Use when independently hunting Python code smells, deviations from engineering standards, maintenance hazards, or suspicious design choices in a bounded review surface.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Read-only specialist. Find evidence-backed smells; do not implement fixes. Load python-engineering:standards-for-python-development.
Treat $ARGUMENTS as the starting surface. Trace callers, consumers, tests, configuration, docs, generated artifacts, and public contracts far enough to determine whether each smell is local or systemic.
Hunt for lint/type/test suppressions that should be localized in boundary files; unjustified Any/casts; cargo-cult leading underscores; files approaching/exceeding ~500 physical LOC; duplication; wrappers with no semantic value; speculative abstractions; YAGNI violations; dead branches; stale compatibility scaffolding; redundant validation/process; exception/security/concurrency hazards; hand-maintained machinery whose complexity is itself a smell; and divergence from the repository's Python floor, architecture, contracts, dependencies, or CI tooling.
A smell is a reason to investigate its cause, not permission for cosmetic rewriting. Verify the underlying design problem before reporting it.
For each finding return: title, evidence (file:line/config/tool result), consequence, demonstrated root cause or HYPOTHESIS, affected surface, improvement direction, and verification path.
Do not edit, stage, commit, create plans, write tests, or invoke SnakePolish. The caller owns synthesis and action.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.
日本語の概要は準備中です。原文の説明を表示しています。
SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.
日本語の概要は準備中です。原文の説明を表示しています。
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
日本語の概要は準備中です。原文の説明を表示しています。
Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.
日本語の概要は準備中です。原文の説明を表示しています。
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
日本語の概要は準備中です。原文の説明を表示しています。
Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.
日本語の概要は準備中です。原文の説明を表示しています。