メニュー
Agent reviews its own work before presenting to the user. Catches errors, style violations, and omissions before the user sees the output.
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
Analyzes project structure, module dependencies, imports, and entry points to generate architecture diagrams in Mermaid format
Analyzes ETL and data pipeline code for optimization opportunities across Python (Pandas, PySpark), Rust (polars, datafusion), SQL, and general pipeline descriptions
Validates environment variable configurations and config files (YAML, TOML, JSON, .env) for missing required variables, type mismatches, deprecated keys, naming convention violations, secret exposure risks, and invalid value ranges
Analyzes code for performance bottlenecks including N+1 queries, O(n^2) or worse algorithms, unnecessary allocations, sync I/O in async contexts, excessive cloning, missing caching opportunities, and large payload transfers. Supports Rust, Python, TypeScript, and Go.
Analyzes, improves, and restructures LLM prompts for clarity, efficiency, and reliability
Analyzes source code for common security vulnerabilities including SQL injection, XSS, command injection, hardcoded secrets, insecure deserialization, path traversal, and SSRF
| name | self-reviewer |
| description | Agent reviews its own work before presenting to the user. Catches errors, style violations, and omissions before the user sees the output. |
| version | 1.0.0 |
| author | go-on-team |
| tags | ["review","quality","self-check","verification"] |
| min_go_on_version | 1.0.0 |
Performs a structured self-review of the agent's own work before submission. Checks for completeness, correctness, safety, and adherence to project principles.
review, code-quality, self-improvement
A meta-skill that guides an agent through a structured self-review of its own output before presenting it to the user. Applies a comprehensive checklist across code changes, documentation, performance, and safety dimensions. Catches errors, style violations, omissions, and regressions before the user sees the result.
Use this skill before presenting any work product — especially code changes, documentation updates, configuration changes, or generated artifacts. It is the final quality gate in the agent's workflow.
Invoke after completing work but before presenting results to the user.
/self-review — Run full self-review on all pending changes/self-review code — Review only code changes (compile, lint, test, style)/self-review docs — Review only documentation changes/self-review safety — Review for security and safety concerns only| Parameter | Type | Description |
|---|---|---|
scope | string | Review scope: full, code, docs, safety (default: full) |
changes | string | Optional: description or diff of the changes to review |
strictness | string | Optional: normal, strict (default: normal). Strict mode flags warnings as errors |
Returns a structured review report containing:
cargo check or equivalent)cargo test for affected area)TODO or FIXME markers left in the code?/self-review — Run self-review on pending changes/self-review code — Review only code changes/self-review docs — Review only documentation