agentic-ai skills

10,342 tagged agentic-ai, measured the same way as everything else here.

Browse within: agent 427agentic-workflow 387agents 269agent-orchestration 267coding-agents 199agentic 186ai-automation 178babysitter 178LLM 163ai-tools 152software-architecture 146agent-framework 140agentic-framework 139agent-plugins 137

direct

553

rhettcarillo/claude-code-direct-skill

Skill Claude Code

Work autonomously to a finished, verified result instead of narrating options or stopping for permission; spend the cheapest model that cannot get it wrong; report in a short scannable form; and get measurably better each run by recording what actually went wrong. Use when the owner says /direct, "do wonderful…

not rated 1 9d ago A 121 tokens original MIT

summon

554

secondorderai/summon-skill

Skill Claude CodeCodex

Generate bespoke, stack-aware Claude Code agent files for tech teams. Creates specialized AI agent personas (backend, frontend, fullstack, AI/ML, DevOps, QA, security, code reviewer, performance engineer, system architect, tech lead) that Claude Code autonomously picks up from .claude/agents/. Use this skill whenever…

not rated 1 5mo ago A 194 tokens original MIT

bootstrap

555

Stepkar2004/init-configurator

Skill Claude Code

Phase 0 of any project - fire whenever asked to start, scaffold, set up, or adopt a project ("new Python CLI", "set this repo up properly", "add a frontend stack"). Interview, scaffold via OFFICIAL creators, describe into project.yaml, prove with gates.

not rated 1 1mo ago A 59 tokens original MIT

counsel

556

DataJinipk/contexai-consulting-agents

Skill Claude CodeCodex

Senior Contract Administrator & FIDIC / EPC contract specialist for oil, gas, refining, petrochemical, polymer, and upstream capital works. Use whenever the user mentions contract drafting, contract administration, FIDIC (Red Book / Yellow Book / Silver Book / Pink Book / Gold Book / Emerald Book / White Book), Pearl…

not rated 1 3mo ago A 507 tokens original MIT

git-commit-helper

557

lc-rezende/AI-Custom-Skills

Skill Claude CodeCodex

Generate conventional commit messages without scopes based on staged changes. Use when the user asks for commit message help, has staged changes, or is about to commit.

not rated 1 5mo ago A 36 tokens original Apache-2.0

writing

558

takoyaro/the-agency

Skill Claude Code

Format standards and an anti-AI-slop reference for writing and editing documents — READMEs, changelogs, commit messages, PR descriptions, release notes, and general prose or docs. Use when drafting or editing any of these, or when asked to make writing clear and honest. Supplies the standard for each document type…

not rated 1 2mo ago A 121 tokens original MIT

platform-api

559

MakingChatbots/genesys-cloud-skills

Skill Claude Code

Queries the Genesys Cloud Platform API schema for endpoint details, permissions, parameters, and response formats. Use when user asks about Genesys Cloud API endpoints (e.g., "/api/v2/assistants/queues"), API documentation, API permissions, schemas, capabilities, or when implementing Genesys Cloud operations.

not rated 1 6mo ago A 65 tokens original MIT

youtube-research

560

yohn1985/jarvisbot

Skill Claude Code

Research a strategy/market question from many YouTube videos and return a decision-led report (not summaries).

not rated 1 2mo ago A 25 tokens original Apache-2.0

google-adk-python

561

vysotin/cc_google_adk_skill

Skill Claude CodeCodex

Build production-ready AI agents in Python using Google Agent Development Kit (ADK). Use when creating agentic Python applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), multi-agent orchestration, tool development (function tools, MCP, OpenAPI), session and state management…

not rated 1 6mo ago A 146 tokens

audit

563

slowdoctor-dev/workspace-md

Skill Claude CodeCodex

General-purpose workspace maintenance pass. Cross-cutting enforcement of multiple core values (One canonical home / Use-driven evolution) and rules (R1 capacity backstop / R3 source-trail integrity + citation backstop). Every action respects R4 T1-T2 boundary procedurally. 7-class issue scan + journal archival (>3…

not rated 1 3mo ago A 98 tokens original Apache-2.0

C31-plan

564

ChianW/C31

Skill Claude CodeCodex

Turn requirements into validated, executable plans. C31-brainstorm defines WHAT; C31-plan defines HOW — with coverage gates, wave analysis, and threat modeling.

not rated 1 17d ago A 34 tokens original MIT

mobile-design

565

phuonghx/aim-cli

Skill Claude CodeCodex

Guidance for designing and building mobile app interfaces on iOS and Android, including React Native and Flutter projects. Covers touch interaction, on-device performance, platform conventions, navigation, and offline behavior, and emphasizes reasoning about constraints over copying fixed values. Use it when creating…

not rated 1 2mo ago A 70 tokens original MIT

FI-Mihej/codebase-agent-mcp

Skill Claude CodeCodex

Provides token-efficient analysis of dependency libraries. Gathers all necessary information about given libraries. Improves development efficiency. Must be used before the actual development process.

not rated 1 1mo ago A 36 tokens original Apache-2.0

stock-research-agents

567

harshitagarwal2/StockResearchAgents

Skill Codex

Run StockResearchAgents as evidence-first, point-in-time company research through the standalone company-analytics.v1 workflow, including adaptive multi-source web retrieval, deterministic analytics, forecasts, outcome scoring, and a completed-only report. Use for company or security research in Codex or another…

not rated 1 4d ago A 89 tokens original Apache-2.0

ras-end-to-end

568

Zhonghao1995/Agentic-HEC-RAS

Skill Claude CodeCodex

Standard operating procedure for an auditable, headless HEC-RAS workflow via the hec-ras MCP server — how to plan, copy, edit boundaries, run, QA-gate, read results, compare, plot, audit, and safely stop. Use FIRST whenever an agent is handed a HEC-RAS project (.prj folder) or a results file (.p##.hdf) plus a…

not rated 1 27d ago A 113 tokens original MIT

browseros

569

psthi/browseros-skill

Skill Claude CodeCodex

Control the BrowserOS agentic browser (open-source Chromium fork) from a coding agent via its built-in MCP server. Use when the user asks to browse, click, fill forms, scrape/extract data, take screenshots, manage tabs/bookmarks/history, automate a website, do research + write files (Cowork), schedule a recurring…

not rated 1 17d ago A 107 tokens

task-observer

570

mostwise/dot-claude

Skill Claude CodeCodex

Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where the agent is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable…

not rated 1 1mo ago A 181 tokens

truthgate

571

ay7627514-dotcom/truthgate

Skill Claude CodeCodex

Gate high-stakes, factual, or multi-step Hermes tasks before action and verify completion against evidence.

not rated 0 1mo ago A 23 tokens original MIT

pyfit

572

badass-data-science/pyFit-agentic-polygon-nesting

Skill Claude CodeCodex

Nest 2D shapes onto rectangular sheet stock with minimal waste and export ready-to-cut DXF files, via the pyfit CLI. Use when the user wants to lay out/pack/nest parts on plywood, acrylic, sheet metal, or similar stock for a laser cutter or CNC router, or asks how many of a shape fit on a sheet.

not rated 0 1mo ago A 74 tokens original MIT

memory-search-mcp

573

CSOAI-ORG/memory-search-mcp

Skill Claude CodeCodex

Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.

not rated 0 8d ago A 0 tokens original MIT

mettle

574

Creed-Space/METTLE

Skill Claude CodeCodex

Use when a user wants to complete METTLE reverse-CAPTCHA challenges, obtain a signed result, or verify a METTLE credential.

not rated 0 changed 8d ago A 32 tokens original Apache-2.0

integritypulse

575

maryadawson-code/integritypulse

Skill Claude CodeCodex

Cloud cost forecasting via the integritypulse MCP server. Use when a user is planning cloud infrastructure, writing Terraform/Pulumi/CDK, comparing cloud providers, or asking "how much will this cost?" Provides verified pricing for AWS, GCP, and Azure — do not estimate cloud costs from training data when this skill is…

not rated 0 5mo ago A 92 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: