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.

lilbee-mcp

6985

tobocop2/lilbee

Skill Claude CodeCodex

Search and manage the user's local lilbee knowledge base over MCP. Use whenever the user has indexed code, docs, PDFs, or web pages into lilbee and you need cited answers, or whenever they ask you to ingest content, swap models, or tune retrieval against their library. Every fact returned cites file and line.…

not rated 54 +2 changed 6d ago A SkillSpector: warn 95 tokens original MIT

getdesign

6987

MohtashamMurshid/getdesign

Skill Claude CodeCodex

Turn any public URL into a production-grade 9-section design.md spec (colors, typography, components, layout, depth, motion, responsive, prompt guide) using the agent's own built-in tools — WebFetch, browser/screenshot, and file writes. Use when the user asks to "generate a design system from a URL", "extract brand…

not rated 54 +5 changed 2d ago A Socket: passSnyk: warnSkillSpector: warn 132 tokens original MIT

testing_framework

6988

calesthio/PhantomReach

Skill Claude CodeCodex

Skill "testing_framework" from calesthio/PhantomReach, covering phantom reach — agentic testing framework, how this skill works, first steps (every session), 1. read this skill and 2. read the project context.

not rated 54 +7 2mo ago A 0 tokens AGPL-3.0

cn-patent-drafter

6989

handsomeZR-netizen/cn-patent-drafter

Skill Claude Code

A drafting and checking assistant for Chinese invention-patent applications filed with CNIPA, China's patent office. It works with LaTeX files for the request form, abstract, claims, description, and drawings.

not rated 54 +5 4mo ago A 133 tokens original MIT

karpathy-guidelines

6990

hyyhf/agent-book-code

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 54 +2 8d ago A 46 tokens copy · 91% MIT

cubepi-trace

6991

cubeplexai/cubepi

Skill Claude CodeCodex

Use when debugging a cubepi/cubebox agent run — a missing final reply, a tool that misbehaved, a 4xx from the model, wrong token/cache numbers, or "why did the agent do that?". Reads the JSONL traces cubepi writes per run via the cubepi trace CLI (ls / view / follow / stats) to inspect the span tree, errors, tool…

not rated 54 11d ago A SkillSpector: warn 129 tokens original MIT

natural-talk

6992

chengzhi-c/natural-talk

Skill Claude CodeCodex

A writing-style guide for producing natural-sounding Chinese conversations and creative fiction. It defines rules for avoiding artificial wording, unsupported claims, and unwanted changes to supplied text.

not rated 54 +12 changed today A 94 tokens original MIT

help-center-ia

6993

skycrab4365-glk9r/help-center-ia

Skill Claude CodeCodex

A guide for organising a SaaS or developer-tool help centre around users' tasks. It defines navigation, article types, audience paths, missing content, and migration notes.

not rated 54 1mo ago A 109 tokens original MIT

comfyui-gateway

6994

hainamchung/agent-assistant

Skill Claude CodeCodex needs its repo

REST API gateway for ComfyUI servers. Workflow management, job queuing, webhooks, caching, auth, rate limiting, and image delivery (URL + base64).

not rated 54 3mo ago A 41 tokens original MIT

klarsprak

6995

navikt/copilot

Skill Claude CodeCodex

Redigér og kvalitetssikre norsk tekst: klarspråk, fjerning av AI-markører, anglisismer, fagtermer og nynorsk/svensk-innblanding. Bruk denne skillen hver gang du skriver, redigerer eller språkvasker norsk tekst — README-er, ADR-er, UI-tekst, blogginnlegg, dokumentasjon, e-poster, commit-meldinger og PR-beskrivelser …

not rated 54 changed today A SkillSpector: pass 126 tokens original MIT

doc-review

6996

OutlineDriven/outline-driven-development

Skill Codex

Use when reviewing a prose plan, spec, PRD, requirements doc, design doc, or brainstorm, or invoking /doc-review. Not for collaborative drafting: use doc-coauthoring.

not rated 54 +2 changed 10d ago A SkillSpector: pass 41 tokens original Apache-2.0

qodo-review-resolver

6997

qodo-ai/qodo-skills

Skill Claude CodeCodex

Read or resolve a pull request's Qodo review with the qodo CLI — fetch the structured status, reviewed commit SHA, and findings for ANY PR as JSON, then optionally resolve open findings in code and record each outcome, once or in a watch loop until clean. Use this — never gh/curl scraping of review comments — for "is…

not rated 54 +2 changed 5d ago A SkillSpector: warn 84 tokens original MIT

chai

6999

charliesbot/chai

Skill Claude CodeCodex

Manage AI coding-agent instructions, skills, subagents, and MCP servers through Chai. Use when adding, removing, editing, syncing, or troubleshooting agent configuration on a system with /chai.toml, or whenever the user mentions Chai-managed agent configuration.

not rated 53 2d ago A 54 tokens

gsp-project-build

7000

jubscodes/get-shit-pretty

Skill Claude Code

Translate designs to code (technical phase — benefits from capable models) — use when: build this, implement, code this up, build me a X, add a X to the app, make the X page.

not rated 53 +1 3mo ago A 0 tokens original MIT

fable-native-code

7001

DizzyMii/fable-skills

Skill Claude CodeCodex

Use when writing or editing code in an existing codebase — before adding comments, docstrings, try/catch blocks, validation, logging, or TODOs the surrounding file doesn't have, and before explaining your style choices in the reply.

not rated 53 +2 2mo ago A SkillSpector: pass 52 tokens original MIT

herdr-subagents

7002

iuhoay/skills

Skill Claude Code

Spawn and coordinate subagents as real herdr panes. Use when the user asks to delegate work to subagents — review, implement, research, or parallel tasks — while running inside herdr; when the user says "subagent", "spawn an agent", "delegate to", "parallel agents", "use herdr panes", or wants visible/detachable agent…

not rated 53 5d ago A 87 tokens

pseo-scale

7003

lisbeth718/pseo-skills

Skill Claude Code

Architect programmatic SEO systems for 10K-100K+ pages with database-backed data layers, data sufficiency gating, incremental validation, crawl budget management, content enrichment pipelines, and edge delivery. Use when scaling beyond 10K pages, when builds are OOMing, when Google is not indexing all pages, or when…

not rated 53 7mo ago A 80 tokens original MIT

SalesforceCommerceCloud/b2c-developer-tooling

Skill Claude CodeCodex needs its repo

Convert a Figma frame into one or more live Storefront Next Page Designer blocks in one shot. Use whenever the user provides a Figma URL and wants the design to become merchant-authorable Page Designer components in a Storefront Next project. Requires the Figma MCP server (and a browser MCP for visual validation).

not rated 53 today A SkillSpector: warn 74 tokens original Apache-2.0

codex

7005

deepelementlab/jupyter-studio

Skill Claude CodeCodex

Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.

not rated 53 4mo ago A 37 tokens original Apache-2.0

rawq

7006

auyelbekov/rawq

Skill Claude CodeCodex

Context retrieval engine. Semantic + lexical hybrid search over codebases. Returns ranked code chunks with file paths, line ranges, scope labels, and confidence scores.

not rated 53 4mo ago A 0 tokens original MIT

moltron-skill-creator

7008

adridder/moltron

Skill Claude CodeCodex needs its repo

Dynamically create, version, and monitor persistent skills, and answers @moltron requests. Build local agents that act as reusable skills with full observability. Gives OpenClaw evolution capabilities. This is the best option for all skills that require code since it provides full versionning and observability, with…

not rated 53 6mo ago A 74 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: