agentic-ai skills

10,186 tagged agentic-ai, measured the same way as everything else here.

Browse within: agent 412agentic-workflow 386agents 271agent-orchestration 265coding-agents 200ai-automation 178babysitter 178agentic 172cursor 172ai-tools 152LLM 148agent-framework 147software-architecture 146agentic-framework 138

adding-external-mcp

290

XAIHT/Tlamatini

Skill Claude CodeCodex

The authoritative reference for adding a NEW external MCP server to Tlamatini universal MCP client layer. Covers the full lifecycle: catalog import, transport selection, activation, runtime provisioning, diagnosis, verification, and troubleshooting. READ THIS BEFORE calling externalmcpimport, before editing…

not rated 16 yesterday A SkillSpector: warn 71 tokens original MIT

expense

291

Caprista/KarvyLoop

Skill Claude Code

Read a receipt or invoice — pasted text, or a photo/scan — and turn it into one clean, structured expense record: merchant, date, currency, total, tax id, and itemised amounts, with those amounts checked to actually sum to the stated total. OCR text is dirty (O↔0, l↔1, misplaced decimals); this skill calibrates that…

not rated 16 +6 yesterday A 0 tokens original MIT

DauQuangThanh/hanoi-rainbow

Skill Claude CodeCodex needs its repo

Analyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to…

not rated 16 +1 7mo ago A 186 tokens original MIT

artifact_editor

293

sandeshnaroju/ai-skill-engine

Skill Claude CodeCodex

Skill for generating, searching, reading, surgically editing, and rolling back digital artifacts (code scripts, 1000-page documents, spreadsheets, presentations, SVG diagrams, 2D/3D CAD drawings, geospatial maps, and industrial automation/schedules).

not rated 16 +4 yesterday A 56 tokens

skill-creator

294

a-tokyo/agent-skills

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 15 1mo ago A 64 tokens copy · 88% MIT

usage-guard

295

shirley-xue-2025/usage-guard

Skill Claude Code

Arm proactive 5-hour usage protection for long Claude Code sessions (batch, subagents, high window % at start). Daemon reads account-level 5-hour window usage (not per-session). User types /usage-guard at session start. Re-arm every sitting. If user mentions usage-guard by name, read this file and run arm.sh.

not rated 15 1mo ago A 75 tokens original MIT

agentv-eval-writer

296

EntityProcess/agentv

Skill Claude CodeCodex needs its repo

Write, edit, review, and validate AgentV EVAL.yaml / .eval.yaml evaluation files. Use when asked to create new eval files, update or fix existing ones, add or remove test cases, configure graders (llm-rubric, script), review whether an eval is correct or complete, convert between EVAL.yaml and evals.json using agentv…

not rated 15 2mo ago A 129 tokens original MIT

jup-architect

297

andrader/jup

Skill Claude CodeCodex

Use when analyzing the jup codebase, identifying technical debt, suggesting architectural improvements, or ensuring high engineering standards.

not rated 15 1mo ago A 28 tokens

backlog-goal

298

mazen160/backlog

Skill Claude CodeCodex

Goal-driven autonomous workflow on top of the backlog CLI. Two strict modes — PREP (exhaustive intake, classify the goal shape, decompose into checkpoints + Scout/Judge/Worker tasks, seed the backlog project, stop) and RUN (execute the board, one active task at a time, structured receipts as comments, Worker tasks…

not rated 15 2mo ago A 167 tokens original MIT

the-news

299

SFKislev/The-News

Skill Claude CodeCodex

This skill gives agents access to the main headlines of many newspapers and news sites, across 20 countries, via a public API. The API has two modes: a live mode, updated in near real-time, and an archive mode that lets you fetch the headlines from a given moment in time. In both modes, the endpoint returns a JSON…

not rated 15 2mo ago A 31 tokens original MIT

weather

300

liquidos-ai/Odyssey

Skill Claude CodeCodex

Get current weather and forecasts (no API key required).

not rated 15 20d ago A 13 tokens GPL-3.0

tokenless-install

301

jazelly/tokenless

Skill Codex

Install, upgrade, repair, and verify Tokenless API CLI, agent skills, browser/runtime dependencies, and the optional macOS menu app. Use for requested installation, upgrades, setup, browser sign-in handoff, or installation health checks.

not rated 15 +1 changed 2d ago A SkillSpector: warn 52 tokens original MIT

make-video

302

av/skills

Skill Claude CodeCodex

Build a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents — builders never review their own work. Quality decisions are grounded in project context (identity, audience, goals) and established visual/motion design principles. Measurable criteria (text size…

not rated 15 +3 5d ago A SkillSpector: warn 104 tokens original MIT

tenable/cyberagents-exchange

Skill Claude CodeCodex

A dependency-free Claude skill that groups vulnerability findings by the fix they share and ranks the shortest set of actions that retires the most weighted risk.

not rated 15 +1 today A 36 tokens

vibesurfer

304

frane/vibesurfer

Skill Claude CodeCodex

Agent-native headless browser. 26 primitives over a Unix-socket wire protocol. Real WKWebView (macOS), WebKitGTK 6 (Linux), or WebView2 (Windows) — all three engines verified per-commit by a real-browser integration suite. Optimistic concurrency via state tokens; tree-delta wire format; durable session/page/auth state…

not rated 14 +1 changed 6d ago A SkillSpector: warn 81 tokens original Apache-2.0

harmix-music-search

305

Harmix/harmix-skills

Skill Claude CodeCodex

Search for music tracks using natural language prompts or video content via the Harmix AI API. Use when the user asks to find music, search for songs, discover tracks, needs music recommendations based on mood/genre/tempo/scene, or wants to find music for a video, video soundtrack, or music that matches video content.

not rated 14 5mo ago A 72 tokens original MIT

daily-deep-brief

306

KCNyu/clawock

Skill Claude CodeCodex

A scheduled, pre-market investment briefing for Hong Kong and United States stocks. A deterministic preparation step gathers data and an agent adds judgment, while a later step validates and publishes the result.

not rated 14 changed yesterday A SkillSpector: pass 163 tokens original MIT

api-testing

309

laragentic/agents

Skill Claude CodeCodex

Comprehensive API testing, validation, and test suite generation.

not rated 13 5mo ago A 14 tokens

weshop-openapi

310

weshopai/weshop-dsh-plugin

Skill Claude CodeCodex

Use for WeShop image and video generation, editing, and transformation tasks — virtual try-on, model swap, background replace, pose change, canvas expand, background removal, AI video generation, product/photo generation, and more.

not rated 13 21d ago A SkillSpector: pass 51 tokens original MIT

code-review

311

denn-gubsky/loomcycle

Skill Claude CodeCodex

How to review a slice of a code repository with high precision — confidence-scored findings, project-guideline compliance, and Karpathy behavioral guidelines (simplicity, surgical scope, surfaced assumptions). Use when reviewing or auditing source files.

not rated 13 today A 49 tokens original Apache-2.0

cto

312

yzfly/skills

Skill Claude CodeCodex

Startup / AI-startup CTO who is also a top-tier individual contributor. Two modes: (1) greenfield — turn fuzzy business intent into a buildable design (brief.md, arch.md, specs/) through conversation; (2) brownfield — work hands-on inside an existing codebase: investigate, recommend, refactor, write features, debug…

not rated 12 18d ago A 174 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: