree (pnpm -r …) only on explicit /qg all — that's the pre-push/CI backstop, not the inner loop. Detect configured gates from the project; skip what isn't there (no test script → skip Tests).
| Gate | Status | Issues |
|---|---|---|
| Format | PASS/FAIL | — or N files changed |
| Lint | PASS/FAIL | — or N errors |
| Typecheck | PASS/FAIL | — or N errors |
| Tests | PASS/FAIL | N/M passed |
| Build | PASS/FAIL | — or error |
On failure: top 3 issues as file:line — not full error dumps.
Use when the user asks to commit, create a git commit, checkpoint changes, save work to git, or write a commit message.
Generate a centralized, high-altitude mental-model of a codebase as a few whole-system "lens" documents (overview, capabilities, dataflow, codemap, domain) — read instead of the code to understand what a system does. Use when the user wants architecture docs, a codebase overview/mental model, onboarding docs, or to (re)generate `codemap/`. Triggers: "build codemap", "generate architecture docs", "refresh the codemap", "document this codebase".
Use when a task is multi-step, ambiguous, or high-impact and you need an executable implementation plan before editing code.
Use when the user asks to create or update a pull request for the current branch.
Use when rewriting an existing skill so Opus 4.8 (or any frontier reasoning model) executes it with better judgment, less scaffolding, and tighter calibration. Do NOT trigger for new skills from scratch (use skill-creator) or for prompt artifacts (use prompt).
Use when the user asks to merge another branch into the current branch, pull upstream changes without rebasing, or resolve merge conflicts.
