Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,247 indexed, measured the same four ways as everything else here.
Use when analyzing Android ANR or bugreport traces (anr, traces.txt, Waiting Channels, DALVIK THREADS, SIGQUIT stacks), especially when root-cause evidence and lock/Binder chain mapping are required for com.thunder. or other Android projects.
A general framework for analysing stocks in China, Hong Kong, and the United States using value-investing perspectives. Value investing means judging an investment by the worth of the underlying business rather than price movement alone.
Cria um plano profissional de vídeo de ALTA PERFORMANCE a partir de um assunto ou link, usando uma base de conhecimento (estratégia viral + linguagem de câmera + prompting cinematográfico + motion graphics premium). Detecta o input, define a estratégia, escolhe preset e emite plano-edicao.json + RESUMO.md. Render…
Use when a learner's English reading/listening task includes retell audio, video, transcript, or teacher instructions, and the assistant must align task goals, learner level, output evidence, expression gaps, feedback, and teacher review.
A filesystem-based guide for working with notes in an Obsidian vault, which is a folder of linked Markdown notes managed by the Obsidian app. It covers reading, searching, editing, organizing, and linking those notes.
A framework for designing and refining programming-contest problems for events such as CSP, NOI, ICPC, and LeetCode competitions. It covers the algorithmic idea, difficulty, constraints, subtasks, tests, solutions, and reference implementations.
Cria carrosseis completos para Instagram em HTML interativo com slides exportaveis como imagens individuais. Use esta skill sempre que alguem pedir para criar um carrossel, carousel, slides para Instagram, post com multiplas imagens para Instagram, conteudo swipeable, ou qualquer conteudo visual com multiplos slides…
An academic-paper search and download tool for finding research papers from sources such as arXiv and major machine-learning conferences. It can also produce structured summaries and BibTeX citations, a format used by academic writing tools.
Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.
Manage QQBot reminders through real OpenClaw cron jobs with explicit per-user timezone settings. Use when a QQ user asks for reminders, alarms, timed notifications, recurring reminders, reminder lookup, reminder cancellation, or timezone setup/change. On a user's first reminder request, require them to explicitly…
A workflow for breaking down a reference video into its production structure, including spoken words, timing, shots, visuals, sound, and editing patterns. It turns those observations into a shot list and a repeatable production guide.
VEA (Virtual Entity Augmented) gives an AI agent a visible body on the web. Use this skill to drive an entity's live state — mood, thinking, intensity, character, scene objects — in VEA PhysicClaw, and to author or load its form in VEA perZona. Trigger on "give my agent a body", "show the entity", "set mood", "spawn…
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
Perform all financial and health calculations from countly.cz directly in chat. Covers Czech net salary (HPP), self-employed income (OSVC/OSVČ), HPP vs OSVC comparison, retirement planning (savings needed, safe withdrawal, duration), mortgage (annuity/degressive, extra payments, investment comparison), and BMI. Use…
Configure marketplace-agent user workspaces from natural-language search/selling briefs. Create/update marketplace.toml, preserve gitignored workspace data, validate, run find, and inspect output.
Use when asked to audit, evaluate, or walk through a product's UX from the user's seat — "run a UX audit", "try doing X as a user", "why is this flow so hard", "how could this UX be drastically improved" — or any task-based usability walkthrough of a live web app.
Generate a comprehensive handoff document when the user wants to continue a long-running project conversation in a new chat. Use this whenever the user says things like "สรุปทุกอย่างให้หน่อยจะไปขึ้น chat ใหม่", "create a handoff doc", "this chat is too long, summarize for next chat", "ช่วยสรุปสำหรับ chat ใหม่", or any…
Meta-skill that learns new capabilities from NPM and pip package registries. Use when user asks to integrate with a service (e.g., "I need to use Asana"), mentions an API we don't have a skill for, or explicitly invokes "/skill upskill ". Automatically searches NPM and pip, installs packages globally to /.claude/, and…
Full-spectrum security audit for any project — SAST, DAST, SCA, secret scanning, IaC security, container hardening, IAM/RBAC review, threat modeling, and API security. Step-by-step investigation with context-gathering questions before scanning. Produces triage findings, autofix patches, and a structured report.
A Chinese-language business analysis adviser covering common strategy, marketing, business-model, organisation, and problem-solving frameworks. Frameworks are structured methods such as SWOT, PEST, the 4Ps, and the business model canvas.
Package and publish one local agent Skill, or audit and release a Registry-driven public Skill portfolio, as polished installable GitHub packages. Use when the user gives a SKILL.md, Skill directory, or multi-Skill repository and asks to open-source, publish, release, share, validate, detect drift, synchronize…
★not rated 5 2mo agoA117 tokens
originalMIT
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: