Skills

W

workshop

anthropics / cwc-workshops

Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types /workshop, asks for a workshop act or module ("act 2", "next act", "where am I"), wants a TODO(workshop-N) implemented or explained, or asks for help following WORKSHOP.md.

W

workspace-init

willoscar / research-units-pipeline-skills

Initialize a missing research Workspace from the repository template without overwriting existing Run state; use before Pipeline binding when the target under `workspaces/` has no valid core artifacts.

W

write-a-skill

leandrocfe / skills

Create new agent skills with correct structure, progressive disclosure and bundled resources. Use when the user wants to create, write, or build a new skill.

W

writing-plans

21307369 / superpowers-zh

Use when you have specifications or requirements for a multi-step task, before writing any code

W

writing-skills

21307369 / superpowers-zh

Use when creating a new skill, editing an existing skill, or validating that a skill works before deployment

W

writing-skills

lucianghinda / superpowers-ruby

Use when creating new skills, editing existing skills, or verifying skills work before deployment

A

add-pattern

pchalasani / claude-code-tools

Use this skill when you learn one or more design pattern(s) in the

A

adk-agent-builder

jeremylongshore / tons-of-skills-marketplace

Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel/Loop), tool wiring, evaluation, and optional Vertex AI Agent Engine deployment. Use when building, scaffolding, or deploying ADK agents on Google Cloud, or when wiring ADK tools and orchestration patterns. Trigger with "build an ADK agent", "scaffold an agent on ADK", or "deploy to Agent Engine".

A

adk-engineer

jeremylongshore / tons-of-skills-marketplace

Execute software engineer specializing in creating production-ready

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

A

agent-collaboration

pascalorg / skills

Multi-model agent orchestration using specialized agents for planning, coding, research, math/science, visual analysis, and adversarial review. Use when tasks are complex enough to benefit from different models' strengths, when you want adversarial review to catch blind spots, or when coordinating multi-step workflows across agent roles. Triggers on complex projects, multi-step tasks, architecture decisions, or when explicitly requested.

A

agent-context-loader

jeremylongshore / tons-of-skills-marketplace

'Execute proactive auto-loading: automatically detects and loads agents.md

A

agent-coordination

d-o-hub / rust-self-learning-memory

Coordinate multiple specialized Skills and Task Agents through parallel, sequential, swarm, hybrid, or iterative execution strategies. Use when orchestrating multi-worker workflows, managing dependencies, or optimizing complex task execution with quality gates.

A

agent-patterns

jeremylongshore / tons-of-skills-marketplace

'Execute this skill should be used when the user asks about "SPAWN REQUEST

A

agent-sessions

vladmdgolam / agent-skills

Search, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi`.

A

agent-skill-creator

ravnhq / ai-toolkit

Guide for creating effective, portable skills that extend Claude's

A

agent-teams-guide

hexbee / hello-skills

Guide for orchestrating and controlling Claude Code agent teams. Use when working with or managing multi-agent team coordination in Claude Code, including: (1) Creating and starting agent teams, (2) Controlling teammates (display modes, task assignment, delegation), (3) Best practices for parallel work, (4) Troubleshooting team issues. Covers concepts like team lead, teammates, shared task lists, and inter-agent messaging.

A

agent-tool-testing

naodeng / awesome-qa-skills

Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include agent tool testing.

A

AgentDB Learning Plugins

ruvnet / ruview

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

A

agentic-jujutsu

proffesor-for-testing / agentic-qe

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

A

ai-product-strategy

oldwinter / skills

Create an AI Product Strategy Pack (thesis, prioritized use cases, system plan, eval + learning plan, agentic safety plan, roadmap). Use for AI product strategy, LLM/agent strategy, AI roadmap, AI-first product direction.

A

amend

jayden-dang / skills

Use when an already-shipped, spec'd feature needs a small in-scope change — a

A

are-decisions-from-this-session-saved

mtngtools / agents

Ask what would be lost from the plan if this session ended now — decisions about the system made in conversation and never written down — drive each to a home or an approved forget, then answer honestly whether anything would have to be decided again.

A

argument-selfloop

willoscar / research-units-pipeline-skills

Build a final, machine-readable argument snapshot from current H3 sections and refresh section fingerprints before merge.

A

ask-me-bro

jayden-dang / skills

Routes among the already-installed development skills to the one that fits the task at

A

autonomous-loops

xu-xiang / everything-claude-code-zh

Patterns and architectures for autonomously running Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

A

autoresearch-setup

d-laub / dlaub-togo

Use when setting up an autonomous ML experimentation harness (an “autoresearch” loop): a fixed harness that owns data and metrics plus a hackable training script an LLM iterates on under a fixed time budget. Use when scaffolding harness.py/train.py/program.md, designing structured training-dynamics logging for agents to read, or enforcing that experiments cannot game the metric

B

batch

cowork-os / cowork-os

Plan and execute parallel, repeatable migrations across code, docs, research artifacts, ops configs, or mixed task sets.

B

batch-research

miantiao-me / aigc-weekly

Batch data collection skill that schedules researcher agents concurrently in batches to fetch all data sources.

B

brainstorming

jd-opensource / joysafeter

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

B

brainstorming

makerjackie / jackie-skills-starter

Use before creative implementation work to clarify intent, requirements, and design direction.

B

breezing

chachamaru127 / claude-code-harness

Team execution mode — backward-compatible alias for harness-work with team orchestration. Composer/composer 2.5 maps to the cursor backend.

B

browser-use

bmaltais / browser-use-skill

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.

C

cc-canary-html

delta-hq / cc-canary

HTML-rendered version of /cc-canary — produces a long-form nerf-detection report as a standalone dark-theme HTML file and auto-opens it in the browser. Same analysis as /cc-canary (forensic markdown writeup), same narrative placeholders, but the output is a styled HTML page suitable for viewing, sharing, or printing. Writes `./cc-canary-<YYYY-MM-DD>.html` to the current directory.

C

cc-cursor-cc

chachamaru127 / claude-code-harness

Validates brainstormed ideas with Cursor PM, updates Plans.md, then handoff back. Cursor ↔ Claude Code 2-Agent workflow support. Use when user mentions Cursor PM handoff, 2-agent plan validation, CC-Cursor round trip, or brainstorm review. Do NOT load for: implementation work, single-agent tasks, or direct coding.

C

checkpoint

identity16 / skills

Exit ritual for a work session. Use when the user invokes /checkpoint, says they are done for the day or leaving a project for a while, or accepts the wrap-up proposal armed by /lets-work. Routes each piece of understanding gained this session to its proper home — a code comment, the PR/commit message, or the personal journal — then records the visit marker the next /lets-work will brief from.

C

claude-api

jackspace / claudeskillz

This skill provides comprehensive knowledge for working with the Anthropic Messages API (Claude API). It should be used when integrating Claude models into applications, implementing streaming responses, enabling prompt caching for cost savings, adding tool use (function calling), processing images with vision capabilities, or using extended thinking mode. Use when building chatbots, AI assistants, content generation tools, or any application requiring Claude's language understanding. Covers both server-side implementations (Node.js, Cloudflare Workers, Next.js) and direct API access. Keywords: claude api, anthropic api, messages api, @anthropic-ai/sdk, claude streaming, prompt caching, tool use, vision, extended thinking, claude 3.5 sonnet, claude 3.7 sonnet, claude sonnet 4, function calling, SSE, rate limits, 429 errors

C

claude-code-agent

ben2pc / g-claude-code-plugins

Delegate coding, review, diagnosis, planning and structured-output tasks to independent Claude Code sessions through the `claude -p` Agent SDK entry point of the Claude Code CLI. Use cases include `--resume` / `--continue` for multi-turn sessions, `--output-format json` for single-result output, `stream-json` event streams, and scripted / CI calls that need `--worktree`, tool allowlists, `--bare` or structured JSON output.

C

claude-code-hooks

0xdarkmatter / claude-mods

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

C

code-agent

aws-samples / sample-strands-agent-with-agentcore

Autonomous coding agent. Delegate any task that involves understanding, writing, or running code — from a GitHub issue, a bug report, or a user request. It explores, implements, and verifies on its own.

C

connection-doctor

duvoai / skills

Diagnose and health-check the Connections and credentials a Duvo Agent relies on. Use when the user asks whether a Connection is set up or available, why an Agent is blocked on authentication, what a Connection can do, or wants a proactive check across an Agent or a folder of Agents. In Ask Duvo, for an Automation, starts from getAutomationReadiness. Reads each Build's Connections and their live state via the Duvo public API, names the problem, and proposes one concrete fix — handing off to run-debugger when the evidence lives in a single failing Run.

C

context-manager

rmyndharis / antigravity-skills

Elite AI context engineering specialist mastering dynamic context

C

context-mode

mohitagw15856 / pm-claude-skills

Keep Claude Code sessions productive across resets with output filtering, session logging, and auto-resume. Use when starting a long or complex coding session, when previous sessions lost context mid-task, or when you need Claude to resume exactly where it left off after a reset. Produces a session.log at the project root, filtered command output that preserves context, and automatic resume of in-progress tasks after any reset.

No description yet

C

crank-execute

chrisliva / liva-toolbench

Execute an implementation plan task-by-task with RED→GREEN→REFACTOR, independent reviews, and a retro.

C

cross-examine

zebbern / claude-code-guide

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

C

cuopt-skill-evolution

promptingcompany / nv-skills

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active—applies to every interaction.

C

cuopt-user-rules

promptingcompany / nv-skills

Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals—use cuopt-developer for those.

D

dart-genkit

dhruvanbhalara / skills

Use when building AI workflows, tool calling agents, structured outputs, or LLM pipelines using the Genkit Dart SDK.

D

deepgram-python-conversational-stt

deepgram / deepgram-python-sdk

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription. Covers `client.listen.v2.connect(...)`, Flux models, end-of-turn detection. Use `deepgram-python-speech-to-text` for standard v1 ASR, `deepgram-python-voice-agent` for full-duplex interactive assistants. Triggers include "flux", "v2 listen", "conversational STT", "turn detection", "end of turn", "EOT", "listen.v2", "flux-general-en", "flux-general-multi".

D

dev-task-loop

timlai666 / skills

This skill MUST be used when the user wants to process a backlog of dev tickets end-to-end with a known project / branch / merge target / task tracker / design reference workflow, but without committing to any specific platform (Jira / Linear / GitHub Issues / Notion / Figma / Zeplin / etc.). Trigger on requests like 「幫我跑任務」、「照我的流程把 backlog 做完」、「review failed 的全部處理掉」、「用我那套開發流程做事」、"work through my task list", "run my dev loop", "process my tickets end-to-end". MUST NOT be used for a single ticket, which belongs to the other dev-workflow skills. MUST ask the user up-front for project root, working branch, merge target, task list location, design reference location, and how to mark a task done — then loops through tickets implementing → verifying → committing → opening PR → merging → syncing → updating the tracker. MUST NOT bake in platform-specific API calls; figure those out at run time from the user's answers.

No description yet

D

dispatching-parallel-agents

lucianghinda / superpowers-ruby

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

D

ds-vision-skill

sorwcyra / ds-vision-skill

Add vision capabilities to text-only reasoning models. Use when the user provides images, screenshots, photos, charts, UI screenshots, code screenshots, math problem images, scans, PDFs, or documents and asks to describe, understand, reason about, read, OCR, extract text from, parse charts in, or analyze the content. By default calls scripts/vision-router.ps1 for automatic routing: image understanding goes first through the free racing pool GLM/Agnes, then custom-1/custom-2/custom-3/local, document parsing goes through MinerU, and plain text recognition goes through Baidu OCR or Windows OCR. All tools output standard JSON, which is then passed to the main model for reasoning and summarizing.

D

dstack-core

robertderose / dstack

Shared dstack workflow contracts and conventions. Installed as support for the other dstack skills; use directly when reviewing workflow authority, trust boundaries, or naming conventions.

Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are validated using reasoned analysis rather than simple vote counting. Reports merge verdict (YES / NOT SURE / NO). Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues in a collapsible section.

E

execute-common

jayden-dang / skills

Use when build-in-waves, build-by-story, or build-inline loads the shared controller recipe — produces an In-progress catalog stamp, a runtime-bound session snapshot, lease state, ledger state, and a revision-bound close receipt.

E

execute-gitlab-issue

nextstage-brasil / skills

(NS) Execute a GitLab issue end-to-end — first-act status, branch-reuse and source-branch gates, single-worktree isolation, atomic delivery, MR lifecycle, mandatory code review gate with bounded fix loop. Use when the user provides a GitLab ISSUE_URL or asks to implement a GitLab issue directly — not for local-only ad-hoc coding (use code-coder) or non-GitLab autonomous runs (use code-autonomous standalone). Delegates actual coding to the code-autonomous engine. Requires mcp-gitlab-usage for MCP and code-reviewer for the review gate.

Use when you have a written implementation plan to execute in a separate session with review checkpoints.

E

experts

flc1125 / skills

Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by distinct expert viewpoints.