aelf-node-skill
20161Skill Claude CodeCodex
AElf node querying and contract execution skill for agents.
not rated 4 1mo ago A 17 tokens
original MIT
Louishin/claude-api-cost-optimization
Skill Claude CodeCodex
Save 50-90% on Claude API costs with Batch API, Prompt Caching & Extended Thinking. Official techniques, verified.
not rated 4 2d ago A 33 tokens
original MIT
omv-find
20163Skill Claude CodeCodex
Finds and ranks open-source packages worth auditing for passive CVE/VulDB research. Use when the user asks for vulnerability research targets, CVE hunting candidates, packages to audit, projects to fuzz, or /omv-find. Supports npm, Python, Go, Rust, Java, Ruby, PHP, C#, Swift, Dart, Elixir, Perl, R, and Lua, with…
not rated 4 1mo ago A 122 tokens
original MIT
fabled
20164Skill Claude CodeCodex
Six-phase build discipline that turns one prompt into a complete, runnable deliverable with zero placeholders. Use for ANY non-trivial single-prompt build request — "build me…", "create an app/script/tool/site/game/bot/pipeline that…", "make a complete…", "write a program that…" — and whenever the user says…
not rated 4 8d ago A 171 tokens
original MIT
stock-images
20165Skill Claude CodeCodex
Search and download stock photos from Pexels, Unsplash, and Pixabay for projects, landing pages, UI mockups, and content. Use when users explicitly ask to find stock photos, need a hero/profile/content image, or want to download a selected stock image.
not rated 4 5mo ago B 57 tokens
original MIT
ai-skill-auditor
20166smartbrainactivity/smartbrain-skill-auditor
Skill Claude CodeCodex
A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.
not rated 4 7mo ago A 28 tokens
original MIT
engaging-networks-api
20167orkestre-ai/orkestre-engaging-networks
Skill Claude CodeCodex
Engaging Networks Public API integration for nonprofit data synchronization and reporting. Use when implementing Engaging Networks Public API calls, building campaign widgets, creating donor rolls, fetching supporter counts, retrieving donation summaries, or integrating EN data with external systems. Supports…
not rated 4 6mo ago A 85 tokens
original MIT
clarify-first
20168Skill Codex
Resolve unclear instructions before acting. Ask focused clarification questions until every ambiguity that could change scope, behavior, safety, compatibility, data sources, API contracts, or acceptance criteria is settled. Use whenever a request starts with cf: or cf :, or when the user explicitly requests…
not rated 4 1mo ago A 83 tokens
original MIT
mobile-ui-replicator
20169Neilander/mobile-ui-replicator
Skill Claude CodeCodex
You (the agent) just got asked to turn a UI screenshot + style reference image + a written description of the app's features into a working single-file HTML demo painted in the style of the reference. This file tells you how.
not rated 4 5mo ago A 0 tokens
harness-design
20170Skill Claude CodeCodex
Quality harness for design-dna Phase 3 output with browser-based visual verification. After an agent generates a design from a Design DNA JSON + user content, this skill acts as a verification and scoring layer — collecting all page resources via console/network inspection, performing section-by-section screenshot…
not rated 4 5mo ago A 232 tokens
original MIT
searxng-websearch
20171Skill Claude CodeCodex
Use this skill whenever the user wants to search the web, do research on a topic, fetch a webpage, or gather information from online sources using a self-hosted SearXNG instance. Triggers include: 'search for', 'look up', 'find online', 'deep research', 'fetch this page', 'web search', or any request that needs…
not rated 4 2mo ago A 130 tokens
original MIT
layout-discipline
20172crazyzlnofficial/layout-discipline
Skill Claude CodeCodex
A set of rules for keeping AI-generated web pages visually consistent, including their text sizes, spacing, alignment, cards, and colors.
not rated 4 3mo ago A 105 tokens
original MIT
aoa-memo-writeback
20173Skill Codex
Use only before any memo artifact exists to decide whether live-session, closeout, landed-work, PR, diff, or review evidence yields one guarded memo candidate, export, or no-write result. If a concrete memo candidate, export, object, corpus, lifecycle, or read-model target already exists, use aoa-memo. Do not use for…
not rated 4
changed 29d ago A 95 tokens
original Apache-2.0
ast-code-graph
20174Skill Claude CodeCodex
Use this skill ANY time you need to search for code structure, refactor symbols, analyze impact, find dead code, or trace dependencies. ALWAYS invoke BEFORE using grep for structural code analysis. Trigger categories: structural pattern search (e.g. useEffect without deps, async without try-catch, fetch calls outside…
not rated 4 16d ago A 196 tokens
original MIT
bitbake-metadata
20175prashantdivate/awesome-yocto-ai-agent-skills
Skill Codex
Official-doc-first BitBake metadata support for AI coding agents. Use when inspecting, creating, editing, or debugging BitBake recipes, appends, classes, include files, configuration, tasks, variables, overrides, fetchers, signatures, sstate, dependency graphs, parse errors, QA errors, or files ending in .bb…
not rated 4 3mo ago A 100 tokens
original MIT
wan27-image
20176Skill Claude CodeCodex
Free AI text-to-image generator powered by Alibaba's open-source Wan 2.7 model. No signup needed.
not rated 4 5mo ago A 27 tokens
skill-testing
20177Skill Codex
Test Agent Skills from tests/skillcases.yaml files. Use when validating whether a Skill triggers correctly, produces a dry-run plan, satisfies output contracts, handles edge/failure cases, or when asked to run Skill Test cases, judge Agent responses against YAML expectations, or produce Skill test reports.
not rated 4 3mo ago A 61 tokens
original Apache-2.0
innovator-computer
20178Skill Claude CodeCodex
A computer-science research adviser for designing novel ideas, finding gaps in existing research, comparing related work, and planning technical approaches.
not rated 4 5mo ago A 85 tokens
writing-skills
20179izyanrajwani/agent-skills-library
Skill Claude CodeCodex
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
not rated 4
+1 today A 20 tokens
skill-autoresearch
20180Skill Claude CodeCodex
Validates and improves agentic skills by running isolated executor agents against test briefs, scoring confusion, fixing unclear instructions, and rerunning until stop criteria pass. Use when asked to test or evaluate a skill, find skill failure modes, or harden a skill before reuse. Inspired by Karpathy's…
not rated 4 4mo ago A 67 tokens
microcks-openapi-mocking
20181Skill Claude CodeCodex needs its repo
Write OpenAPI examples that work with Microcks dispatchers for API mocking. Covers example pairing rules, JSON body dispatching, Groovy script dispatching, and dispatcher configuration via the Microcks API.
not rated 4 6mo ago A 47 tokens
original Apache-2.0
lets-talk
20182Skill Claude CodeCodex
Speak replies aloud through the ElevenLabs API during a conversational voice session. Use this skill whenever the user's prompt starts with "Let's talk" or "Okay, let's talk", or when the user says they want a speech session, voice session, spoken session, wants you to talk out loud, mentions using Wispr Flow or…
not rated 4 2mo ago A 112 tokens
understand
20183Skill Claude CodeCodex
Use when someone wants to genuinely understand something and have it stick — a topic, mechanism, paper, theorem, algorithm, domain, or real code — not just get an answer. Fires on comprehension intent even without the word "understand": "help me understand X", "derive X from first principles", "why does this behavior…
not rated 4 3mo ago A 134 tokens
original MIT
agent-forge
20184sinclarespeaking143/openclaw-superagent
Skill Claude CodeCodex
A tool for creating, improving, and reviewing skills and agents for OpenClaw. It has separate workflows for creating a skill, creating an agent, or improving an existing one.
not rated 4 today A 111 tokens
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: