.claude/skills/implement/SKILL.md
Pick the top task from todo and implement it with tests and review based on related documents
npx skillsauth add peintangos/deep-agents-example implementInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Arguments: $ARGUMENTS
$ARGUMENTS, use itdocs/prds/*/todo.md using Glob
The target PRD path is docs/prds/prd-{slug}/ below.
docs/prds/prd-{slug}/todo.md and identify the first unchecked - [ ] task (or the task specified in $ARGUMENTS)docs/prds/prd-{slug}/specifications/)docs/prds/prd-{slug}/knowledge.md if it existsdocs/ubiquitous/glossary.md if it exists to align on project terminologyExecute the following in order:
/test to execute tests/build-check to run build and lint checkschrome-devtools MCP to verify the rendered output visually:
/code-review to conduct code reviewdocs/prds/prd-{slug}/todo.md as - [x] (do not remove it) and keep remaining executable tasks as unchecked - [ ] linesdocs/prds/prd-{slug}/progress.md using the exact template schema
done and fill in the completion datein-progress and leave the completion date blankdocs/prds/prd-{slug}/knowledge.md/commit-push to commitdone just because one todo item was completedtodo.md and report to the userdata-ai
監査レポートを Zenn 技術記事向けの文体 (だ/である調 + 比較表 + 階層化された見出し) に整えるスキル。`src/reporter.ts` の骨組みを LLM が整形してレポート (`out/*.md`) を仕上げるときに読み込む。
testing
OSS リポジトリの既知脆弱性 (OSV / GHSA) を照合し、重大度と影響範囲を分類するスキル。セキュリティ監査を実行するときに読み込む。
data-ai
OSS リポジトリのメンテナンス健全性 (リリース頻度・Issue 対応速度・放置 PR) を定量的に評価するスキル。メンテナンス監査を実行するときに読み込む。
tools
OSS リポジトリのメインライセンスを特定し、商用利用制約・依存互換性・NG ライセンスの検出までを行うスキル。ライセンス監査を実行するときに読み込む。