codex skills

17,209 tagged codex, measured the same way as everything else here.

Browse within: claudecode 303agentic-ai 238coding-agents 208claudecode-skills 186skills 179agent 170ai-coding 170openai 143ai-tools 141awesome 141awesome-list 141codex-plugins 141copilot 137cli 103

paper-review

769

guruvamsi-policharla/paper-review-skill

Skill Claude CodeCodex

Systematic LaTeX paper review for correctness, clarity, and consistency. Builds overview from intro sections, then reviews each section in parallel.

not rated 17 7mo ago A 31 tokens original MIT

db-performance

770

sawrus/agent-guides

Skill Claude Code

PostgreSQL query performance — EXPLAIN ANALYZE, index design, pgstatstatements, slow query detection, connection pool tuning.

not rated 17 12d ago A SkillSpector: warn 32 tokens original MIT

PSPDFKit-labs/nutrient-agent-skill

Skill Codex

Process documents with Nutrient DWS Processor. Use for PDF generation and conversion, packet assembly, OCR, Processor JSON-content extraction, staged redaction, watermarking, signing, password protection, optimization, PDF/A, or PDF/UA output. Route high-fidelity markdown or spatial parsing to Nutrient Data…

not rated 17 +1 13d ago B Socket: passSnyk: warn 90 tokens

agent-bus

772

MustaphaSteph/agent-bus

Skill Claude CodeCodex

Coordinate work across Claude/Codex/Cursor sessions on the same machine via a local message bus. Use to delegate to helpers, get a second opinion, ask specialists by capability, or track shared tasks.

not rated 17 2mo ago A 45 tokens original MIT

NickGuAI/Herd

Skill Claude Code

Distill Herd commander memory, clean stale MEMORY.md entries, promote durable commander lessons into LONGTERMMEM.md, and propose shared-knowledge updates through a review gate. Use for periodic commander memory cleanup.

not rated 17 yesterday A 46 tokens AGPL-3.0

unsloppify

774

woerndl/unsloppify

Skill Claude CodeCodex

Remove AI writing tells from text. Use when a text artifact is the deliverable or a major part of one, such as documentation, PR or commit text, release notes, reports, marketing copy, code comments, or when asked to de-slop, humanize, or clean up text. Not for chat replies, status updates, or completion summaries…

not rated 17 +1 26d ago A 81 tokens

director-agent

775

62656456/ai-film-skills

Skill Codex

Create, revise, or diagnose screenplays and develop director treatments or pre-storyboard decisions covering causality, character action, dialogue, performance, visual storytelling, sound, editing, and optional AI-executable screenplay compilation. Exclude editing an existing image, static visual polishing, static…

not rated 17 +7 changed 4d ago A SkillSpector: pass 188 tokens original Apache-2.0

wu5-dev-flow

776

WenOwen/wu5-dev-flow

Skill Codex

A Chinese-language workflow for developing Python projects with written specifications, strict red-green-refactor TDD, and Git safety checks. TDD means writing a failing test, making it pass, then improving the code.

not rated 16 1mo ago A 94 tokens original MIT

xlbaoxl/interactive-map-builder

Skill Claude CodeCodex

Turn existing spatial or coordinate data into portable, browser-openable interactive map files and report-ready figures. Use when the user wants parcels, buildings, facilities, parking, roads, water, green space, projects, or Excel/CSV coordinates presented as a searchable, filterable, sortable map, map-and-list page…

not rated 16 changed 2d ago A 203 tokens original MIT

Coff0xc/coffee-skill

Skill Claude CodeCodex

A guide for creating and checking editable Office files, including PowerPoint presentations, Word documents, PDFs, and Excel workbooks. It also covers checking layout, formulas, and file structure.

not rated 16 3mo ago A 85 tokens

channel-telegram

779

moshthepitt/lionclaw

Skill Claude CodeCodex

Run and operate a Telegram channel worker for LionClaw using the kernel channel bridge APIs.

not rated 16 11d ago A SkillSpector: pass 22 tokens original MIT

acceptance-testing

780

onfire7777/universal-ai-skills-library

Skill Claude CodeCodex

Use for verifying business requirements with executable specifications using BDD frameworks. Covers Cucumber (Java, JS, Ruby), SpecFlow/Reqnroll (C#), Behave (Python), Gauge (ThoughtWorks), and Godog (Go). Includes Gherkin feature files, step definitions, BDD workflow, and cross-language examples. USE FOR: Cucumber…

not rated 16 yesterday A 163 tokens original MIT

workflow-skill-router

781

eric861129/Workflow-skill-router

Skill Claude CodeCodex

A routing guide for choosing the right coding-agent skill based on the size, stages, and long-term nature of a task. It can also account for skills the user or workspace has already specified.

not rated 16 yesterday A 56 tokens original MIT

Xialiang98/design-visual-frontend

Skill Claude CodeCodex

Design, build, redesign, or critically review distinctive frontend interfaces with strong composition, domain authenticity, responsive behavior, component coherence, and browser-verified visual quality. Use for websites, landing pages, login and form flows, dashboards, admin tools, product pages, portfolios, visual UI…

not rated 16 2mo ago A 80 tokens original MIT

implementation-loop

784

olddonkey/olddonkey-skills

Skill Claude CodeCodex

Delegate implementation to Codex, grok, or cursor-agent, then review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex, the grok 后端, or cursor-agent to write code, mentions handing off / delegating implementation to one of those backends, asks…

not rated 16 24d ago A SkillSpector: warn 215 tokens original MIT

anti-slop-review

785

markoblogo/abvx-agent-skills

Skill Codex

Review an implemented product UI or public prose surface for hard visual defects, design-system incoherence, repeated template patterns, and AI-writing tells without treating subjective taste as universal law. Use for pre-ship screenshots, browser review, README/tool-page copy, launch notes, guide prose, or redesigns…

not rated 16 +1 today A SkillSpector: pass 91 tokens original MIT

mcpmu

786

Bigsy/mcpmu

Skill Claude Code

Install, set up, and manage MCP servers using the mcpmu CLI. Use when the user wants to install mcpmu, register it as an MCP server, add/remove/list MCP servers, manage namespaces, set tool permissions, manage server-level denied tools, or expose servers via serve mode.

not rated 16 +1 changed 4d ago A SkillSpector: warn 64 tokens original MIT

ac-isolation

787

gni/agents-container

Skill Claude CodeCodex

Workspace location, Python venv setup, and Rust installation guide. Use as a quick reference for environment setup.

not rated 16 2mo ago C 26 tokens original Apache-2.0

interview-prep

788

riwonswain-ovo/OfferLoop

Skill Codex

An interview-preparation workflow that creates a tailored preparation document for a specific company, role, interview round, and personal background. A job description, or JD, is the employer's description of the role and requirements.

not rated 16 changed 6d ago A SkillSpector: pass 251 tokens original MIT

safeagentdb

789

Aidan945/SafeAgentDB

Skill Claude CodeCodex

Sets up and maintains SafeAgentDB-style database safety infrastructure for AFK agentic development. Use when integrating isolated local, develop, preview, and production database workflows; configuring Supabase/Vercel/GitHub Actions previews; adding migration guardrails; packaging SafeAgentDB into a project; or…

not rated 15 3mo ago A 72 tokens original MIT

compose-navigation

790

piyushverma0/android-agent-skills

Skill Claude CodeCodex

Jetpack Compose Navigation for Android AI agents. Use this skill whenever implementing navigation, NavHost, NavController, back stack, deep links, navigation arguments, routes, type-safe navigation, @Serializable routes, navController.navigate, popBackStack, navigateUp, bottom navigation, tab navigation, nested…

not rated 15 4mo ago A 138 tokens original MIT

claude-codex-bridge

791

Jayden-X-L/claude-codex-bridge

Skill Claude Code

Bridge Claude Code and Codex for bidirectional execution review. Use when Claude should send its result to Codex/GPT-5.5 for audit, audit Codex/GPT-5.5 handoffs, return feedback to Codex, or run an automated Claude-Codex review loop.

not rated 15 3mo ago A 68 tokens original MIT

hypothesis-validator

792

evgeniy038/hypothesis-validator

Skill Claude CodeCodex

Use for decision-grade startup hypothesis validation: kill/refine ideas, identify ICP, jobs, demand, money signals, wedges, and GTM paths via the bundled Russian research prompt.

not rated 15 4mo ago A 40 tokens

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: