メニュー
Re-read Alt's authoritative project context — CLAUDE.md, the path-scoped rules, and the wiki entry point — and treat it as binding for the rest of the session. Invoke manually after a long session, after context compaction, or when the working assumptions have drifted from what the repo actually says.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Drive Alt changes test-first in outside-in order — E2E (Playwright/Hurl) → CDC (Pact) → Unit (RED-GREEN-REFACTOR) — and close with a local CI parity sweep (format/lint/type/security) for every touched microservice. Use when implementing a feature, fixing a bug, or refactoring, when deciding what test to write first, or when the user says "TDDで". Also use before declaring work complete, since "tests pass" is not "CI will pass".
Alt の Architecture Decision Record を日本語で `docs/ADR/NNNNNN.md` に書き起こす。番号採番、frontmatter（title/date/status/tags/affected_services/aliases/supersedes）、Context・Decision・Consequences の書き分け、wikilink 形式、OSS 公開向けの情報衛生を扱う。実装が一段落して決定を記録するときに使う。ユーザが「ADR書いて」「ADRにまとめて」「ADRに記録して」「実装が終わったのでドキュメントに」と言ったとき、または設計上の判断を伴う変更を終えたときに使う。
Interrogate a plan against the project's documented decisions and domain language — challenging fuzzy terms, cross-referencing the code, and surfacing where the plan contradicts an existing ADR or canonical contract. Use when the user wants a plan stress-tested against what the project has already decided, rather than in the abstract. Prefer plain grill-me when there is no documented model to test against, and plan-context-loader when the goal is to gather vault context rather than be questioned.
Hunt for deepening opportunities — shallow modules whose interface costs as much to learn as their implementation saves — and present them as a visual before/after report, informed by the decisions already recorded in docs/ADR/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, reduce the cost of understanding a subsystem, or make code more testable. Use clean-architecture instead when the question is whether a specific change violates Alt's layer rules.
設計・計画タスク時に、Obsidian vault から関連 ADR・contract・review・runbook を 必要最小限だけ集めて計画の精度を上げる。 次のときに使う: - 「計画を立てて」「設計して」「プランを作って」 - ADR や過去の決定を確認したい - Knowledge Trail / Knowledge Home や reproject-safe / immutable 設計が絡む
Alt の Go 規約を適用する。エラーラップ、context 第一引数、slog、テーブル駆動テスト、http.Server の 4 タイムアウト、Redis Streams の XACK/XAUTOCLAIM 対、fail-fast 設定を扱う。Go のコードを書く・直す・レビューするときに使う。ユーザが「Go」や規約名に触れなくても、Go サービス（alt-backend, auth-hub, pre-processor, search-indexer, mq-hub, rag-orchestrator, altctl）の実装・修正に入るなら使う。
| name | reload |
| description | Re-read Alt's authoritative project context — CLAUDE.md, the path-scoped rules, and the wiki entry point — and treat it as binding for the rest of the session. Invoke manually after a long session, after context compaction, or when the working assumptions have drifted from what the repo actually says. |
| allowed-tools | Read, Glob, Bash |
| disable-model-invocation | true |
Read the following and treat every line as authoritative for the remainder of the session:
./CLAUDE.md — the project's critical rules.claude/rules/*.md — path-scoped standing constraints (di-wiring, event-stream-consumer,
knowledge-home, security-boundaries)docs/wiki/HOME.md — the current navigation layer over ADRs, runbooks and plansThen state, in a few lines, which rules bear on the work currently in progress. Reloading is only worth the tokens if it changes what you do next.
Skills are discovered from their own frontmatter and do not need to be read here.