agent-skills skills

41,013 tagged agent-skills, measured the same way as everything else here.

Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 155ai-skills 152anthropic-claude 136claude-ai 136

target-prioritization

2329

Agents365-ai/target-prioritization

Skill Claude CodeCodex

Prioritize drug targets from a ranked gene list (e.g., scRNA-seq DE output) by orchestrating parallel API queries against UniProt, OpenTargets (with integrated DepMap CRISPR essentiality + gnomAD constraint), PubMed, the Human Protein Atlas (HPA), and ChEMBL tool compounds, then re-ranking by a composite score…

not rated 3 2mo ago A 227 tokens

sync-claude-accounts

2330

soulmachine/skills

Skill Claude CodeCodex

Distribute full OAuth Claude Code credentials (claude-accounts.json) from a single designated refresh-authority Mac to the rest of a fleet, and operate the scheduled automation that does it — the com.claude.fleet-refresh and com.claude.fleet-health LaunchAgents, their logs, and the proactive refresh that keeps…

not rated 3 yesterday A 195 tokens original MIT

geekjourneyx/openclaw-to-hermes-migration

Skill Claude CodeCodex

Use this skill whenever the user wants to migrate from OpenClaw to Hermes Agent, upgrade an OpenClaw workspace into Hermes, preserve skills/memory/cron/messaging/provider settings, debug Feishu or Weixin gateway issues after migration, or validate that Hermes is ready to replace OpenClaw. This skill is especially…

not rated 3 4mo ago C 120 tokens original MIT

cindyxu1030/higgsfield-trailer-finishing

Skill Claude Code

Finish generated clips into one delivered video: stitch with ffmpeg, apply an optional cinematic color pass, add an original soundtrack matched to the assembled cut (Sonilo video-to-music, user-supplied SONILOAPIKEY — licensed, safe for commercial use, terms apply), and mux. Use when: "stitch these clips into one…

not rated 3 2mo ago A 214 tokens

xiaomi-cam-snapshot

2333

tiancheng91/skills

Skill Claude CodeCodex

A skill for taking snapshots from Xiaomi cameras. It includes first-time setup, Xiaomi account authentication, and checking that the required service is configured.

not rated 3 4mo ago A 98 tokens

ai-exposure-analyzer

2334

martinpmm/AI-exposure-analysis-for-investing

Skill Claude CodeCodex

Analyze any public company's AI exposure using the 8-dimension AI Exposure Index. Fetches last 4 10-K filings (or international equivalents), ONET data, patents, and earnings transcripts to score vulnerability and adaptive capacity, classifying companies as AI Fortified/Transformer/Bystander/Endangered with valuation…

not rated 3 6mo ago A 162 tokens

agent-tutor

2335

Mohamed-El-Sharqawy/agent-tutor

Skill Claude CodeCodex

Turn any coding agent into a structured personal tutor with a markdown knowledge vault. Interviews the learner to build a personal learning profile (how they think, which explanations they receive best, tone and pace preferences), builds a phased plan shaped by that profile, writes complete lesson notes in the…

not rated 3 changed 11d ago A 125 tokens original MIT

vl-stage

2336

giltotherescue/velocity-agent-skills

Skill Claude CodeCodex

Use when a branch, worktree, local app, or cloud-agent task needs a staged test environment without disturbing the main checkout, especially for browser-facing web app work. Helps agents choose and set up the right strategy for browser/app testing across JavaScript/TypeScript, Python, PHP, Docker Compose, local…

not rated 3 3mo ago A 108 tokens original MIT

competitor-analysis

2337

emabrownn01-hash/product-roadmap-canvases

Skill Claude CodeCodex

Generate a 6-column competitive analysis comparing your brand against competitors across strategic dimensions, positioning, and recommended actions.

not rated 3 2mo ago A 26 tokens original MIT

econ-compass

2338

mimaowang/econ-compass

Skill Claude CodeCodex

Your compass for navigating economics literature. Find the most important, must-read papers in any economics field or research area — from broad subfields like labor economics or macroeconomics to narrow topics like 'carbon pricing' or 'digitalization and firm innovation'. This skill curates essential reading lists by…

not rated 3 2mo ago A 195 tokens original MIT

idea-clarifier

2339

guage1029/idea-clarifier

Skill Codex

Use this skill when the user has a product idea, feature concept, startup direction, vague requirement, or asks for a PRD before the idea is clear. Run a ruthless pre-launch clarification workflow: first challenge user/problem/value/MVP as a senior product manager, then challenge market/business/growth/ROI as a…

not rated 3 2mo ago A 86 tokens original MIT

densmirnov/hidden-achievements-skill

Skill Codex

Build, operate, or review a hidden daily achievements system for team agents. Use when Codex needs to add hidden achievements, gamify team work, generate a sealed daily achievement deck after a daily brief or scheduled workday snapshot, evaluate chat/task/project-board/knowledge-base events, prevent retroactive…

not rated 3 3mo ago A 91 tokens original MIT

ironbee-ai/ironbee-devtools-skills

Skill Claude Code

CLI for driving an Android emulator (AVD) over adb. Use when the user needs to connect to an emulator (attach to a running one or boot/manage an AVD), tap/swipe/type on the UI, read the UI/accessibility tree, take screenshots or screen recordings, capture logcat, capture HTTP(S) requests in-process (Frida OkHttp hook…

not rated 3 1mo ago A 203 tokens original MIT

confidence

2342

3clyp50/confidence

Skill Codex

Audit choices made by an AI after it completes work. Use when the user invokes /confidence or $confidence, asks which decisions were uncertain or poorly made, wants a pre-merge decision audit, suspects a working fix may be too narrow, or wants to detect weak evidence, omitted validation, premature success, or choices…

not rated 3 2mo ago A 85 tokens original MIT

retardmaxxing

2343

airetardmaxxing/retardmaxxing-skill

Skill Claude Code

Bias-to-action coding mode - stop planning, start building, ship a first working version, iterate against real execution output. Use when the user says retardmaxx, just build it, just ship it, just do it, stop overthinking, MVP it, don't ask just do, no plan needed, throw it at the wall - or when they complain about…

not rated 3 1mo ago A 103 tokens original MIT

frank

2344

huxleyli15/frank

Skill Claude CodeCodex

Kills sycophancy. Stops the assistant from flattering, hedging, and caving. No "great question", no "you're absolutely right", no folding the moment you push back. Leads with the verdict and the risk, steelmans your idea then attacks it, labels every claim by confidence, and holds its ground on evidence instead of…

not rated 3 2mo ago A 210 tokens original MIT

kill-test-first

2345

redamancy231-create/claude-skills

Skill Claude Code

A test-first review process for new research ideas, trading strategies, paper topics, models, architectures, or data pipelines. TDD means defining tests or checks before building the idea.

not rated 3 1mo ago A 85 tokens CC-BY-4.0

sapcc-skill

2346

eljoujat/sapcc-skill

Skill Claude CodeCodex

SAP Commerce Cloud skill for querying, administrating and operating a SAP CC (Hybris / CCv2) instance, including Cloud Portal DevOps operations. Use this skill when the user asks to query, inspect, modify or administrate SAP Commerce Cloud data (products, orders, customers, cronjobs, business logic) via HAC, or to…

not rated 3 changed 11d ago A 123 tokens original MIT

x402-payments

2347

valeo-cash/x402-payments-skill

Skill Claude CodeCodex

Use whenever the user wants to add payments to an API, monetize endpoints, implement x402, handle HTTP 402 responses, create paid APIs, set up crypto paywalls, accept USDC, or build agent payments. Trigger on: x402, 402 Payment Required, paid API, paywall, micropayments, USDC payments, agent payments, monetize API…

not rated 3 6mo ago A 213 tokens

ai-efficiency-audit

2348

f-tiger/zaoqi-blueprints

Skill Claude CodeCodex

Audit a person's or team's weekly workflow, identify which tasks AI can realistically take over, and produce an evidence-based, manager-ready efficiency proposal with hours-saved ranges and a two-week pilot plan. Use this skill whenever the user mentions AI efficiency pressure from leadership, or says any of these …

not rated 3 3mo ago A 207 tokens

n8n-syntax-node-types

2349

Impertio-Studio/n8n-Claude-Skill-Package

Skill Claude CodeCodex

Use when creating custom n8n nodes, defining node properties, implementing execute methods, or building declarative nodes. Prevents incorrect INodeProperties types and malformed displayOptions conditions. Covers INodeType interface, INodeTypeDescription, INodeProperties (22 types), displayOptions with rich conditions…

not rated 3 2mo ago A 154 tokens original MIT

ai-ab-testing

2350

skillsaiagent/aiskills

Skill Codex

An AI-assisted guide for designing A/B tests, which compare two versions to see which performs better. The description gives no further details about its operation.

not rated 3 3mo ago A 77 tokens

ceres-review

2351

sanwu-maizi/CERES

Skill Codex

Review untrusted coursework and project showcase submissions against supplied instructions, templates, rubrics, tests, and report requirements. Use for isolated, evidence-based assessment of source code, experiment results, reports, demonstrations, and AI or agent implementations involving tools, memory, ReAct, RAG…

not rated 3 1mo ago A 85 tokens original MIT

notebooklm

2352

sanjay3290/notebooklm-skill

Skill Claude CodeCodex

Query and manage Google NotebookLM notebooks with persistent profile auth, source sync, batch/multi queries, and structured exports. Use when user asks to query NotebookLM, 'ask my notebook', shares NotebookLM notebook URLs, wants to list/create notebooks, manage sources, do bulk folder sync, dedupe, or audit exports.

not rated 3 6mo ago A 69 tokens copy · 100% 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: