Loading...
Loading...
Found 40 Skills
Python development best practices including PEP 8 style guidelines, type hints, docstring conventions, and common patterns. Use when writing or modifying Python code.
Rewrite Python docs and docstrings from source code. Use when Codex needs to refresh the docs.
Trim and freshen technical documents, READMEs, design notes, PR descriptions, internal messages, and source-code comments or docstrings. Uses independent fresh-reader reviews to expose author-context bias, then deletes repetition, defensive caveats, filler, decorative structure, and code restatements while preserving facts, decisions, actions, constraints, and necessary rationale. Use when text is overexplained, repetitive, hard to scan, written while thinking, or when comments restate code or have drifted out of sync with it.
Write docstrings for PyTorch functions and methods following PyTorch conventions. Use when writing or updating docstrings in PyTorch code.
Write Python docstrings following the Google Python Style Guide, using clear sections and examples.
Code Style Conventions. Use when writing, editing, or reviewing Python code. This includes conventions such as type hints, Decimal precision, docstrings, module organization, etc. Enforces type hints, Decimal precision, docstrings, and module organization.
Adds and enhances comments and documentation comments in code. Use with requests like 'add comments', 'write comments', 'enhance comments', 'add JSDoc', 'add docstring', 'add documentation comments'. Preserve role boundaries from the package/service perspective, prerequisites and contracts between callers and callees, and context from other files/services in a 'readable on the spot' format. Do not modify the code itself (for implementation changes, use implement-issue). Refer to code-comment-style for detailed rules, create-commit for commit creation, and update-docs for CLAUDE.md synchronization.
Expert guidance for writing clear, comprehensive documentation including READMEs, API docs, docstrings, and technical guides. Use when creating or improving documentation.
Audit code comments and docstrings quality across 6 categories (WHY-not-WHAT, Density, Forbidden Content, Docstrings, Actuality, Legacy). Use when code needs comment review, after major refactoring, or as part of ln-100-documents-pipeline. Outputs Compliance Score X/10 per category + Findings + Recommended Actions.
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.
Checks WHY-not-WHAT, density (15-20%), forbidden content, docstrings quality, actuality, legacy cleanup. Returns findings with severity, location, and recommendations.
Write and audit Python code comments using antirez's 9-type taxonomy. Two modes - write (add/improve comments in code) and audit (classify and assess existing comments with structured report). Use when users request comment improvements, docstring additions, comment quality reviews, or documentation audits. Applies systematic comment classification with Python-specific mapping (docstrings, inline comments, type hints).