Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,202 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Entrenador personal de running y trail running, con soporte para trabajo complementario de fuerza/core, ciclismo y natación como apoyo al objetivo principal. Analiza estado físico, crea planes periodizados, da feedback post-entreno, consejos de nutrición, técnica y recuperación. Triggers: entrenamiento, plan, carrera…
Skill Claude CodeCodex
Process accumulated run retrospectives in runs/ into the prioritized improvement backlog (runs/TODO.md), apply channel tuning, archive processed runs, and present the top 5 issues for the user to pick one to work on. Invoke when the user types /vicaya-improve or asks to "process the runs", "triage run feedback", or…
Skill Claude CodeCodex needs its repo
Blueprint for writing or updating an AGENTS.md file that includes agent instructions for a KMP project.
trae-op/electron-modular-boilerplate
Skill Claude CodeCodex
Skill "electron-modular" from trae-op/electron-modular-boilerplate, covering skill instructions, workflow and input guidance.
CAMARA-CHILENA-INTELIGENCIA-ARTIFICIAL/cchia-skills
Skill Claude CodeCodex
Search, compare, and analyze LLM model benchmarks using data from Artificial Analysis (artificialanalysis.ai). Use this skill whenever the user asks about model selection, model comparison, benchmark scores, pricing, speed, or wants to know which model is best for a task. Also use when the user mentions "Artificial…
Skill Claude CodeCodex
Use when non-instant work reaches a user-facing checkpoint and you need the user back for review, confirmation, reply, or completion.
Skill Claude CodeCodex
A strict heuristic framework to prevent AI design hallucinations. This skill serves as an index and workflow guide to the Anti-Slop UI framework.
lincwang123-bot/x-ops-assistant
Skill Claude CodeCodex
Use when operating any X/Twitter account. Bare @handle → full detailed report. Drafts must mirror the account’s observed voice/layout habits from recent posts. Ban-check, autopsy, scorecard, peer benchmark. Owner-first when search-suppressed. Optional xurl opt-in. Agent-agnostic.
Skill Claude CodeCodex
Two modes. (1) Prevents AI over-engineering on simple dev/research tasks — adding signatures/hash-locks on top of git, writing 200-line admission thresholds, demanding written authorization for public datasets, over-validating config keys, stuffing try/except/fallback into training scripts, generating test files for…
sham-jadhav03/Claude-Token-Reducers
Skill Claude CodeCodex
Activates compact, high-density response mode when the user types /reduceToken or any variant like /reduceToken 500 or /reduceToken study. Apply this skill immediately and hold it for the entire session. Trigger on: /reduceToken, "token constraint", "reduce tokens", "compact mode", "token budget reminder", or when the…
kjx-talesofai/claude-skill-lark-lite
Skill Claude CodeCodex
A lightweight entry point for Feishu, a Chinese workplace collaboration platform. It provides identity rules, common commands, and routing to Feishu functions through lark-cli.
Skill Claude CodeCodex
Batch query weather for multiple cities and generate a formatted report using the bundled script.
Arinin77/project-learning-tutor-skill
Skill Codex
Use when the user wants to systematically learn, dissect, and master a codebase or engineering project, especially architecture, core implementation chains, evidence-cited code explanations, engineering tradeoffs, long-term learning archives, resume packaging, and interview preparation. Supports overview, deep-dive…
ai-integr8tor/Nutlope-hallmark
Skill Claude CodeCodex
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
dungnotnull/herbal-essential-oil-extraction-agent-skill
Skill Claude CodeCodex
This document is the authoritative reference for how skills (agents, tools, hooks) are registered, resolved, executed and validated in the v2.0 runtime. It supersedes the linear-only flow described in the original markdown skills while remaining backward-compatible with them (skills/.md are now the human-readable…
Skill Claude CodeCodex
Guide for how an agent should use the epub2skill CLI.
Cumulocity-IoT/cumulocity-skills
Skill Claude CodeCodex
Analyze Angular / Cumulocity Web SDK code for anti-patterns, bugs, and quality issues. Use when reviewing components, services, or modules for code quality, maintainability, performance, and correctness. Covers TypeScript best practices, Angular idioms, C8Y SDK usage patterns, and project-specific conventions.…
Skill Claude CodeCodex
Structured, expert-level technical SEO workflow for planning, executing, and validating website migrations. Covers multiple migration types and prioritizes crawlability, indexation, and signal preservation through phase gates.
Skill Claude CodeCodex
Develop software from detailed specifications that serve as contracts. Use when building APIs, integrations, complex features with multiple conditions, or when the user provides OpenAPI specs, JSON schemas, detailed requirements, or mentions SDD, specification, contract-first development.
Skill Claude CodeCodex
Effect v4 (beta) development and v3 → v4 migration guidance. Use when building new Effect v4 code or upgrading from v3, including API renames, behavior changes, before/after examples, and v4-specific patterns for services, layers, generators, Effectable, error handling, and schema codecs.
Skill Claude CodeCodex
Brainstorming partner — asks the right questions at the right time and keeps a live document as an artifact. Opens on: "help me think", "help me plan", "I'm stuck", "I don't know where to start", "brainstorm", "unpack this", "help me decide", "I'm torn between", "me ajuda a pensar", "me ajuda a planejar", "tô…
Skill Claude CodeCodex
This skill provides a work history. Always use this skill before answering any question that involves what the user has worked on, built, shipped, or contributed to — at any level of granularity or time range. Do not attempt to answer from memory or context alone; the data lives on disk and must be queried.
Skill Claude CodeCodex
Collaborate with the user asynchronously through a shared markdown file in the working tree. The agent writes questions or proposals in the file and stops; the human replies at their own pace, freeform. Use when the user mentions "lazychat" or asks to "discuss in a file", when the task has several entangled decisions…
Skill Claude CodeCodex
Agent-to-Agent collaboration via shareable links. Use this skill when the user expresses intent to transfer context, problems, knowledge, or work results to another AI agent for collaboration — regardless of language. Core intent patterns: (1) seeking help from another agent, (2) sharing knowledge/context with another…
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: