Skills for Codex

215,111 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

motion-video

12601

memi-design/design-skills

Skill Claude CodeCodex

Product animation, UI motion, portfolio videos — Apple-grade reveals, motion tokens, full production pipelines.

not rated 7 1mo ago A 22 tokens original MIT

kotlin-ktor-patterns

12602

gongyijie85/dsh-ecc

Skill Claude CodeCodex

Ktor server patterns including routing DSL, plugins, authentication, Koin DI, kotlinx.serialization, WebSockets, and testApplication testing. Use when building a Ktor server — routing, plugins, auth, DI, serialization, or tests.

not rated 7 +1 17d ago A SkillSpector: pass 55 tokens original MIT

api-harness

12603

sabbour/agentweaver

Skill Claude CodeCodex

Use the API harness to drive Agentweaver through its REST API, capture the complete request/response evidence, and emit a normalized agentweaver.persona-judge-verdict/v1 JSON verdict. It is for backend/API end-to-end validation; use the UI or MCP harness for those surfaces.

not rated 7 changed 3d ago A 0 tokens original MIT

snap-oci-analyzer

12604

rascheel/scheel-skills

Skill Claude CodeCodex

Alternative producer of snap-analysis.json for OCI/container input: Docker Hub URLs, image references, docker save tarballs, or pre-extracted config.json + rootfs/. Downloads with skopeo, extracts via docker-to-snap, derives the build architecture from OCI metadata, and delegates binary analysis to…

not rated 7 changed 19d ago A 224 tokens

pr-review

12605

CiscoDevNet/essentials

Skill Claude CodeCodex

AI-assisted review of one or more GitHub Pull Requests. Offloads deterministic checks (lint, complexity, duplication, security, perf) to repo linters via self-contained scripts, then applies LLM judgment to what linters cannot catch and posts high-signal findings after a single human approval. Pass one or many PRs…

not rated 7 2d ago A 121 tokens original Apache-2.0

agent-workflow

12606

galact-byte/galact-Skills

Skill Claude CodeCodex

Use when an agent must decide whether to proceed autonomously, ask for clarification, request approval, or select an appropriate verification scope for a coding or documentation task.

not rated 7 changed 18d ago A 35 tokens

cbctscope-reading

12607

rezamotaghi/cbctscope

Skill Claude CodeCodex

Drive the CBCTScope CBCT viewer through its MCP server for a human reader. Use when a user asks to open, navigate, window, bookmark, or snapshot a CBCT or dental radiograph in CBCTScope, or to run a reading choreography (MPR survey, pano survey, TMJ setup, replay saved views). Navigation only, never interpretation.

not rated 7 5d ago A 78 tokens AGPL-3.0

agy-delegate

12608

PyModel/claude-agy-mcp

Skill Claude CodeCodex

Delegate a coding task to the Google Antigravity CLI (agy) as a separate implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use Antigravity…

not rated 7 3d ago A 132 tokens original MIT

workshop-nightly-pilot

12609

microsoft/aibast-agents-library

Skill Claude CodeCodex ✓ vendor

Pilot an AIBAST industry-solution workshop end-to-end in a live Copilot Studio environment -- build the agent, run every demo prompt fresh, capture real screenshots, fix annotation boxes, file real product bugs -- then rotate to the next solution. Designed to be re-run nightly against all solutions/ workshops.

not rated 7 11d ago A 69 tokens original MIT

taste-director

12610

Taste-AI/skills

Skill Claude CodeCodex

Direct the design of websites and brand systems from evidence in Taste Engine references. Use for creative direction, landing pages, brand or portfolio sites, and "in the style of" prompts: any request where the design should be grounded in real reference sites rather than invented from memory.

not rated 7 4d ago A 0 tokens

type-designer

12611

nmassi/glyphs-mcp

Skill Claude CodeCodex

Trigger: type design, Glyphs, spacing, kerning, stems, color, proportions, masters, interpolation, production QA, typeface voice or DNA, differentiation, and anti-copycat analysis.

not rated 7 9d ago A 44 tokens original MIT

buildwright

12612

raunakkathuria/buildwright

Skill Claude CodeCodex

Apply agent-led software development workflows for planning, implementation, TDD, verification, security review, code review, shipping, repository analysis, and cleanup. Use when developing or maintaining a software project with Buildwright.

not rated 7 8d ago A 45 tokens

buscador-uruguay

12613

eduair94/cambio-uruguay

Skill Claude CodeCodex

Busca alquileres, oportunidades inmobiliarias, autos usados y precios de productos en Uruguay con los datos de cambio-uruguay.com. Usala cuando alguien quiera alquilar (presupuesto, barrio, garantía, mascotas, cerca del trabajo o la facultad), saber si un alquiler o un auto está caro, comparar barrios, comprar un auto…

not rated 7 changed 5d ago A 138 tokens

code-simplifier

12614

yeisonrestrepo/code-conductor

Skill Claude CodeCodex

Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why.

not rated 7 today A 38 tokens original MIT

chestnut-copy

12615

chestnutzoe/chestnut-copy-skill

Skill Codex

Use when a Chinese creator wants to write, rewrite, evaluate, or adapt copy with Zoe/Chestnut's copywriting method. Also use to review an existing script, transcript, or draft before filming or publishing: diagnose what attracts viewers, topic and audience risks, cover/title/hook alignment, retention risks, off-voice…

not rated 7 4d ago A 83 tokens original MIT

agentplaybooks-tools

12616

matebenyovszky/agentplaybooks

Skill Claude CodeCodex

Connect AgentPlaybooks skills, MCP servers, and federated OpenAPI tools to Hermes. Guide playbook sync, authentication, secret setup, and recovery.

not rated 7 +1 yesterday A 36 tokens original MIT

evo-delegation-guide

12617

ZekaiShi/evo-subagent

Skill Claude CodeCodex

Choose an existing evo-subagent role and prepare a focused delegation task. Use when deciding which agentkey to call or when a child task needs clearer scope and acceptance criteria.

not rated 7 +1 yesterday A 41 tokens original MIT

fdd

12618

ainetx/FDD

Skill Claude CodeCodex

Unified FDD tool for validation and search. Validates FDD artifacts (BUSINESS.md, DESIGN.md, ADR.md, FEATURES.md, feature DESIGN.md, feature CHANGES.md) against FDD requirements. Provides read-only search and traceability for FDD artifacts and FDD/ADR IDs with repo-wide scanning capabilities. Supports optional…

not rated 6 8mo ago A 88 tokens original MIT

My Commit Wizard

12619

kainulla/skillfire

Skill Claude CodeCodex needs its repo

Write a polished git commit message from my staged changes following Conventional Commits, with an optional emoji and the related issue key.

not rated 6 3mo ago A 29 tokens original MIT

caching-strategies

12620

KraitDev/skiLL.Md

Skill Claude CodeCodex

When improving read performance and reducing database load.

not rated 6 3mo ago A 15 tokens original MIT

video-notes-generator

12621

DDDFXYqiming/Agent_Extensions

Skill Claude CodeCodex needs its repo

Summarize video URLs or local videos into timestamped Markdown notes from complete transcripts and actual visual evidence, with adaptive sampling and targeted visual follow-up. Supports Bilibili, YouTube, Douyin and Kuaishou.

not rated 6 changed 20d ago A SkillSpector: pass 51 tokens original MIT

rabbit

12623

sidtheone/zodiac-skills

Skill Claude CodeCodex

The Filter (兔). Orchestrator and post-processor that makes LLM output actually readable. Invokes other zodiac animals based on what the user needs, then synthesizes and reshapes their raw output for the specific human reading it. Breaks the LLM default of audience-blind verbosity — walls of text, wrong detail level…

not rated 6 +1 6mo ago A 162 tokens

dsh-landscape

12624

cyanseek/dsh-landscape

Skill Codex

Run a read-only capability preflight before adding, installing, comparing, replacing, upgrading, disabling, composing, or building for DeepSeek Harness. Use when a user asks whether DSH already supports something, which plugin fits, whether an option fits the current profile, what risks or duplicates exist, what…

not rated 6 14d ago A SkillSpector: warn 76 tokens original MIT

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: