Instructions file
Claude Code instructions for archibate/dotfiles-claude, covering global behavior rules, environment, harness pitfalls, coding discipline and output style.
40 10d ago B 3,336 tokens
Agent
Use this agent when the user needs deep investigation on a topic, technology, library, API, market data source, academic papers (arXiv/SSRN), or any subject requiring web research.
40 10d ago B 45 tokens
Skill Claude CodeCodex
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", "browser automation", "chromium --headless", "screenshot of…
40 10d ago A 82 tokens
agent-crew
04Skill Claude CodeCodex
Multi-specialist agent crew for complex, cross-cutting tasks spanning product scoping, design, research, engineering, or operations. Use when requirements are ambiguous and need structured breakdown, when the user asks for planning/architecture before implementation, or says "plan this", "break this down", "crew".
40 10d ago A 65 tokens
Skill Claude CodeCodex
Create algorithmic/generative art using p5.js — flow fields, particle systems, seeded randomness, interactive parameter exploration.
40 10d ago A 28 tokens
ast-grep
06Skill Claude CodeCodex
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. definition). Also use when renaming a symbol across call sites +…
40 10d ago A 93 tokens
babysit
07Skill Claude CodeCodex
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 work, or when the user says "run in background", "use babysit".…
40 10d ago A 91 tokens
Skill Claude CodeCodex
Translate English into Chinese in natural human voice. Use before writing or polishing any Chinese translation of English content.
40 10d ago A 25 tokens
bilibili-api
09Skill Claude CodeCodex
Programmatic Bilibili operations via the bilibili-api-python async library (400+ endpoints) — videos, users, favorites, danmaku, live rooms, comments, search, uploads.
40 10d ago B 47 tokens
Skill Claude CodeCodex
Prompt cache cost optimization. Generates periodic conversation turns to keep the 5-minute prompt cache warm during idle gaps. TRIGGER immediately after any Bash or Agent call with runinbackground=true on the official Anthropic runtime, or when the user says "cache keep-alive".
40 10d ago A 61 tokens
Skill Claude CodeCodex
Create beautiful visual art in .png and .pdf documents using design philosophy. This skill should be used when the user asks to create a poster, piece of art, design, or other static piece.
40 10d ago A 43 tokens
chrome-cdp
12Skill Claude CodeCodex
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 for headful browser automation. This skill should be used…
40 10d ago A 112 tokens
claude-dm
13Skill Claude CodeCodex
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 peer in tmux", "send to peer", "handover to claude"…
40 10d ago A 92 tokens
Skill Claude CodeCodex
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.
40 10d ago A 55 tokens
Skill Claude CodeCodex
Measure code quality quantitatively — cyclomatic complexity, cognitive complexity, maintainability index. Use when evaluating whether code meets quality thresholds.
40 10d ago A 31 tokens
Skill Claude CodeCodex
Get a cross-model second opinion from gpt-5.5 on your current approach. Use before substantive work (writing, editing, committing to an interpretation), when stuck (errors recurring, approach not converging), when changing approach, or before declaring a task done. The reviewer sees your opening task plus recent work…
40 10d ago A 73 tokens
context7
17Skill Claude CodeCodex
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.
40 10d ago A 52 tokens
Skill Claude CodeCodex
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 changing computation-intensive kernels, high-throughput data…
40 10d ago A 107 tokens
Skill Claude CodeCodex
High-quality C++ OOP coding style (archibate / parallel101 lineage) that overrides sloppy AI-default C++. Use this skill WHENEVER writing, editing, refactoring, or reviewing C++ code (.cpp / .h / .hpp / .cc / .cxx), designing C++ classes, interfaces, APIs, or libraries, or when the user mentions C++ design, OOP…
40 10d ago A 179 tokens
deepwiki
20Skill Claude CodeCodex
Query AI-generated overview of GitHub repositories via DeepWiki MCP. Use when needing a fast high-level understanding of a repository's architecture and design decisions without fetching full repository.
40 10d ago A 37 tokens
deslop
21Skill Claude CodeCodex
Review an AI-generated article to detect AI slop patterns. Loads a AI slop pattern checklist. Rewrite to strip AI smell without changing meaning or losing information. Restores a human voice. Use before publishing any AI-written article to public under the name of human author.
40 10d ago A 57 tokens
Skill Claude CodeCodex
Structured workflow for co-authoring documentation, proposals, technical specs, or decision docs — context gathering, iterative refinement, reader testing.
40 10d ago A 31 tokens
doc-detrim
23Skill Claude CodeCodex
Audit agent-facing documentation (CLAUDE.md, SKILL.md, AGENTS.md, prompt markdown, agent reference doc, memory pages) for over-description and propose trims. Use proactively after writing or editing any agent-facing doc, or when the user says "trim this doc", "audit doc bloat", "this is over-explained".
40 10d ago A 75 tokens
docx
24Skill Claude CodeCodex
Create, read, edit, or manipulate Word documents (.docx). Triggers: 'Word doc', '.docx', or requests for reports, memos, letters, or templates with formatting (TOC, headings, page numbers, letterheads). Also extracting content, inserting images, find-and-replace, or tracked changes/comments in .docx files.
40 10d ago A 76 tokens