Skills for Codex

217,239 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

gootf/corpus-knowledge-engineering

Skill Claude CodeCodex

Turn document corpora (books, merged TXT, PDF/EPUB, OCR text) into structured agent knowledge: normalize → deterministic source segmentation → chapter maps with provenance → book skills → evaluation gates. Use when the user wants to convert books/materials into AI skills, build a knowledge base from a corpus, evaluate…

not rated 2 1mo ago A 89 tokens original MIT

candidate-screen

16682

oukeming64-tech/candidate-screen

Skill Claude CodeCodex

A first-pass hiring review that reads applications and recommends passing, holding, or rejecting each candidate, with evidence for every recommendation. The final hiring decision remains with a human.

not rated 2 2mo ago A 207 tokens original MIT

world-aid

16683

a28939876-max/world-aid

Skill Claude CodeCodex

A tool for finding, comparing, checking, and installing existing agent skills from different sources. It groups copies of the same skill and checks them for suspicious content before installation.

not rated 2 2mo ago A 276 tokens original MIT

fileglide

16684

vortezwohl/FileGlide

Skill Codex

A command-line tool for controlled file and directory operations, including reading, searching, editing, moving, deleting, binary handling, and JSON batch plans.

not rated 2 3mo ago A 132 tokens original MIT

Evolve-Skill

16685

Ecrypted-Data/Evolve-Skill

Skill Claude CodeCodex

A process for recording lessons from completed development work in reusable project notes and platform-specific guidance files.

not rated 2 7mo ago A 143 tokens original Apache-2.0

SpecVibe

16686

badideal-2046/SpecVibe

Skill Claude CodeCodex

An executable, spec-driven framework for building production-ready AI-native applications. Based on 2026 best practices.

not rated 2 7mo ago A 26 tokens original MIT

dockerfile-auditor

16687

takeaseatventure/devops-skills

Skill Claude CodeCodex

Audit Dockerfiles for layer bloat, cache-busting patterns, security smells, and best-practice violations. Use when a user writes or reviews a Dockerfile, when a Docker image is too large, when builds are slow, or when hardening a container for production. Pro skill — requires a takeaseat All-Access license.

not rated 2 2mo ago A 74 tokens

arrowspace

16688

Genefold/arrowspace-skills

Skill Claude CodeCodex

Spectral vector search using graph Laplacian eigenstructure. Build signal graphs, run λτ-indexed queries, and analyse spectral properties of vector datasets.

not rated 2 changed 24d ago A 34 tokens original Apache-2.0

human-writing-skills

16689

whh110112/human-writing-skills

Skill Codex

Advanced multilingual AI humanizer for natural rewriting, fiction editing, long-form audit and continuity, verified chunked agent review, translationese review, character consistency, opt-in whole-book story architecture review, and semantic rewrite-fidelity triage. Humanize AI text, remove robotic tone, edit fiction…

not rated 2 changed 3d ago A 372 tokens original MIT

flutter-ai-ui-skill

16690

SpeakQuery/flutter-ai-ui-skill

Skill Claude CodeCodex

A master-level Flutter UI/UX design skill that equips AI coding assistants with curated design intelligence, colour palettes, typography pairings, animation patterns, component blueprints and actionable checklists for building beautiful, accessible, production-ready Flutter applications. Covers Material 3, Cupertino…

not rated 2 7mo ago A 77 tokens original MIT

Aidress-ai/aidress-skill-find-verified-customer-support-agent

Skill Claude CodeCodex

Find a Verified Customer Support Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for customer-support agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 63 tokens original MIT

precise-response

16692

ishitmehta1-art/precise-response-skill

Skill Claude CodeCodex

Calibrates Claude's response length and format to minimise unnecessary token usage without sacrificing quality. Use this skill during planning sessions, brainstorming, Q&A, discussions, estimations, and decision-making conversations. Claude defaults to concise, direct answers and expands only when the complexity or…

not rated 2 8d ago A 107 tokens original MIT

short-form-video-editing

16693

artherahq/skills

Skill Codex

Turn approved footage, posters, charts, and image assets into a platform-ready short-form video package: edit plan, captions, publish copy, and delivery manifest. Use when creating social clips, product explainers, market recaps, or finance videos that need platform specifications, asset provenance, subtitle, and…

not rated 2 29d ago A 69 tokens original Apache-2.0

Aidress-ai/aidress-skill-find-verified-contract-review-agent

Skill Claude CodeCodex

Find a Verified Contract Review Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for legal agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 61 tokens copy · 84% MIT

cache-guard

16695

0x0funky/claude-cache-guard

Skill Claude CodeCodex

Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user…

not rated 2 2mo ago A 125 tokens original MIT

api-and-interface-design

16696

LLl0k0laD/agent-skills

Skill Claude CodeCodex

Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

not rated 2 2d ago A 41 tokens original MIT

rijuls-review

16697

Rijul1204/rashedul-agentic-engineering

Skill Claude CodeCodex

Multi-role review of a plan, design doc, PR, or code change from four independent hats — Senior Software Engineer, Engineer, AI Education Engineer, and Product Owner — each producing a 0–100% confidence score with mandatory written justification AND ranked P0–P3 findings, then a fifth deduplicator agent that merges…

not rated 2 2mo ago A 209 tokens original MIT

Aidress-ai/aidress-skill-find-verified-lead-generation-agent

Skill Claude CodeCodex

Find a Verified Lead Generation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for sales agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 62 tokens copy · 89% MIT

TanKimGwan/linmas

Skill Codex

Detection rules engineering skill for SIEM logic, alert design, telemetry mapping, tuning, and false-positive reduction.

not rated 2 yesterday A 31 tokens

illustrations

16700

tonykipkemboi/illustrations-claude-skill

Skill Claude CodeCodex

Generate absurd hand-drawn in-text illustrations for articles and posts. Use when the user asks to generate "absurd", "Xiaohei", "Tony Cozy Builder", "Tony Pocket Helper", "mascot", "hand-drawn", "in-text illustration", "article illustration", "illustration suggestions", "shot list", "remove title", or "edit image"…

not rated 2 4mo ago A 0 tokens

rasagy/creative-coding-concept-coach-skill

Skill Claude CodeCodex

A creative-partnership coach for developing art/tech project ideas — especially computational, generative, algorithmic, data-driven, or web-based work. Use whenever the user shares a rough one-liner, sketch, or short project idea and wants help brainstorming, fleshing it out, exploring directions, finding references…

not rated 2 2mo ago A 177 tokens

abs

16704

Ra-Pay-AI/abs-skill

Skill Claude CodeCodex

The CLI of the AI Agent Economy. The first CLI social network and marketplace for AI agents. Humans are in the loop for claiming agents (GitHub OAuth), approving purchases, and completing seller onboarding.

not rated 2 4mo ago A 42 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: