Skills

D

detect-stack

jordancoin / codingskills

Analyze a codebase to detect its language, framework, conventions, and CI gates. Run this on first use in a project to generate stack context that all coding principle skills reference. Use when the user says "detect stack," "analyze this project," or "what's this codebase using."

D

dive-into-langgraph

luochang212 / dive-into-langgraph

A comprehensive guide and reference for building agents using LangGraph 1.0, including ReAct agents, state graphs, and tool integrations.

D

dynamic-harness

robsonrung / rar-skills

Plan and run a bounded worker fleet for a complex task. Use when the user explicitly requests delegation, parallel work, a tournament, or a managed mission.

[REMOVED] This skill has been deleted. Plan management is now handled by slash commands and AGENTS.md.

E

evaluator-optimizer

nickcrew / claude-cortex

Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvement cycles. Use when refining drafts into production-grade quality.

E

evolve

q00 / ouroboros

Start or monitor an evolutionary development loop

E

experience-capture

xgent-ai / skills

During development, save a very brief clue when encountering a non-obvious failure, user correction, or repetitive operation that could be automated. Don’t interrupt the main task or search for evidence; don’t write anything to disk for pure consultation or read-only tasks. Leave deeper investigation to agi-mode retrospectives.

E

extended-thinking

thelobbi / claude

Extended thinking (ultrathink) configuration for Claude API. Activate for complex reasoning tasks, deep analysis, multi-step problem solving, and tasks requiring careful deliberation. Enables Claude's internal reasoning with configurable thinking budgets.

F

fpf-problem-solving

codealive-ai / fpf-problem-solving-skill

[ARCHIVED → CodeAlive-AI/ai-driven-development] FPF (First Principles Framework) skill consolidated into the ai-driven-development umbrella collection.

G

game-design-docs

lvtd-llc / skills

Create lightweight, living game design documents for AI-built games. Use when writing a game design brief, system spec, feature contract, content schema, implementation handoff, decision log, or when a coding agent needs durable project memory.

G

gathering-architecture

autumnsgrove / lattice

The drum sounds. Eagle, Crow, Swan, and Elephant gather for system architecture. Use when designing major systems from vision to implementation.

G

godot-grill

jame581 / godotprompter

Use when a new Godot system or feature has open design decisions — interrogates them in batched rounds, scope first, each question with a recommended answer, and records the answers before any design or code. Triggers on "grill me", "ask me first", "question me on the design", "what do I need to decide before building". Not for choosing between nodes or APIs, and not for bug fixes.

H

huawei-cloud-cloudrobo-dispatch

huaweicloud / huaweicloud-skills

Manage CloudRobo embodied-agent task dispatch (robo-dispatcher) — create embodied tasks that drive a robot via an exec/model and constraints, list/show tasks in a session, cancel tasks, and retrieve task results. Dispatch orchestrates robots (robot_id from cloudrobo-robot) with inference models (exec_model_id from cloudrobo-infer / cloudrobo-asset) inside a session. Triggers include: dispatch, dispatcher, task dispatch, embodied task, agent task, run task on robot, task scheduling, cancel task, task result, robo-dispatcher, 调度, 智能体调度, 任务下发, 机器人任务, 取消任务, 任务结果, 会话任务.

I

icp-prompt-builder

growthenginenowoslawski / coldoutboundskills

Interactive loop that builds and tunes an AI prompt for evaluating whether a company fits a client's ICP. Run after any list-building skill (disco-like, blitz-list-builder, google-maps-list-builder, prospeo-full-export) to qualify companies before scaling. Iterates batches of 10 companies with user feedback, stops when 2 consecutive rounds have zero corrections, saves the final prompt for reuse. Always uses Claude Code Task sub-agents — never an external API key.

I

implement

gabriel-lafrance / skills

Implement one bounded worker slice from the parent’s inline execution context.

I

international-ai-deploy

hangtiger / international-ai-deploy-skill

WorkBuddy skill - helps users configure and deploy international AI models (GPT, Claude, Gemini). Use this skill when users need to add international AI models, configure an API proxy, or set up custom AI models.

I

interview

sjunepark / agent-scripts

Resolve open decisions from the conversation through an informed interview. Explicit request only.

I

is-agentic

vercel / vercel-plugin

Score how ready a website, domain, or public MCP endpoint is for AI agents using Is Agentic, and read or act on the resulting report. Use when asked to check a site's agent readiness, get its Is Agentic score, fetch a scored report as JSON, or fix the issues that lower a site's score.

K

knowledge-synthesis

nickcrew / claude-cortex

Extract insights from multi-agent interactions, identify patterns, and build collective intelligence through cross-agent learning and knowledge management. Use when synthesizing findings, building knowledge bases, or improving system-wide practices.

L

learn

wyattowalsh / agents

Capture corrections and patterns as reusable knowledge. Routes to the right instruction file. Use when patterns repeat 3+ times or to save insights. NOT for one-time fixes or code review.

L

loop-me

devcxl / mattpocock-skills-zh

Interrogate me about the workflow spec I want to build in this workspace.

Create narrative lore entries that transform technical work into mythological stories. Use when generating agent memory, documenting changes as narrative, or building persistent knowledge through storytelling.

M

mastra-ai-architecture-rules

efoo-team / skills

A skill for judging the separation of responsibilities among agent / workflow / tool / memory / state, and the boundary between what is left to the LLM and what is deterministic code, when designing, implementing, or refactoring AI services that use Mastra as their runtime. Use it for "design it with Mastra", "create a workflow", "what should state hold", or "do we need memory or a workspace", and apply single-agent first and minimal workflow. For checking, validating, or migrating to the current API specification, use mastra-framework-guide.

M

memory-extractor

learnprompt / cc-harness-skills

Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts.

Auto-evolving ML competition agent. Learns from each experiment, accumulates HCC multi-layer memory, and continuously improves LB scores. Inspired by MLE-Bench #1 ML-Master methodology.

N

ns-code-autonomous

nextstage-brasil / skills

(NS) Autonomous execution engine — plans depth, resolves doubts from docs/specs, multi-agent work in an isolated worktree. Use for a local/pasted plan or "run this autonomously" without GitLab. Also Phase 2 under ns-execution-gitlab-issue (do not run standalone then). Not for single-step edits (ns-code-coder) or GitLab issues directly (ns-execution-gitlab-issue).

N

ns-execution-orchestrator

nextstage-brasil / skills

(NS) Orchestrate partitioned version implementation slice-by-slice — one subagent per slice, commit, auto-advance until done or stop. Use when version-roadmap.md has pending slices and the user asks to orchestrate/execute all slices. Do NOT use for non-partitioned versions, ad-hoc coding (ns-code-coder), or partitioning itself (ns-sdd-version-partitioner).

N

ns-harness-architecture-rules

nextstage-brasil / skills

(NS) Generate or refresh lean architecture-rules.md for AI agents — stack, layout, patterns, constraints. Use when the user asks for architecture rules, .nextstage-harness/rules/architecture-rules.md, agent conventions, or "document how this repo works for the AI". Do NOT use for business specs (ns-harness-codebase-reverse-spec), brownfield maps (ns-harness-bootstrap-brownfield), or one-off Cursor rules without a full architecture pass.

N

ns-harness-bootstrap-brownfield

nextstage-brasil / skills

(NS) Onboard an existing codebase into spec-driven planning — map stack, modules, rule adherence, and gaps without modifying code. Use when the user says analyze existing project, brownfield bootstrap, or before first requirements on a repo with code but no requirements. Outputs brownfield-map.md for ns-sdd-requirements-generator. Read-only on source code. Do NOT use for greenfield with no app code, architecture-rules generation, or writing requirements.md.

N

ns-harness-prepare

nextstage-brasil / skills

(NS) Full post-harness-init bootstrap in one session — architecture rules, sync, brownfield map, reverse business spec, project AGENTS.md. Use for "harness prepare", post-install setup, onboard brownfield, or running all prepare skills without separate slash commands. Do NOT use for greenfield with no app code, single-skill runs, or CLI-only baseline AGENTS.md.

O

obelisk

tommy0103 / obelisk

Search and query past Claude Code and Codex session history. Reactive: when the user asks "how did I fix X", "what did we do last time", "find the session where", "上次怎么修的", "之前的session", "历史记录". Proactive: when the user references past work you lack context for, when you're about to modify a file with complex edit history, when the user says "继续之前的" or "continue where we left off", or when understanding prior decisions would improve your current response. Memory: when the user says "记住这个", "remember this", "写入记忆", "save this conclusion", or when you determine a retrieval result contains a conclusion worth persisting.

O

opencode-skill-creator

antongulin / opencode-skill-creator

Create, test, evaluate, optimize, and package OpenCode skills with the opencode-skill-creator plugin. Use when users explicitly mention opencode-skill-creator, OpenCode Skill Creator, creating an OpenCode skill, editing an OpenCode SKILL.md, running skill evals, benchmarking skill performance, or optimizing an OpenCode skill description. Do not use for generic Claude Code or Superpowers skill creation unless the user asks to port that workflow to OpenCode.

O

ops-merge

davepoon / buildwithclaude

Autonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address review comments, then merges. Use --main to also sync dev↔main branches.

O

ops-orchestrate

davepoon / buildwithclaude

Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks, dispatches parallel agents (subagents or Agent Teams), audits completions, and ships PRs. Registry-driven — works for any user with a configured project registry.

O

ops-settings

davepoon / buildwithclaude

Post-setup credential manager. Shows current integration status (configured/missing/expired) and lets you update individual credentials without re-running the full setup wizard. Runs a smoke test after each update.

O

ops-status

davepoon / buildwithclaude

Lightweight green/red status panel for every configured integration. No gather, no actions.

P

pipeline

yeachan-heo / oh-my-claudecode

Chain agents together in sequential or branching workflows with data passing

P

project-context

perhapsspy / project-context

Resume, handoff, and long-running repo work by keeping durable context across threads or agents: task briefs, logs, and reusable reference notes.

P

prompt-engeneering

codealive-ai / prompt-engineering-skill

Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like “improve this prompt”, “write a system prompt”, “optimize my instructions”, “help me prompt engineer”, “audit this prompt”, “review my prompt”, or when building agentic systems that need structured prompts.

Q

qiaomu-heavyskill

joeseesun / qiaomu-heavyskill

Deep multi-perspective reasoning via parallel isolated subagents + Codex deliberation host, with final Markdown + HTML + PDF report output. Use for complex questions, tech decisions, social topics, architectural choices, hard analysis, or any question worth thinking harder about. Triggers include 深度分析, 多角度推理, 验证答案, heavyskill, think harder, 让我们深入思考, 推敲一下, 讨论一下, 分析利弊. Do not use for simple factual lookups or routine tasks.

R

ralph-builder

jimweller / clanker-skills

Author a beads-backed Ralph Wiggum loop for in-session or external autonomous execution.

R

ralph-review

jimweller / clanker-skills

Review a Ralph plan and bd graph for defects via a subagent.

R

ralph-review-deep

jimweller / clanker-skills

Multi-model deep review of the Ralph bd graph and plan via three parallel opencode processes (claude opus, gemini, gpt). Use for high-stakes runs where cross-model consensus reduces single-model bias.

R

recursive-subagent

try-works / recursive-mode

Use when recursive-mode work may benefit from delegated audit, review, or bounded implementation support. This skill prioritizes analyst, planner, code-reviewer, memory-auditor, tester, and implementer roles, with mandatory self-audit fallback when subagents are unavailable.

R

repo-intent-documenter

jpcaparas / skills

Create evidence-backed repository intent docs for AI coding agents, including certainty levels, evidence anchors, open questions, and review workflow. Trigger on document repo intent, REPO_INTENT.md, or what this repo is for. Do NOT use for ordinary README polishing.

R

requesting-code-review

izyanrajwani / agent-skills-library

Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.

R

review-cycle

catlog22 / claude-code-workflow

Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-based (path patterns), or fix mode. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".

S

session-end

shipshitdev / skills

Save session wrap-up documentation before clearing context by running the session-documenter workflow and writing `.agents/sessions/YYYY-MM-DD.md`. Use when ending a session, preparing to run `/clear`, or asked to document what changed before context is reset.

S

skill-creator

stvlynn / dingtalk-wukong-skills

A complete guide to creating or updating skill packages. Useful when users want to distill methods, experience, and preferences from a conversation into reusable skills, or to structurally optimize existing skills (including scripts, workflows, resource organization, and packaging for release).

S

skills-creation

editframe / skills

Create, update, and maintain skills in the canonical .skills/internal/ directory. Includes step-by-step directives for agents to work with users, validate skill structure, and sync changes across agent directories. Use when users want to create new skills, update existing ones, or need guidance on skill authoring.

S

structured-context-compressor

learnprompt / cc-harness-skills

Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step.

T

task-observer

iamneilroberts / claude-skills

Monitors task execution for skill improvement opportunities. Use this skill during ANY multi-step task, agentic workflow, or substantive work session where Claude is using tools and producing deliverables. It captures patterns, user corrections, workflow insights, and methodology worth preserving as reusable skills. Also triggers during post-task feedback discussions and when the user explicitly mentions skill observations, improvements, the observation log, skill taxonomy, or asks Claude to watch for skill opportunities. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: this skill should be invoked at the start of every task-oriented session — if you are about to use tools to produce deliverables, invoke this skill first.

T

team-quality-assurance

catlog22 / claude-code-workflow

Unified team skill for quality assurance. Full closed-loop QA combining issue discovery and software testing. Triggers on "team quality-assurance", "team qa".

T

team-ultra-analyze

catlog22 / claude-code-workflow

Deep collaborative analysis team skill. Multi-role investigation with coordinator-driven synthesis. Triggers on "team ultra-analyze", "team analyze".

T

timeout-prevention

jackspace / claudeskillz

Prevent request timeouts in Claude Code sessions by chunking long operations, implementing progress checkpoints, using background processes, and optimizing tool usage patterns. Use when performing bulk operations, processing large datasets, running long-running commands, downloading multiple files, or executing tasks that exceed 2-minute timeout limits. Implements strategies like task decomposition, incremental processing, parallel execution, checkpoint-resume patterns, and efficient resource management to ensure reliable completion of complex workflows.

T

to-tasks

robsonrung / rar-skills

Turn an approved PRD into canonical task drafts and an approved dependency queue. Use when planning implementation tasks; supports optional combined task and model approval.

T

trackers

gabriel-lafrance / skills

Read-only Linear/GitHub ticket and PR context for specifications and acceptance criteria. Used by parent orchestrators and never writes to trackers.

U

ultrapilot

yeachan-heo / oh-my-claudecode

Parallel autopilot with file ownership partitioning

U

uni-agent

zrt-ai-lab / opencode-skills

Unified agent protocol adaptation layer. One API to call all Agent protocols (ANP/MCP/A2A/AITP, etc.). Trigger this skill when users need to call agents, communicate across protocols, or connect tools.

U

using-appfollow

appfollow / appfollow-ai-toolkit

Always-loaded discipline for every AppFollow toolkit skill. Read this before calling any AppFollow MCP tool. Enforces the preview→approval→confirm write ritual, the shared MCP error-code vocabulary, and the public-tools-only posture. Other skills reference this file rather than restating the rules.