From python-toolkit
This skill should be used when the user asks to "explain a ruff rule", "what does F401 mean", "show me rule E501", "explain this lint code", or otherwise requests the definition or rationale for a specific ruff rule code. Wraps `ruff rule <code>` with optional discovery via `ruff check --statistics .` when no code is given.
How this skill is triggered — by the user, by Claude, or both
Slash command
/python-toolkit:ruleThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Explain a ruff lint rule by code. When the user provides a rule identifier (e.g. `F401`, `E501`, `B006`, `UP007`), surface the rule name, explanation, and examples. When no code is provided, run a statistics pass first to discover which rules are firing in the project, then offer to explain any of them.
Explain a ruff lint rule by code. When the user provides a rule identifier (e.g. F401, E501, B006, UP007), surface the rule name, explanation, and examples. When no code is provided, run a statistics pass first to discover which rules are firing in the project, then offer to explain any of them.
Determine the rule code(s) from the user's request.
F401, E501, B006, UP007), proceed to step 2.For each provided rule code, run:
ruff rule <code>
Display the full output for each: rule name, explanation, and examples. When multiple codes are supplied, present them sequentially in the order the user listed them.
Discovery mode (no code provided). Run a statistics pass on the current directory to surface what is actually firing:
ruff check --statistics .
Summarize the violation counts and offer to explain any of the reported rules. Wait for the user to pick before invoking ruff rule <code>.
This skill currently inlines its procedure (a direct ruff rule invocation). The forward-looking design per the v3 toolkit spec and the Path B decision is for this skill to invoke the shared diagnostic-review pipeline via:
Skill(skill: "python-toolkit:diagnostic-review", pass: "rule CODE")
The shared diagnostic-review skill already ships at skills/diagnostic-review/SKILL.md and documents the pass: rule CODE selector. The per-pass invocation wiring lands in a separate chore — until then, this skill body matches the legacy /rule command behavior.
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
npx claudepluginhub zaynram/code-marketplace --plugin python-toolkit