Skill Claude CodeCodex
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 mandatory: NEVER skip this skill before writing…
Skill Claude CodeCodex
A Chinese writing and formatting skill covering full-width punctuation, spacing between Chinese and Latin text, and validation with zhlint.
Skill Claude Code
Use minimalist language.
Skill Claude Code
A writing skill for composing or rewriting employee work-chat messages in a natural, concise, direct voice.
Skill Codex
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…
Skill Codex
Enforce a closed content inventory for generic artifacts. Use when creating, editing, planning, or reviewing PDFs, resumes, documents, slides, roadshows, videos, tutorials, web pages, generative images, or similar deliverables. Apply for artifacts by default unless the user explicitly requests detailed or…
Skill Codex
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…
Skill Codex
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.
Skill Codex
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…
Skill Codex
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…
Skill Codex
Re-derive a fresh-mind architecture design reasoned forward from requirements. Use this skill before applying follow-up patches, feature changes potentially shift optimal design, or refactorization on a pre-existing codebase. Does not apply to empty codebase or new project.
Skill Codex
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.
Skill Codex
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".
Skill Codex
Lark/Feishu (飞书) CLI tool. Use when the user asks to do anything on Lark/Feishu.
Skill Codex
Report in minimalist language. Use when user complained AI report format cogonition overload.
Skill Codex
Surface-neutral visual quality assurance for browser UIs, terminal/TUI apps requiring PTY interaction, native desktop apps, documents/slides/PDFs, images, and diagrams. Use after creating or changing visible output, or when asked to test visible interaction states, animation, abrupt transitions, stutter, layout…
Skill Claude CodeCodex
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 designing agent-facing JSON Schema, MCP tool prompts, or tool/script/CLI responses, and before…
Skill Claude CodeCodex
Wait, wake later, schedule a time point, periodically continue, monitor, or poll a Bash-visible condition without holding a Codex turn open. Use for long or indefinite waits and reminders. Skip ordinary commands and short mid-flight waits within an active task.
Skill Claude CodeCodex
A writing aid for composing or rewriting workplace chat messages in a natural, concise employee voice.
Skill Codex
Audit consequential software after implementation or material changes and before production deployment. Use for services, daemons, long-running/background/silent jobs, system software, shared or machine-wide changes, security-sensitive or high-attack-surface components, state machines, error-prone or poorly testable…
Skill Claude CodeCodex
Delegate a self-contained survey or independent work to a background Pi subagent. Use to keep large exploration out of the main context, get a fresh-mind review, or run several directions in parallel.
Skill Claude CodeCodex
Fetch page content as agent-readable markdown — articles, docs, READMEs, blogs, social posts, and academic papers. Use this skill WHENEVER you want to read text content from an URL or link. Also use when curl returns noisy, truncated, or refused results.
Skill Claude CodeCodex
Search the web via the Jina search engine with time-window, region/language, and site: filters; find academic papers (arXiv/SSRN), citations, and images. Use this skill WHENEVER you need to search for solutions, verify a fact, ask for niche knowledge, look up public resources.
Skill Claude CodeCodex
Mandatory safety gate before designing or running nontrivial execution tests, integration tests, browser/GUI/audio/PTY/filesystem/configuration E2E, or deployed hardware tests on a personal or shared computer. Prevent disturbing the user or other agents; require verified private resources, silent checks first, and…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: