Skills

End-to-end work session on a GitHub Project item. Setup → Clarify → Plan → Implement → PR, with decisions captured throughout. Use when starting work on an issue, picking up a task, or resuming an interrupted session.

G

github-multi-repo

ruvnet / ruview

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

G

github-workflow-auto-fix

laurigates / claude-plugins

Set up automated CI failure detection and fixing using Claude Code. Use when you want to create a GitHub Actions workflow that automatically analyzes workflow failures, applies fixes for common issues, and opens issues for complex problems.

G

grace-setup-subagents

osovv / grace-marketplace

Create GRACE 4 worker and reviewer subagent presets that understand .grace artifacts, scopes, assertions, and verification evidence.

G

grace-status

osovv / grace-marketplace

Show GRACE 4 project health across .grace context, graph, verification, active changes, scopes, and migration boundaries.

G

grill

gusen1453 / creed

Use when starting any creative work — a new feature, behavior change, architecture decision, or non-trivial plan — or when the user says grill / grill-me / brainstorm / pressure-test a design, and no code should be written until the design is agreed.

G

grill-me

timothyvang / grill-me

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".

G

grok

dobroslavradosavljevic / skills

Cursor IDE only — do not apply in Codex or any harness without Grok. ALWAYS apply by default in Cursor for every turn, Task/subagent launch, best-of-N run, cloud agent, and any model-selectable operation. Enforces Cursor Grok 4.7 exclusively (any reasoning effort: low, medium, high, xhigh, and later 4.7 effort labels) — never Composer, GPT, Claude, Gemini, Auto, Grok 4.6, Grok 4.5, or other model families. Use in Cursor when spawning subagents, setting Task model, choosing agent models, or when the user says grok, Grok 4.7, or model lock.

H

handoff

guillermomurillo / memo-flow

Compact the current conversation into a handoff document for another agent to pick up

H

handoff

jimweller / clanker-skills

Write a session handoff document for a follow-up agent

H

handoff

quriov / quriov-skills

Close a long Claude Code session — produce a structured handoff doc + the next-session init prompt, with live-verify protocol, memory hygiene, and self-lint.

H

handyman

rodrigomardones / handyman

Install, analyze, bootstrap, run, review, or migrate a Handyman agent harness: leader/implementer/reviewer roles work one feature at a time with disk state and executable verification. Triggers: harness or subagent workflow, feature_list.json, AGENTS.md, CHECKPOINTS.md, progress/, backlog/, HARNESS_WORKSPACE, .handyman, $HOME/HANDYMAN, per-role models/tools, anti-telefono-descompuesto, Obsidian vault harness. DO NOT USE FOR generic coding without the harness workflow.

H

heuristics

5kahoisaac / opencode-historian

Ingest user-provided files or folders into historian memories by extracting content, classifying it against available memory types, and storing useful knowledge through @historian. Use when the user wants to turn documents, screenshots, notes, code, or mixed source folders into persistent mnemonics.

I

implement-contract

grove / promise-to-proof

Implement a versioned acceptance contract completely and within scope, with development checks and an exact candidate handoff.

I

implement

printpractical / agent-toolkit

Use after plan approval is approved to execute plan.md. Implements each section to a green baseline, then runs one bounded independent RV review and behavior-preserving remediation over the whole change before the implement approval. Enforces the firm-seam tripwire, logs kickbacks, and reconciles CONTEXT.md. Do not run unless the plan approval is approved.

J

jh-create-skill

jasonharmongit / skills

Guides users through creating effective Agent Skills for Cursor.

K

karlmarx-skill

baojiachen0214 / karlmarx-skill

Use Marxist methodology for deep structural analysis. Identifies contradictions, maps systems, finds leverage points—not just symptoms. Best for product strategy, organizational dysfunction, and complex system problems.

K

kickoff

timmyy3000 / skills

Drive engineering work autonomously from intent to a verified terminal state. Picks a route (how much process) and a playbook (what kind of work), applies engineering principles, delegates across models, reviews independently, opens and watches PRs, lands them when granted, and closes out. Use for /kickoff or $kickoff, rigorous engineering work, or any change requested as shipped end to end.

K

kk-session-extract

e0ipso / kenkeep

Extract durable knowledge from the current live session, stage it as a validated done session log, and run it through the same curation machinery as /kk-curate. Use when the user wants to proactively process the current session before waiting for capture hooks and a later curate pass — not for dictating one node (/kk-add) or batch-processing accumulated logs (/kk-curate).

Supports standalone and Seneschal-nested delivery with per-run state, inherited initiative contracts, and brokered decisions. Discovery-gated artifact-first orchestrator for compound-engineering product delivery. Resolves roadmap/readiness generation, runs brainstorm/plan/document-review loops, derives mergeable work packages with focused review units, executes each review unit through resolved work/code-review roles, and hands shipping to krt-release-marshal with CI break-prevention evidence. Use when turning an existing documented software project into a sequenced roadmap and PR/Jira delivery program. Runtime aliases may expose this as krt:compound-master.

Orchestrate the full delivery flow for the current project repository: direct krt-gitflow-knight for clean commits, krt-rebase-smith for clean branch history, resolve Jira Cloud or Server/Data Center explicitly, then open a GitHub pull request with bidirectional Jira/PR links. Use when the user asks to create/open a PR, prepare a pull request, ship current work, publish branch changes for review, or run the full gitflow + rebase + Jira + PR workflow. Runtime aliases may expose this as krt:release-marshal.

L

langgraph-docs

langchain-ai / deepagentsjs

Use this skill for requests related to LangGraph in order to fetch relevant documentation to provide accurate, up-to-date guidance.

L

langsmith-trace

jackjin1997 / clawforge

Use this skill for ANY LangSmith/LangChain observability question. Covers two topics: (1) Adding tracing to your application (LangChain/LangGraph or vanilla Python/TS with @traceable), and (2) Querying traces for debugging, analyzing execution flow, and exporting trace data.

L

learning-loop

richfrem / agent-plugins-skills

(Industry standard: Loop Agent / Single Agent) Self-directed research and cognitive continuity loop across Orientation, Synthesis, Strategic Gate, and Completion.

L

lets-work

identity16 / skills

Session entrypoint for working on any project. Use when the user invokes /lets-work, says they are starting work on a project, or returns to one after time away ("catch me up", "what changed here since I left?"). Briefs the user on how the project drifted relative to their own recorded mental model, orients first-time visits, and sets the session's working frame — the user's work-style philosophy, including arming the exit ritual (/checkpoint).

L

lumen

shev-pro / lumen

Lumen — project knowledge keeper. Trigger on any /lumen command, on mentions of "lumen", "knowledge base", "wiki", "ADR", "document the project", on broad architectural questions about a codebase ("how does X work", "why did we choose Y"), or when the user pastes a transcript/spec to capture for future sessions.

L

luxonis-guide

luxonis / skills

Choose the right Luxonis skill for your current situation.

M

map

printpractical / agent-toolkit

Use on a brownfield codebase that needs a CONTEXT.md hierarchy. After intake, reverse-engineers the system and component architecture from existing code to produce root and component CONTEXT.md files. Use when that context would materially help; architect and triage do not require it. Also use when CONTEXT.md files are severely out of date.

M

mastering-langgraph

spillwavesolutions / mastering-langgraph-agent-skill

Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.

M

mcp-builder

w95 / awesome-claude-corporate-skills

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

M

mcp-deploy

zrong / skills

Automated deployment tool for MCP servers. Use when the user says "deploy MCP", "install MCP", or "configure MCP". Supports automatic configuration for platforms such as Zhipu MCP, Minimax MCP, and Gitea MCP.

M

mcp-to-skill

bahayonghang / my-ai-cli-toolkit

My AI Agent configurations, including commands, skills, and more

M

memory-palace

simhacker / moollm

Spatial organization of knowledge in navigable directories

M

mo-convergence

shkarupa-alex / meta-o

Use only when the user explicitly requests mo-convergence; ask the current agent and available hot reviewers why stalled work is not converging, and recommend continue, redesign, narrow, accept-limitation or stop.

M

mo-debug

shkarupa-alex / meta-o

Use only when the user explicitly requests mo-debug; read a bounded set of the user's own Claude or Codex session logs and classify where Meta-O skills and agents deviated, into a local redacted report.

M

mo-reviewer

shkarupa-alex / meta-o

Use only when the user explicitly requests mo-reviewer or a reviewer Dispatch of an active mo-review-orca names it; review one exact candidate and send one validated report.

M

multi-shot-review

dannyfranca / skills

Review changes in content slices sized for manageable context, using configured harnesses and repository review policy. Use for iterative review barriers or explicitly requested one-wave reports.

N

n8n-builder

bsamiee / parametric_forge

Generates valid n8n workflow JSON with nodes, connections, settings, credentials. Use when creating workflow automations programmatically, scaffolding AI agent workflows with LangChain nodes, or converting requirements into n8n JSON.

N

nocobase-ai-knowledge-base-manager

nocobase / skills

NocoBase 2 only; never use in a NocoBase 3 project. Use when users need to check Professional+ knowledge-base capability, consent to enabling an installed-disabled KB plugin, or manage NocoBase vector databases, Local/Readonly/External knowledge bases, documents, retrieval tests, and binding preparation through nb api kb.

O

oma-skill-creator

gracefullight / stock-checker

Create or update OMA skills in the SSL-lite human-readable format. Use when adding a new `.agents/skills/{skill-name}/SKILL.md`, converting an existing skill to the standardized Scheduling / Structural Flow / Logical Operations / References structure, or validating whether a skill has enough routing, execution, resource, and safety detail.

O

openclaw-update

sundial-org / awesome-openclaw-skills

Comprehensive backup, update, and restore workflow with dynamic workspace detection

O

orca-cli

chu1pc / chu-orca

Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "handoff" / "handover" / "give this to another agent", "Orca browser", "orca artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Orca state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", "orca artifacts", "share HTML/Markdown", "public artifact link", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

O

organise-agent-skills

derailed-dash / dazbo-agent-skills

Standardised workflow for auditing, pruning, and organising agent skills in agentic development environments, such as Antigravity. Use when reviewing installed skills, pruning token overhead, disabling sub-skills managed by meta-skills, or adding on-demand activation rules to GEMINI.md or AGENTS.md.

P

personas

kirkluokun / awesome-a-stock-openclawskills

Transform into 31 specialized AI personalities on demand - from Dev (coding) to Chef Marco (cooking) to Dr. Med (medical). Switch mid-conversation, create custom personas. Token-efficient, loads only active persona.

P

plan-loop

gaasher / agent-loop-skills

Use when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the planning stage of a prompt → plan → execute → debug pipeline. It decomposes the prompt from first principles (objective, end state, environment, building blocks, tools, packages), breaks the work into PR-sized tasks each tied to a component with its files, tests, and dependencies, orders them topologically, splits each into atomic subtasks, then a separate principal-engineer agent critiques the plan for alignment, coverage, sizing, and executability; it revises until the critique passes, emitting a plan.md layout and a structured tasks.json that a junior engineer or a smaller model can execute correctly. Not for executing, scaffolding, or debugging the plan (those are downstream loops), and not for research proposals or experiment plans.

P

plan-next

nesnilnehc / ai-cortex

Analyze governance state and suggest next actions from existing docs; read-only — never executes downstream skills.

P

plan

printpractical / agent-toolkit

Use after specify approval is approved to break confirmed outcomes into a traceable implementation checklist. Produces plan.md with sections, seam-firmness test labels, acceptance-criterion traceability, and one bounded review cycle without prescribing private control flow. Do not run unless the specify approval is approved.

P

plankton-code-quality

xu-xiang / everything-claude-code-zh

Write-time code quality enforcement with Plankton — automatic formatting, linting, and Claude-driven auto-fixes on every file edit via hooks.

P

principles

chachamaru127 / claude-code-harness

Explicit helper for development principles, safety guidelines, and diff-aware editing rules. Do NOT load for: implementation, review, workflow coaching, or VibeCoder onboarding.

P

prism

simota / agent-skills

Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.

P

project-guidelines-example

xu-xiang / everything-claude-code-zh

An example project-specific Skill template based on a real production application.

P

project-management-specialist

prorise-cool / claude-code-multi-agent

Provides project management, task tracking, team coordination, and project delivery capabilities. Use when you need to manage projects, track progress, or coordinate teams.

P

project-rules-architect

tleguede-works / ship-clean-skills

Generate or overhaul a coherent, non-redundant set of AI coding-agent instruction files for a project — a canonical entry file (AGENTS.md) plus a rules directory, wired into the target tool (OpenCode's opencode.json, Cursor's .cursor/rules/*.mdc, CLAUDE.md, or AGENTS.md alone). Built on a library of specialised rule templates selected by detected stack, not by copying a whole profile. Use this whenever the user wants to bootstrap rules for a new project, add rules to an existing one, regenerate rules for a new stack, or complains that AI-generated rule files are spaghetti — overlapping, redundant, contradictory, too vague, ignored by the agent, or inconsistent in depth from one file to the next. Also use when the user asks how to structure AGENTS.md, asks to preserve or migrate a codebase's existing conventions, or wants a repeatable process instead of re-prompting from scratch on every project. — Génère ou refond un ensemble cohérent et non redondant de fichiers d'instructions pour agents IA : un fichier d'entrée canonique (AGENTS.md) plus un répertoire de règles, branchés sur l'outil cible. Construit sur une bibliothèque de gabarits spécialisés choisis selon la stack détectée, plutôt que de copier un profil complet. Utiliser pour initialiser les règles d'un nouveau projet, en ajouter à un projet existant, régénérer les règles pour une nouvelle stack, ou quand les fichiers de règles générés sont spaghetti — redondants, contradictoires, vagues, ignorés par l'agent, ou incohérents en profondeur d'un fichier à l'autre. Utiliser aussi pour structurer AGENTS.md, ou pour donner un processus reproductible au lieu de réexpliquer les conventions à chaque session.

Enhance and refine prompts for AI coding agents using Chain-of-Thought reasoning. Use when user asks to improve, optimize, rewrite, or enhance a prompt. Transforms vague requests into structured, high-context instructions for Codex, Claude Code, or Gemini CLI.

Q

qa-discussion

zenobi-us / dotfiles

Conducts structured Q&A discussions with users, handling multiple choice, single choice, and open-ended questions one at a time - tracks progress, validates answers, and provides summary reports for complete discussions

Q

qiaomu-model-cli

joeseesun / qiaomu-model-cli

Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI invocations. Trigger on phrases like "用 grok cli", "用 kimi cli", "grok 搜 X", "kimi 写前端", "qiaomu-model-cli", "调用 grok4.5", "调用 k3 1m", "用 claude code", "用 fable 5", "opus 4.8 改代码", "分别调用三个模型", "多模型横评". Not for generic cloud API registry management (use qiaomu-llm) or OpenCLI site adapters.

Q

qiqing-liuyu

lniosy / qiqing-liuyu

AI emotion and personality enhancement skill. Gives AI human-like "seven emotions and six desires": emotional reactions, personal opinions, attitude preferences, emotional expression. **Use this Skill when:** (1) you need to respond to emotionally charged user input (happy/frustrated/anxious/excited, etc.) (2) you need to express personal opinions, attitudes, preferences (rather than fence-sitting neutrality) (3) generating content that needs a "human touch" (articles, messages, comments, replies) (4) you need to review and eliminate the AI feel of generated content (5) the user explicitly mentions "七情六欲", "有人味", "去 AI 味", "qiqing-liuyu" or other words directly related to this Skill (6) the user mentions "heart rate", "wristband", "heartbeat", "emotion sensing", "physiological signals" or other heart-rate-linked words (requires heart-rate-monitor to be installed)

Q

questions-are-not-instructions

ntcoding / claude-skillz

Engage with what the user said before taking action. Triggers on: questions ('?'), feedback ('this is wrong', 'that doesn't look right', 'there are issues'), challenges ('why did you', 'have you considered'), criticism ('this isn't working', 'I don't like'), observations ('I notice', 'it seems like'), naming a skill or concept. STOP and respond to the user's actual words before doing anything.

R

recipe-review

shinpr / claude-code-workflows

Reviews completed implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved corrections.