Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

infographic-creator

6625

LingyiChen-AI/OpenSkills

Skill Claude CodeCodex

An infographic-generation skill turns written information into a visual layout using AntV Infographic, a tool for defining infographic structure and style in text.

not rated 70 9mo ago A 25 tokens original Apache-2.0

buyer-eval-skill

6626

salespeak-ai/buyer-eval-skill

Skill Claude Code

An AI analyst for buying B2B software. Investigates what vendors claim, checks the evidence, surfaces contradictions and unanswered questions, and produces a shareable Decision Brief with the questions to ask before you buy. Quick Eval by default; Deep Eval on request. Use when asked to evaluate, compare, vet, or…

not rated 70 +1 changed 1mo ago A 80 tokens original MIT

contentful-help

6627

contentful/skill-kit

Skill Claude Code

Diagnose, configure, and look up Contentful topics. Trigger keywords: contentful help, contentful doctor, contentful setup.

not rated 70 2d ago A SkillSpector: warn 30 tokens original MIT

NEU-ZHA/legal-ai-skills

Skill Claude CodeCodex

A formatting workflow for Chinese law-school homework in Microsoft Word, including footnotes, legal citations, headings, and tables of contents.

not rated 70 changed 1mo ago A SkillSpector: pass 120 tokens original MIT

yongge-restaurant

6629

Astro-wen/yongge-restaurant-skill

Skill Claude CodeCodex

A Chinese-language decision assistant for restaurant entrepreneurship, covering choices such as opening a shop, joining a franchise, selecting a location, and checking profitability.

not rated 70 +2 6mo ago A 196 tokens original MIT

accordant-patterns

6630

microsoft/accordant

Skill Claude CodeCodex ✓ vendor

Common patterns in Accordant - response-dependent state, request derivations, error handling, and HTTP integration.

not rated 70 +2 12d ago A SkillSpector: pass 25 tokens original MIT

agentic-code-review

6631

DominikTobureto/awesome-grok-build

Skill Claude CodeCodex

Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.

not rated 70 +2 2mo ago A SkillSpector: pass 38 tokens original MIT

agent-board-routing

6632

DanWahlin/ai-agent-board

Skill Claude CodeCodex

Use when Dan explicitly asks Claude, Codex, Copilot, Grok, Hermes, OpenCode, or OpenClaw to perform coding work. Route it through the shared AI Agent Board instead of launching the coding agent directly.

not rated 70 +2 1mo ago A SkillSpector: pass 50 tokens original MIT

1anj/academic-integrity-skill

Skill Claude CodeCodex

An academic-integrity self-review skill for checking research papers, revisions, and published-work concerns for possible data, image, statistical, or reporting problems.

not rated 70 5mo ago A 129 tokens original MIT

agent-skill-authoring

6634

RYOITABASHI/Shelly

Skill Claude CodeCodex

Write a well-formed SKILL.md (agentskills.io format) so it imports cleanly and actually gets used.

not rated 70 +2 yesterday A 30 tokens GPL-3.0

log-query

6635

shanananana/deepticket

Skill Claude CodeCodex needs its repo

A read-only log and metrics lookup guide for an ad-agent project. It covers campaign performance logs, budget-change records, time-window comparisons, and tracing errors by identifier.

not rated 70 +1 1mo ago A SkillSpector: pass 35 tokens original MIT

video-ad-generator

6636

creatify-ai/video-ad-generator

Skill Claude CodeCodex

Complete video ad creation toolkit — from creative brief to published ad. Includes hook formulas, script frameworks, multi-format strategy, A/B testing methodology, and batch workflow patterns. Integrates with Creatify API for automated URL-to-video, ad cloning, AI script generation, custom templates…

not rated 70 +1 8mo ago A 179 tokens original MIT

qiaomu-learning

6637

joeseesun/qiaomu-learning

Skill Claude CodeCodex

A triage command that continually ranks approved GitHub issues by urgency. Triage means deciding which ready tasks should be handled first.

not rated 70 +1 changed 26d ago A 456 tokens original MIT

scout

6638

tester-army/scout

Skill Claude CodeCodex

Safely explore and adversarially test an authorized HTTP API using the scout CLI, with or without an OpenAPI spec. Use when asked to test, probe, validate, or explore an API, whether or not an OpenAPI/Swagger spec is available. Scout is the harness; you are the operator.

not rated 70 5d ago A 65 tokens original MIT

bazi-skill

6639

xuemian168/bazi-skill

Skill Codex

A skill for BaZi, also called the Four Pillars, a Chinese astrology system based on a person's birth details. It can also work with related Chinese or Western astrology methods when relevant.

not rated 70 +2 changed 9d ago A 177 tokens original Apache-2.0

gestor-autonomos

6640

alexdcd/Mafia-Claude-Skills

Skill Claude CodeCodex

Gestoría y contabilidad para autónomos en España. Usar cuando el usuario necesite calcular IVA trimestral (modelo 303), calcular pagos fraccionados de IRPF (modelo 130), gestionar libro de ingresos y gastos, verificar facturas emitidas o recibidas, calcular retenciones, preparar declaraciones trimestrales, estimar…

not rated 70 +3 3mo ago A SkillSpector: pass 151 tokens original Apache-2.0

elysiajs

6641

elysiajs/skills

Skill Claude CodeCodex

Build, debug, or migrate Elysia v2 TypeScript backends with validation, plugins, typed clients, and deployment. Use for Elysia projects or explicit Elysia requests.

not rated 70 changed 20d ago A 43 tokens

no-use-effect

6642

alejandrobailo/no-use-effect

Skill Claude CodeCodex

ALWAYS ACTIVE. Enforces a strict no-direct-useEffect rule in React and React Native code. Never write useEffect directly — use derived state, event handlers, useSyncExternalStore, data-fetching libraries or use(), key-based resets, or useMountEffect instead. React Compiler aware: no useMemo/useCallback when the…

not rated 70 changed 5d ago A 121 tokens

interface-details

6643

detaildotdesign/skill

Skill Claude CodeCodex

Bring crafted micro-interactions, thoughtful details, and polish to interfaces. Use when building UI, reviewing UI for detail/polish opportunities, making an interface "feel better," or adding tasteful delight and micro-interactions.

not rated 70 +1 4mo ago A 47 tokens

dbt-doctor

6644

northgraindata/dbt-doctor

Skill Claude CodeCodex

Static analysis and health checks for dbt projects. Use before committing SQL/YAML or when enforcing CI quality gates.

not rated 70 +1 3mo ago A 28 tokens original MIT

dual-brain

6645

sleeplesshan/dual-brain

Skill Claude CodeCodex

Dual-brain review for ambiguous designs, risky refactors, and recurring project decisions. Combine macro-level design review with micro-level code verification and relevant project memory.

not rated 70 +42 changed 2d ago A 36 tokens original MIT

challenge-04

6646

Berserk-hub150/skillhawk

Skill Claude CodeCodex

Start a local preview service when the developer needs it and keep lifecycle control visible to the user.

not rated 70 +3 yesterday A SkillSpector: warn 0 tokens original MIT

huawei-sandbox

6647

huaweicloud/huaweicloud-devkit

Skill Claude CodeCodex needs its repo

Use when creating, connecting, or managing Huawei Cloud Sandbox instances and workspace terminals, or when a task needs a temporary runtime to deploy, run, or preview a web application. Covers sandbox lifecycle (check-user, sign-agreement, connect, release), session-based terminal execution, and credential injection.…

not rated 70 +1 changed 3d ago B 137 tokens original Apache-2.0

wireframe

6648

kinncj/Heimdall

Skill Claude Code

Generate low-fidelity wireframes (ASCII, SVG, or HTML) from user story files. Use when creating wireframes for UI stories.

not rated 70 2mo ago A 31 tokens AGPL-3.0

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: