Browse Skills

Docs Impact Classifier classifies the documentation impact of a pull request diff into no change, in-place edit, or structural change. It uses deterministic path gates, symbol extraction, and a bounded LLM call to keep docs-sync costs low when no docs work is needed.

Docs Impact Localizer translates a classifier's in-place verdict into a page-by-page documentation edit plan. It reads candidate pages, narrows changes to specific sections, flags cross-page consistency requirements, and returns JSON task briefs for doc-sync writers.

Docs Sync assesses whether documentation must change when a pull request opens, reopens, or synchronizes, detecting silent drift between code and docs. It classifies impact as no-change, in-place edit, or structural change, then orchestrates a panel to produce a patch-ready advisory without merging or pushing.

OSS Growth improves open source project adoption by refining README conversion surfaces, quickstarts, templates, release announcements, and contributor funnels. Use it when working on OSS adoption and growth tactics.

PR Description drafts a self-sufficient GitHub-Flavored Markdown pull request body with TL;DR, problem, approach, implementation, validated mermaid diagrams, trade-offs, validation evidence, and how-to-test sections. Use it when asked to write a PR description, draft a PR body, open a PR, or fill in a PR template.

Python Architecture guides the creation of new modules, refactoring class hierarchies, introducing design patterns, and making multi-file changes in the APM CLI codebase. Use it to follow existing patterns and centralize shared logic with regression tests and static checks.

Shepherd Driver drives one existing pull request to a mergeable state: classifies review, runs the review panel, folds recommendations, pushes, watches CI, and resolves conflicts under caps. Use it as the composed per-PR stage in a batch bug shepherd or issue autopilot orchestrator, not standalone.

Markdown to WeChat converts Markdown to WeChat Official Account HTML and supports preview, draft upload, image generation, image-post creation, writer-style drafting, title suggestions, AI trace removal, and provider/theme discovery via the md2wechat CLI.

MD2WeChat converts Markdown into WeChat Official Account HTML and manages article images, drafts, and titles. Use it to inspect providers/themes/prompts, write in creator styles, and remove AI writing traces.

PerfUp autonomously researches, benchmarks, and implements performance optimizations for vllm-mlx, then ships production-ready pull requests when improvements are confirmed.

Add Domain extends an existing knowledge system by deriving a new domain configuration through conversation, then generating folders, templates, and vocabulary while connecting to the current architecture. Use it when adding a new subject area to a multi-domain note system.

Ars Contexta Setup scaffolds a complete knowledge system by detecting the platform, asking a few questions, deriving a configuration, and generating files. Use it to create a structured vault with processing pipeline, automation hooks, and navigation maps for an AI agent.