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.

premortem

6649

AndyShaman/premortem

Skill Claude CodeCodex

A short premortem planning session that asks what could make a plan fail before work begins. It examines a plan from several viewpoints, suggests responses, and records the discussion in the project documentation.

not rated 58 4mo ago A 138 tokens original MIT

aidlc

6650

aws-samples/sample-aidlc-decisions-driven-skill

Skill Claude CodeCodex ✓ vendor

AI-DLC workflow orchestrator. Reads manifest state, dispatches to phase skills, manages rollback and status. Executes phases by loading and following each skill's SKILL.md.

not rated 58 +3 2mo ago A 38 tokens MIT-0

sop-build

6651

charlesdove977/procedure-ops

Skill Claude Code

Builds standard operating procedures from a guided interview, screen-recording transcript, or existing draft. Use when the user says "write an SOP", "document this process", "make an SOP for X", "I keep redoing this", "delegate this to my VA", "onboarding doc for new hire", "write up how I do this", or asks to audit /…

not rated 58 +1 3mo ago A 112 tokens original MIT

zz-haooo/Meta-Team

Skill Claude CodeCodex

Structured 5-step workflow for producing long-form research reports that satisfy rubric-based evaluation across 6 axes (Explicit, Implicit, Synthesis, Communication, Instruction Following, References).

not rated 58 +1 1mo ago A 41 tokens

sands-lab/nika

Skill Claude Code

Broad-search escalation toolbox. Enter when the blind start surfaces no symptom. Run phases in order, and exit the moment a helper surfaces an anomaly.

not rated 58 +2 yesterday A 36 tokens

sensei

6654

spboyer/sensei

Skill Claude CodeCodex

WORKFLOW SKILL — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE…

not rated 58 3mo ago A 91 tokens original MIT

fangongzi-perspective

6655

gaminiYJ/fangongzi

Skill Claude CodeCodex

A reference guide based on the thinking frameworks and examples of 梵公子, also known by similar Chinese names. It covers relationships, social strategy, personal development, conversation, and dating situations.

not rated 58 +1 5mo ago A 210 tokens

noahnan-max/private-equity-investment-dd-skill

Skill Codex

A guide for turning private-company investment materials into an evidence-based review and decision package. It covers private equity, venture capital, acquisitions, and other investments in companies that are not publicly traded.

not rated 58 +2 1mo ago A 106 tokens

plugin-authoring

6657

laurigates/claude-plugins

Skill Claude Code needs its repo

Add, modify, or delete a skill or plugin in this repo — frontmatter shape, the seven metadata files a plugin touches, and the create/delete checklists. Use when creating a new skill or plugin, removing one, or asking which files a plugin change must update.

not rated 58 today A SkillSpector: warn 59 tokens original MIT

clawd-emotes

6658

xixicc186/clawd-emotes-skill

Skill Claude CodeCodex

Create original pixel-art "Clawd" crab emotes as pure SVG + CSS keyframe animations (no frame-by-frame GIFs, no raster sprites), and optionally export them to looping GIFs. Each emote is a tiny pixel crab doing an activity — holding a prop, wearing a hat, reacting — built from / / and animated with @keyframes. Use…

not rated 58 +1 1mo ago A SkillSpector: pass 204 tokens original MIT

neuron-nki-writing

6659

aws-neuron/neuron-agentic-development

Skill Claude Code

Guide for writing and modifying NKI kernels. Covers new kernel creation from PyTorch/NumPy/natural language, editing existing kernels, adding shape/dtype support, refactoring tiling strategies, and implementing new features in NKI code. Use when user says "write NKI kernel", "convert PyTorch to NKI", "translate numpy…

not rated 58 28d ago A SkillSpector: warn 172 tokens original Apache-2.0

wp931120/tiny_agent

Skill Claude CodeCodex

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

not rated 58 +2 6mo ago A 131 tokens

whoamihappyhacking/lazycat-skills

Skill Claude CodeCodex

A guide to advanced networking for Lazycat MicroServer apps. It covers routing, multiple domains, TCP and UDP forwarding, cross-origin access, and complex proxy rules.

not rated 58 +2 20d ago A 57 tokens

openbiliclaw-adapter

6662

whiteguo233/dsh-openbiliclaw

Skill Claude Code

Use OpenBiliClaw's versioned Agent Bridge CLI to read multi-source recommendations, profile state, dialogue, probes, saved lists, and submit explicit feedback.

not rated 58 +1 5d ago A 40 tokens copy · 100% BSD-3-Clause

triaging-mutants

6663

mattwynne/yaks

Skill Claude CodeCodex

Use when mutation testing reveals survived mutants — guides deep analysis of whether each mutant signals a missing test, a design improvement opportunity, or an equivalent mutation.

not rated 58 1mo ago A SkillSpector: warn 34 tokens original MIT

media-publish-check

6664

XshuiAi/media-publish-check

Skill Codex

A review workflow for checking and adapting content before publishing it on Douyin, Xiaohongshu, Weixin Video Accounts, or Kuaishou.

not rated 58 +3 1mo ago A 192 tokens original MIT

level

6665

matteotitta/claude-code-marketing-quickstart

Skill Claude Code

Score your Claude Code environment on a fun 0-10 ladder (Tourist → Swarm) calibrated to the quickstart's 4 systems — Context, Skills, Integrations, Orchestration. Two front doors - an interactive quiz (zero setup, shareable) or a silent scan of your repo. Outputs a next-level roadmap plus a branded HTML dashboard or a…

not rated 58 +1 1mo ago A 133 tokens

paper-insight

6666

Stars-Shen/Paper-insight-skill

Skill Codex

Structured scholarly paper reading and research ideation. Use when Codex needs to read or summarize papers/PDFs, judge innovations, score paper quality and reading priority, compare related work, draft related work sections, expand a literature map with backward/forward citation chaining, identify limitations…

not rated 58 +4 3mo ago A 108 tokens original MIT

plate-rotation

6667

hssqz/plate-rotation-skill

Skill Claude CodeCodex

A Chinese-language tool for analysing rotation and strength among sectors in China's A-share stock market. It compares sector rankings, leading stocks, trading activity and changes over time from two data sources.

not rated 58 +1 25d ago A 207 tokens original MIT

zaycruz/hermes-opencode-plugin

Skill Claude CodeCodex

Use OpenCode as a meta-subagent for heavy coding work. Offload engineering tasks to OMO's multi-agent harness so Hermes stays focused on planning, memory, and orchestration.

not rated 58 +1 3mo ago A 42 tokens original MIT

codex-gpt-image

6670

ningzimu/codex-gpt-image

Skill Claude CodeCodex

Generate or edit images with GPT Image 2.5 through Codex/ChatGPT subscription authentication instead of OPENAIAPIKEY. Use for text-to-image, reference-image editing, or visual assets when the user wants local Codex auth, especially when no native image tool is available. Do not use for official OpenAI API-key billing…

not rated 58 +3 changed 5d ago A 79 tokens original MIT

senior_analyst

6671

rrred0324/senior-analyst

Skill Codex

A business and financial analysis skill with multiple data sources and several analysis modes. It supports reports, competitor comparisons, industry models, macroeconomic research, and scenario analysis.

not rated 58 +3 2mo ago A 44 tokens original MIT

convex-agent

6672

get-convex/agent-skills

Skill Claude CodeCodex

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

not rated 58 +3 7d ago A Socket: passSnyk: passSkillSpector: pass 25 tokens original Apache-2.0

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: