メニュー
Deep codebase analysis — architecture health, test coverage gaps, tech debt, and actionable findings
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
Run pre-commit checks (fmt, clippy, test) then stage, commit, and push with a conventional message
Review staged or recent changes for correctness, style, and Rust conventions before committing
Use when SSHing into remote machines, looking up credentials, renaming Tailscale devices, or accessing services on the tailnet. Symptoms - SSH auth failures, too many authentication failures, command not found tailscale, need to find credentials for remote machines.
Use when mixing Tokio async code with synchronous blocking I/O libraries (tar, flate2, zip, csv), or when seeing "cannot block the current thread from within the async context" panics, or needing to stream async bytes into a sync reader.
Structured BAML schema edit → validate → test loop for the devloop project. Use when editing any *.baml file in crates/baml/baml_src/ — covers version parity gotchas, uvx invocation, regeneration workflow, and the analyze verify step.
Use when reading large files (logs, JSONL, CSVs) that exceed context limits, when the Read tool returns truncated output, or when needing to locate a specific section in a multi-thousand-line file without reading everything.
| name | analyze |
| description | Deep codebase analysis — architecture health, test coverage gaps, tech debt, and actionable findings |
| trigger | /analyze |
| tags | ["architecture","rust","analysis"] |
Run a structured codebase analysis and produce actionable findings.
Orient — read CLAUDE.md, Cargo.toml (workspace members), and recent git log --oneline -20.
Spawn parallel sub-agents for independent analysis streams:
#[allow(dead_code)]), large files (>500 lines), duplicated logicQuality gates — run and report:
cargo clippy --all-targets 2>&1 | grep -E "^error|^warning" | head -30cargo test --quiet 2>&1 | tail -20Synthesize findings into a prioritized report:
## Critical (block next PR)
- ...
## High (fix this sprint)
- ...
## Low (backlog)
- ...
If devkit is available, also run devkit health and devkit repo-review for scored reports.
Offer to create doob tasks from findings (bd create) if the user wants to track them.