Translate natural language queries into ast-grep rules for structural code search. This skill should be used when a text-only grep would need 2+ alternations, regex capture groups, multi-line patterns, or filtering by syntactic role (call vs. import vs.…
Run long-running tasks under babysit — supervised background runner with cgroup-enforced memory/CPU caps and observability-stall kill. Use BEFORE any long-running task (>2 min), compute-intensive jobs (e.g. builds/benchmarks/renders/training), background…
Interview the user about a plan or design until reaching shared understanding. This skill should be used when the user wants to stress-test a plan, get grilled on their design, or mentions "interview me".
Form a minimal self-contained prompt to reproduce this session. Use when user want to form a minimal spec of existing system, or when they migrate from a degraded session to a fresh one.
Evidence-driven C++ high-performance computing design, profiling, and optimization across algorithmic time/space complexity, data layout, cache and memory behavior, numerics, SIMD, multicore scheduling, and CPU/accelerator pipelines. Use before designing or…
Create or edit agent-facing/LLM prompts using modern prompt-engineering practices. Use this skill before editing agent-facing docs, rule files, references, skills, memory, or any form of LLM prompt. Also use it before writing LLM tests or evaluations. This is…
Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers. Also use as a fallback when curl returns noisy HTML or WebFetch returns truncated, summarized, or refused results.
Fetch current docs and code examples for third-party libraries, SDKs, APIs, and CLI tools via Context7. Use before writing or editing non-stdlib library calls — your prior knowledge may be stale. Prefer over web search for library docs.
Code search across millions of public GitHub repositories via grep.app. Use before writing or planning code to find real-world usage of libraries, frameworks, APIs, algorithms, or syntax patterns. Prefer this over web search for code examples.
Architecture design reasoned forward from requirements. Use when the user wants a fresh-mind design pass — "design an architecture for", "how would you build", "redesign from scratch" — or when repeated follow-up patches accumulate on the same module.…
Send peer-to-peer message and control to Claude Code sessions. Use when coordinating multiple simultaneous Claude sessions, or user says "dm another claude", "list claude sessions", "peek peer claude", "spawn claude in tmux", "monitor remote claude", "notify…
中文排版规范(全角标点、中英文空格)+ zhlint 校验工具。Use whenever writing or editing formal Chinese document content — Chinese markdown docs, README 中文版, blog posts, WeChat articles, translation output, announcements, tutorials — or when the user mentions 排版, 全角/半角, punctuation…
Append a single bullet to staging memory. Use when a durable fact, knowledge, lesson, or pitfall (mistake-correction pattern) emerged mid-conversation that's potentially worth persisting into long-term memory. Also use when user corrected your mistake, says…
Programmatic/headless Claude Code usage — CLI flags, stream-json protocol, Agent SDKs, session management. Use before spawning Claude as a subprocess, testing skill or agent behavior, running "claude -p", or building with the Agent SDK.
Inspect or debug web pages in a headless browser — fill forms, click buttons, take screenshots, test web apps, review frontend UI/UX aesthetics. Use for headless browser automation. This skill should be used when user says "test web app", "headless browser",…
Connect to user's local Chrome session. Inspect and interact with web pages in a headful browser shared with user cookies and login states — navigate pages, click buttons, take screenshots, test web apps in headful Chrome the user could see in real-time. Use…
Spawn and interact with interactive CLIs (python, gdb, etc.) in tmux — send keystrokes, scrape pane output. This skill should be used when running any interactive CLI command, starting program requires interactive stdin / PTY / TUI render, or when the user…
Web search with time-window, region/language, and `site:` filters, academic papers (arXiv/SSRN), PDF table/figure extraction, BibTeX, image search, web page reading, embeddings, reranking, classification, and deduplication (text or images) via Jina AI. Use…
Clone or reuse a cached local checkout of a remote git repo (GitHub/GitLab/Bitbucket). Use when the user gives a repo URL or `owner/repo` identifier (e.g. "facebook/react"), says "clone this repo" / "read the source", or needs to browse a remote codebase.
Scrape, crawl, or extract data from websites using Scrapling — anti-bot bypass (Cloudflare Turnstile), stealth headless, spiders, adaptive scraping, JS rendering. Also a fallback when WebFetch fails due to anti-bot protections or JS rendering.