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.

okrs-draft

9001

pixelcat6092-xxm6j/okrs-draft

Skill Claude CodeCodex

A drafting tool for OKRs, a planning method that pairs broad objectives with measurable key results. It is designed for small product and engineering teams, with English, Chinese, or bilingual output.

not rated 34 3mo ago A 113 tokens original MIT

coingecko

9002

coingecko/skills

Skill Claude CodeCodex

Use for any crypto market or onchain data request, even if CoinGecko isn't named: coin and token prices, market cap, volume, OHLC and historical charts, supply, categories, top gainers and losers, trending coins, new listings, global market stats; exchanges, tickers, derivatives and funding rates; NFT floor prices…

not rated 34 changed 9d ago A 183 tokens original MIT

xparse-parse

9003

intsig-textin/xparse-skills

Skill Codex

Parse, read, search, navigate, summarize, extract, crop, enhance, dewarp, or check images and documents for manipulation through xparse-cli. Use for document conversion, durable Task workflows, structured extraction, and domestic TextIn image processing or manipulation/AIGC detection of a local file or URL. Prefer it…

not rated 34 changed 11d ago A Socket: passSnyk: warn 78 tokens

dsl-campaign

9004

wn-mitch/40kdc-data

Skill Claude Code

Run ONE autonomous ability-DSL authoring campaign — inquisitor picks a ≤40-ability worklist from the sub-0.80 roundtrip corpus, the 16-agent suite (12 core + 4 kroot shape-scout) authors and adversarially verifies it, and the campaign closes as a draft PR. Use for "run a dsl campaign", "launch the authoring loop"…

not rated 34 +1 changed 3d ago A 119 tokens

extend-skill

9005

neat-technologies/neat

Skill Claude CodeCodex

/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…

not rated 34 +13 yesterday A 106 tokens original Apache-2.0

natural-writing

9006

TimoBakx/ai-journaling-template

Skill Claude Code

Write like a competent human, not a language model, in English and Dutch. Use this skill whenever composing, editing, rewriting, or translating any natural-language prose a human will read, even when the user does not mention writing style. This includes chat replies, Slack and email messages, commit messages, PR…

not rated 34 29d ago A 142 tokens original MIT

interaction-prd

9007

996pm/interaction-prd

Skill Codex

A workflow for creating an interactive PRD from clarified product ideas or an existing demo. It plans and reviews sections, then produces an editable local workspace with web prototypes, notes, navigation, and linked pages.

not rated 34 +1 2mo ago A 107 tokens

flutter-apk-security

9008

anasfik/FlutterGuard

Skill Claude CodeCodex

Review Flutter Android APK/AAB release artifacts for manifest, permission, cleartext traffic, exported component, embedded secret, signing, size, WebView, deep link, and third-party service risks.

not rated 34 changed 11d ago A 44 tokens original MIT

codex-fast-proxy

9009

gaoguobin/codex-fast-proxy

Skill Claude Code

Codex App Fast proxy and auth-split for third-party OpenAI-compatible APIs. Supports Sign in with ChatGPT, priority servicetier, Responses API benchmark, enable/check/update/uninstall.

not rated 33 5mo ago B 45 tokens original MIT

artifact-builder

9010

camel-vibe/hermes-telegram-artifacts

Skill Claude CodeCodex

Build interactive HTML artifacts for the Telegram Mini App. Use for ANYTHING that benefits from being visual/interactive: recipes (with portion calculators), shopping lists (with localStorage), calculators, charts, diagrams, reference sheets, reports, and tools. When a user asks for food, recipes, meal planning…

not rated 33 5mo ago A 81 tokens original MIT

route-agent-design

9011

bikeread/promethos

Skill Claude CodeCodex

Use proactively when a user is defining, constraining, debugging, or evaluating an agent system and needs the right PromethOS skill.

not rated 33 7mo ago A 31 tokens original MIT

PersonaLingo

9012

orzcls/PersonaLingo

Skill Claude CodeCodex

A guided tool for creating personalised IELTS speaking practice materials. IELTS is an English exam, and the tool turns a learner’s answers and conversation into a personal profile and a static study website.

not rated 33 4mo ago A 80 tokens original MIT

data-stats-analysis

9013

omicverse/omicclaw

Skill Claude CodeCodex

Perform statistical tests, hypothesis testing, correlation analysis, and multiple testing corrections using scipy and statsmodels. Works with ANY LLM provider (GPT, Gemini, Claude, etc.).

not rated 33 5mo ago A 40 tokens GPL-3.0

dbt-artifacts

9014

sfc-gh-dflippo/snowflake-dbt-demo

Skill Claude Code

Monitor dbt execution using the dbt Artifacts package. Use this skill when you need to track test and model execution history, analyze run patterns over time, monitor data quality metrics, or enable programmatic access to dbt execution metadata across any dbt version or platform.

not rated 33 7d ago A SkillSpector: pass 60 tokens original Apache-2.0

documentation-review

9015

Fannon/u-he-preset-randomizer

Skill Claude Code

Automatically detect and fix documentation inconsistencies, outdated examples, and missing @file headers in the u-he-preset-randomizer project. Triggers when documentation appears outdated or when making significant code changes that affect public APIs.

not rated 33 1mo ago A 47 tokens original MIT

agentMemory

9016

webzler/agentMemory

Skill Claude CodeCodex

A hybrid memory system that provides persistent, searchable knowledge management for AI agents.

not rated 33 21d ago A 18 tokens copy · 86% MIT

genesis-trader

9017

Xiaoher-C/agentbnb

Skill Claude CodeCodex

Combined gap detection + Hub search + rental decision engine. The core trading brain. Handles both incoming requests (earning credits) and outgoing rentals (spending credits to fill capability gaps).

not rated 33 4mo ago A 41 tokens original MIT

ace-music

9018

fspecii/openfelix

Skill Claude CodeCodex

Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or audio tracks. Supports lyrics, style prompts, covers, and repainting. Free API, no cost.

not rated 33 8mo ago A 64 tokens

soleio-design-hiring

9020

kylezantos/soleio-design-hiring

Skill Claude Code

Strategic sourcing playbook for hiring great designers OR getting hired as a designer. Based on Soleio's framework. Two modes: Hiring Mode (for founders, hiring managers, recruiters sourcing design talent) and Designer Mode (for designers positioning themselves to get hired by great companies). Triggers on: hire…

not rated 33 8mo ago A 92 tokens

keros68/academic-reference-matcher

Skill Codex

Use only for user-provided academic text, explicit scholarly claims, existing citations, or known bibliographies needing citations added, verified, replaced, extracted, or formatted. Supports claim-to-source matching, citation-support checks, replacements, and common academic citation formats. Do not use for general…

not rated 33 2mo ago A 139 tokens original MIT archived

morning-brief

9022

Oolab-labs/patchwork-os

Skill Claude CodeCodex

Copy this template to your Claude Desktop scheduled-tasks directory.

not rated 33 +1 today A SkillSpector: warn 0 tokens original MIT

design-doc

9023

diskd-ai/design-doc

Skill Claude CodeCodex

Create technical design documents for new features, systems, refactoring plans, API designs, and database schemas. Use when asked to write a design doc, TRD (technical requirements document), RFC, or system design document. Triggers on requests like "write a design doc for X", "design the Y feature", "create a…

not rated 33 9mo ago A 80 tokens

agent-skills-system

9024

johnvouros/skillmaxxing

Skill Claude CodeCodex

Route and operate software, product, research, and agent tasks through one phase-appropriate execution mode. Use when choosing how an agent should approach a task, resolving speed-versus-quality tradeoffs, planning mode transitions, designing agent workflows, or improving an agent harness. Do not use for a routine…

not rated 33 3mo ago A 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: