agentic-workflow skills

4,508 tagged agentic-workflow, measured the same way as everything else here.

Browse within: agent-orchestration 260agentic-framework 224agentic 214agentic-coding 212agent-framework 170ai-coding-agents 156ask-cli 156adaptive-learning 141ai-education 134ai-literacy 121ai-coding 113atdd 111claude-code-plugin 105competency-based-education 99

openspec-explore

49

Happenmass/omux

Skill Claude CodeCodex

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

not rated 95 1mo ago A 39 tokens

aikito

50

lsaint/aikito

Skill Claude CodeCodex

Install, configure, and operate Aikito workspaces, including memory, skills, project resources, MCP servers, subagents, adoption, synchronization, and status verification.

not rated 105 yesterday A 38 tokens original MIT

task-final-report

51

postmelee/hyper-waterfall

Skill Claude CodeCodex

Apply the final report and PR publication procedure for a Hyper-Waterfall task. Write the final report (report.md), mark the daily task board complete, create the final commit, push the remote publish/task{N} branch, and create an Open PR to {BASEBRANCH}. Invoke only immediately before PR publication after all stages…

not rated 79 +1 1mo ago A 74 tokens original MIT

skillsmith-agent

52

smith-horn/skillsmith

Skill Claude CodeCodex

Delegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills before you install them. The Skillsmith Agent diagnoses in full for free, proposes a batched fix plan, and changes files only with your per-changeset approval, with one-step undo. Triggers: "ask the Skillsmith…

not rated 78 +1 today A 100 tokens

Kubernetes编排

53

microwind/ai-skills

Skill Claude CodeCodex

A guide for using Kubernetes, a system that deploys and manages containerized applications across servers.

not rated 76 +1 3mo ago A 47 tokens

claude-api

54

datascienceworld-kan/vinagent

Skill Claude CodeCodex

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.

not rated 74 5mo ago A 84 tokens copy · 100% MIT

company-setup

55

TOKTOKHAN-DEV/agent-company

Skill Claude CodeCodex

A project setup helper that checks and installs the exact dependencies a code project needs, then applies the chosen company template. It is meant for projects whose files are assembled from a shared core and a selected template.

not rated 75 +1 9d ago A 78 tokens original MIT

JasonxzWen/harness-hub

Skill Claude CodeCodex

Load when the user asks for private agent interaction audits from local Codex/Claude Code traces, task profiles, tool-call decisions, collaboration bottlenecks, prompt/rule or automation-log audits, closeout retrospectives, or evidence-backed Skill/project-rule/Eval/SOP/OKF improvements.

not rated 72 1mo ago A 65 tokens

aixyz

57

AgentlyHQ/use-agently

Skill Claude CodeCodex

Build, run, and deploy an AI agent using the aixyz framework. Use this skill when creating a new agent, adding tools, wiring up A2A/MCP protocols, configuring x402 micropayments, or deploying to Vercel.

not rated 72 1mo ago A 54 tokens original MIT

site-audit

58

brennhill/Kaboom-Browser-AI-Devtools-MCP

Skill Claude CodeCodex

Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.

not rated 65 today A 34 tokens AGPL-3.0

bnomei/kirby-mcp

Skill Claude CodeCodex

Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.

not rated 59 5d ago A 37 tokens original MIT

daw-cli

60

Goldwaterfung/Stratawright

Skill Claude CodeCodex

Instructs agents to control Stratawright DAW via the daw-cli command-line IPC interface. Covers session state, transport, track management, gain staging, VST3/AU plugin hosting, signal routing, clips, MIDI timeline editing, and non-visual DSP analysis & audio intelligence. Requires the DAW application to be running.

not rated 59 +1 3d ago A 72 tokens CC-BY-4.0

premortem

61

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 57 +1 3mo ago A 138 tokens original MIT

leefanv/omit-design

Skill Claude CodeCodex

Bootstrap a fresh omit-design project's visual theme from an existing Figma file — extract design tokens (colors + spacing) and PUT the result to the dev-server so the workspace can apply it to theme-editor. Use when the user pastes a figma.com URL and wants to seed the project's theme. Patterns are produced…

not rated 54 +1 3mo ago A 84 tokens original MIT

ElmatadorZ/MoneyAtlas-ClaudeSkill-Agent

Skill Claude CodeCodex

Use this skill for ANY financial market, investment, or macro-economic analysis. ALWAYS trigger this skill — do not skip it — when the user asks about: BTC, bitcoin, crypto, gold, silver, oil, stocks, forex, bonds, interest rates, Fed policy, inflation, deflation, stagflation, market structure, trading setups…

not rated 54 1mo ago A 186 tokens original Apache-2.0

UCSC-VLAA/VisualClaw

Skill Claude CodeCodex

When inferring character intent or behavioral patterns from video, validate inferences against cumulative observed actions rather than isolated moments or assumptions.

not rated 55 +1 2mo ago A 31 tokens original MIT

allinherog-star/ai-skills

Skill Claude CodeCodex

A sales-account research guide for sales, marketing, operations, and product teams. It uses provided material to examine why a customer or prospect is not moving forward.

not rated 51 +1 3mo ago A 70 tokens

testing-strategy

66

shinpr/agentic-code

Skill Claude CodeCodex

Selects the narrowest sufficient test boundary from requirements, repository evidence, and maintenance cost. Use when deciding integration or E2E coverage.

not rated 49 6d ago A 32 tokens original MIT

QA Review Templates

67

pageel/para-workspace

Skill Claude CodeCodex

Sidecar data for /qa workflow — Red Team personas, dimension checklists, and QA report templates loaded just-in-time.

not rated 49 22d ago A 29 tokens

news-draft

68

alp82/aistack

Skill Claude CodeCodex

Draft a summary and a topic for every undrafted news inbox item, one file per item.

not rated 46 2d ago A 23 tokens original MIT

context-checkpoint

69

clarity-digital-development/tworkflow

Skill Claude CodeCodex

Use when context usage needs checking or a compact/clear decision is due — a context warning or usage figure appears, the user asks whether to compact or clear, the session shows degradation (re-read files, repeated corrections, forgotten constraints), or a dev-workflow phase boundary is reached (step committed…

not rated 46 +1 2mo ago A 70 tokens original MIT

karpathy-guidelines

70

hyyhf/agent-book-code

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 47 +1 22d ago A 46 tokens copy · 100% MIT

soul-interview

71

ldbumble/taskuary

Skill Claude CodeCodex

Conduct a seven-question adaptive interview and turn the answers into Taskuary's SOUL.md. Use when creating or substantially rewriting the owner's operating context, boundaries, priorities, relationships, and communication preferences.

not rated 45 changed today A 44 tokens original MIT

content-creator

72

video-db/agentic-streams

Skill Claude CodeCodex

Turn any research topic into a polished video with narration, dynamic visuals, and background music. Supports pluggable formats (briefing, fireship-explainer, and more). Researches via parallel subagents, scripts a narrative arc, sources real-world assets (stock footage, memes, logos) from APIs and a persistent…

not rated 42 +1 15d ago A 91 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: