Skills

P

park

wkentaro / agent-skills

Print and copy a one-line reminder and the command for resuming the current coding-agent session

P

peach-setup-ui-proto

peachsolution / peach-harness

Sets up the peach harness system for a Frontend-Only UI Proto project. Tidies CLAUDE.md into a minimal entry point and creates/updates AGENTS.md at roughly 70–90 lines. Use when: "ui proto 하네스 설정", "ui proto AGENTS 정리", "Frontend-Only 하네스 설정", "프로토타입 프로젝트 초기 설정" keywords.

P

plane

nmnmcc / skills

Use when one result crosses technical domains and needs integrated scope and proof.

P

planify

aymericderbois / skills

Run a tight interrogation of the need and the technical breakdown of a feature until you reach a shared plan, then hand the writing to planify-write-plan. Open questions grouped into independent batches, each with a recommended answer. Use when the user wants to plan a feature, break a need into easy-to-review tasks, stress-test a plan before coding, prepare a plan-mode session, or invokes /planify. Usage: /planify [demande]

P

planify-write-plan

aymericderbois / skills

Internal writer of the planify skill: formats the summary of a plan (produced by planify's interrogation) into two files under .task/<KEY>/<prefix>/ — a readable plan.md (tasks + acceptance constraints) and a dense tech.md. Invoked by planify through the Skill tool; does not trigger on its own and has no slash command. Asks no further questions and makes no decisions.

P

planning-validate

drillan / speckit-gates

Validates planning artifacts (spec.md, plan.md, data-model.md, contracts/) for quality, completeness, and consistency. Checks for mandatory sections, cross-artifact consistency, and constitution compliance. Always run after /speckit.plan completes.

P

premortem

boshu2 / agentops

Find how a rollout plan could fail before committing to it. Use when: asked what could go wrong or to poke holes in a plan.

P

probe

ilamanov / skills

Before you implement a complex change, write its main architecture as code stubs and agree on them with the user.

P

project-audit

fearovex-labs / agent-config

Deep diagnostic of Claude/SDD configuration. Read-only. Produces audit-report.md consumed by /project-fix. Trigger: /project-audit, audit project, review claude config, project health check.

R

ralph

civitai / civitai

Autonomous agent for tackling big projects. Create PRDs with user stories, then run them via the CLI. Sessions persist across restarts with pause/resume and real-time monitoring.

R

retro

codewithjv / agent-skills

Run a retrospective on the current task or chat history. Use when the user wants to understand mistakes, dead ends, wasted effort, root causes, and what should change to improve performance next time.

R

review-plan

efoo-team / skills

Only use when the user explicitly invokes /review-plan (or $review-plan in Codex). Never auto-invoke. Rigorously review a pre-implementation or work plan from multiple independent review perspectives (review subagents if a delegation mechanism is available), running at least 3 cycles of review → validity check → adoption decision → proposal to reflect adopted findings in the plan document. Do not directly edit the plan document itself or implement source code; present revision proposals in chat.

R

rhdh-context

redhat-developer / rhdh-skills

Resolves the environment the other RHDH skills start from and hands back one JSON document: which RHDH repositories are checked out and where — rhdh, rhdh-operator, rhdh-plugins, rhdh-plugin-export-overlays, rhdh-plugin-catalog, rhdh-cli, rhdh-chart, rhdh-local, backstage and the rest — which tools are on PATH, and the target RHDH and Backstage versions with the source that produced them. Also owns the `rhdh` CLI behind workspace status, worklogs, and todos. Use for RHDH orientation, "where is my rhdh checkout", "which Backstage version goes with RHDH 1.10", `rhdh status`, `rhdh doctor`, `rhdh config`, `rhdh workspace`, `rhdh log`, `rhdh todo`, and for the read-only context another RHDH skill needs before it starts. Read-only — implementation work belongs to the domain skill that owns the requested outcome.

R

run-retro

frostney / known-good-route

Reviews a workstream and agrees process improvements, applying only the selected follow-up actions. Use when the user asks for, runs /run-retro, or accepts a retrospective.

Set up a repository for the other skills using your chosen tracker, asking where tickets live when that choice is missing. Supports GitHub Issues, Linear, Jira, markdown files under .scratch/, or a tracker you describe in a paragraph. Detects and writes the configuration and a pointer block in CLAUDE.md or AGENTS.md. Run once per repo, and again to refresh configuration or switch trackers. Use when asked to set up mana, set up this repo for the skills, choose the issue tracker, connect Linear or Jira, point the skills at a tracker, or /setup-mana.

S

simple-language

ctxr-dev / simple-language

Use for every message a person will read: chat replies, explanations, plans, analysis, review comments, progress updates, error reports, commit and PR text, and docs for humans. Level 1 is the default and applies every time, with no trigger. Level 2 is the simplest version, with commoner words, sentences of nine words at most, and never more words than before; it fires only when the reader asks for it simpler, says like I'm five, or says again that they do not understand. Also use when the user asks you to write text they will send to another person as their own, like a chat message, ticket, comment, reply, email or question: write it the way a hurried human types. Also use when simplifying must not lose a qualifier, a number, a caveat, a conditional or a case count. Do NOT use for text no person reads: prompts and task specs for other agents or subagents, tool arguments, structured handoffs, machine-parsed output, code, identifiers, config keys, log and error strings.

S

skill-conductor

smixs / skill-conductor

Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skill, fixing a skill that never triggers or fires unreliably, running evals to test a skill, benchmarking skill performance, optimizing a skill's description, reviewing third-party skills for quality, or packaging skills for distribution — even if the user doesn't explicitly say "skill" (e.g. "teach Claude to do X", "make the agent always follow Y"). Not for using skills or general coding tasks.

S

skill-cost-projections

nyldn / claude-octopus

Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns

S

skill-creator

iofficeai / aionui

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

S

skill-evaluator

gotalab / skillport

Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.

S

skill-knowledge-work

nyldn / claude-octopus

Switch to Knowledge Work mode for research and writing — use when task is non-code focused

S

skill-system-workflow

arthur0824hao / skills

Pure planning engine. Converts goals into DAGs with Mermaid visualization. Ticket lifecycle has moved to skill-system-tkt.

S

skill-updater

oimiragieo / agent-studio

Research-backed skill refresh workflow for updating existing skills with TDD checkpoints, memory-aware integration, and EVOLVE/reflection trigger handling.

S

speckit-check

full-stack-skills / speckit-skills

Run `specify check` to verify that Spec Kit required tools (git, claude, gemini, code, cursor-agent, windsurf, qwen, opencode, codex, shai, qoder, etc.) are installed and available; interpret results and suggest next steps. Use when the user says "check Spec Kit environment", "specify not working", or "slash commands not showing".

S

stitch-setup

gabelul / stitch-kit

Step-by-step installer for the stitch-kit plugin and Stitch MCP server. Use this when setting up the plugin for the first time, diagnosing connection issues, or helping a new user get Stitch running in Claude Code or Codex CLI.

S

Subagent-Driven Literature Review

kthorn / research-superpower

Use parallel subagents for large-scale paper screening and deep dive analysis

S

subagents

dobroslavradosavljevic / skills

Orchestrator/subagent coordination workflow for tasks that can be split into clear disjoint work. Use when the user invokes $subagents, says "use subagents", "spawn agents", "parallelize this", "delegate this", "split this across agents", or asks for coordinated multi-agent work. Prefer subagents for harder tasks, broad research, multi-file changes, independent reviews, or separable implementation lanes. Skip subagents when the task is simple, the harness does not support them, or safe disjoint work cannot be identified.

S

superskills-upgrade

ariadoss / superskills

Upgrade superskills to the latest version. Pulls from GitHub, re-runs setup, and shows the version change. Use when asked to "upgrade superskills", "update superskills", or "get the latest version of superskills".

S

svelte-ai

full-stack-skills / svelte-skills

Svelte AI assistant integration skill. Use when the user configures the Svelte MCP server for AI coding tools such as Claude Code/Cursor/Copilot/Codex/OpenCode/VS Code, installs the svelte-autofixer/list-sections/get-documentation MCP tools, uses the svelte-task prompt, calls the sv CLI (svelte-ai CLI), or writes Svelte 5 code with the svelte-code-writer/svelte-core-bestpractices sub-agents.

Use when running /ltk:sync-submodules, updating submodules, or needing to \"sync\", \"merge\", \"adapt\", \"learn from\" other Claude Code plugins or repos

T

team-planex

catlog22 / claude-code-workflow

Unified team skill for plan-and-execute pipeline. Pure router — coordinator always. Beat model is coordinator-only in monitor.md. Triggers on "team planex".

T

teams-anthropic-integration

youdotcom-oss / agent-skills

Add Anthropic Claude models (Opus, Sonnet, Haiku) to Microsoft Teams.ai applications using @youdotcom-oss/teams-anthropic. Optionally integrate You.com MCP server for web search and content extraction. - MANDATORY TRIGGERS: teams-anthropic, @youdotcom-oss/teams-anthropic, Microsoft Teams.ai, Teams AI, Anthropic Claude, Teams MCP, Teams bot - Use when: building Microsoft Teams bots with Claude, integrating Anthropic with Teams.ai, adding MCP tools to Teams applications

Use when designing agent tools, creating tool descriptions, implementing MCP tools, or asking about \"tool design\", \"agent tools\", \"tool descriptions\", \"MCP\", \"function calling\", \"tool consolidation\"

T

tuistory

remorses / tuistory

tmux for AI agents. Run dev servers and TUIs in named background sessions that agents can read, wait on, snapshot, and type into. Replaces tmux with reactive waiting instead of blind `sleep`. Projects wrap their dev script with tuistory (`"dev": "tuistory -- next dev"`) so agents get a background session and humans get auto-attached. Use tuistory when you need to: - Run background dev servers or long-lived processes - Control interactive CLIs and TUIs (type, press keys, click, wait, snapshot) - Write Playwright-style tests for terminal apps **CLI** (`tuistory`) for background sessions. **JS/TS API** (`launchTerminal`) for programmatic control and tests.

U

unity-to-tasks

icarealot / dotfiles

Break a plan, spec, or the current conversation into a set of tracer-bullet tasks, each declaring its blocking edges.

U

using-aegis

ganyuanran / aegis

Use when starting a turn or checking Aegis skill routing.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

V

vibeguard

majiayu000 / spellbook

Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates.

W

web-auth

agent-sh / agentsys

Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs for agent access.

W

wjs-voicedrop

jianshuo / claude-skills

Entry point for VoiceDrop. All capabilities live in the MCP (voicedrop.cn/mcp, 44 tools: article reading/writing and versions, writing style and distillation, mining and rewriting, community and tipping, compute, sharing/WeChat official accounts/Xiaohongshu, bookshelf reading and book writing/revision). This skill does one thing — connect you to that MCP: use its login tool to do 6+4 phone pairing login and get a token, then wire it into your client. Trigger words: "voicedrop", "登录 voicedrop", "voicedrop 登录", "接 voicedrop mcp", "voicedrop token", "/wjs-voicedrop".

Use when you have a spec or requirements for a multi-step task, before touching code

W

writing-plans

shipshitdev / skills

Resolves implementation decisions into an exact, current execution plan on the same issue. Use before handing coding to an executor that must escalate missing decisions.

A

aep-map

memorysaver / agentic-engineering-patterns

Decomposes a product into a system map, layered story graph, and agent topology. Use after /aep-envision, or for "break this down" and "plan the stories".

A

ag2-network-governance

ag2ai / ag2-skills

Govern an AG2 multi-agent network — identity (`Passport`, `Resume`), per-agent `Rule` with two top-level blocks `access` (`AccessBlock`) and `limits` (`LimitsBlock`, which nests `RateBlock` + `InboxBlock`), the swappable `HubArbiter` / `RuleBasedArbiter` access-&-routing seam, `AuthAdapter` / `AuthRegistry` registration, channel-level `Expectation`s with `audit` / `notify_channel` / `auto_close` violation handlers, the hub's append-only audit log and `AUDIT_KIND_*` constants, live `HubListener` / `BaseHubListener` observability plus `Hub` `on_*` hooks and `register_sweeper`, and task observation via `agent.task(...)` + `TaskMirror` (updates `Resume.observed` for peer ranking). Use when the user needs rate limits, access policy, SLAs, compliance trails, live metrics/alerting, capability-driven peer ranking, or to inspect what actually happened on the network. Load this after `ag2-network-quickstart`. For the agent-side surface (custom handlers, views, LLM tools, `HumanClient`) see `ag2-network-tools-and-views`.

A

ag2-network-quickstart

ag2ai / ag2-skills

Build a multi-agent AG2 network — load this whenever two or more `Agent`s need to interact. The network is the standard multi-agent pattern in `ag2`. Covers `Hub.open`, `LocalLink`, `HubClient.register`, `Passport`, `Resume`, channel lifecycle (PENDING → ACTIVE → CLOSING → CLOSED), the two 2-party channel adapters (`consulting` for strict 1Q1R and `conversation` for free-form), the `Envelope` wire format, audience routing, `wait_for_channel_event`, WAL replay via `hub.read_wal`, and the five channel-close routes. Entry point — routes to `ag2-network-discussion` (N-party round-robin), `ag2-network-workflow` (declarative orchestration / GroupChat migration), `ag2-network-governance` (rules / expectations / audit), or `ag2-network-tools-and-views` (custom handlers / peer discovery) for deeper needs.

A

ag2-network-tools-and-views

ag2ai / ag2-skills

Shape what an AG2 network agent perceives and which actions its LLM can take. Covers the five auto-injected LLM-facing tools that ship via `NetworkPlugin` (`delegate`, `peers`, `channels`, `tasks`, `context`) plus the adapter-owned `say`; replacing the default handler with `agent_client.on_envelope(callback)` (gateways, headless workers); the `ViewPolicy` Protocol with the built-in `FullTranscript`, `WindowedSummary(recent_n=N)`, and `NamedWindowedSummary(recent_n=N)` views plus how to write a custom view; peer discovery via skill markdown (`skill_md=`, `parse_skill_frontmatter`, `hub.set_skill`); the `Envelope` wire format with the `EV_*` event taxonomy (`EV_TEXT`, `EV_PACKET`, `EV_CHANNEL_*`, `EV_EXPECTATION_VIOLATED`, `EV_TASK_CANCEL_REQUEST`, `EV_TASK_CANCELLED`), `audience` and `visible_to` semantics, `Priority`, `causation_id`, and how to send raw envelopes with custom event types via `agent_client.send_envelope(...)`. Use when the user wants to customise the LLM's network surface, write a custom envelope handler, build a gateway / headless worker, or wire peer discovery.

A

ag2-network-workflow

ag2ai / ag2-skills

Build an AG2 network `workflow` channel — the orchestrated N-party adapter driven by a declarative `TransitionGraph`. Use when the user needs conditional handoffs, multi-step pipelines, context-aware routing, feedback loops, or is migrating from the classic `GroupChat` + `Agent.handoffs` pattern. Covers `TransitionGraph`; factories `TransitionGraph.sequence(...)` / `.round_robin(...)`; built-in targets (`AgentTarget`, `RoundRobinTarget`, `StayTarget`, `RevertToInitiatorTarget`, `TerminateTarget`); built-in conditions (`Always`, `FromSpeaker`, `ToolCalled`, `ContextEquals`); the typed `Handoff` return for dynamic routing; channel-scoped context via `set_context`; `register_target` / `register_condition` for custom subclasses; the packet execution model and idempotent-tool requirement; eight cookbook patterns (pipeline, hierarchical, escalation, feedback loop, triage, and more); and side-by-side migration from classic `GroupChat`. Load this after `ag2-network-quickstart`.

A

agent-arena

zhjai / agent-arena

Use Arena for heterogeneous independent design and cross-review, second opinions, code/bug/plan reviews, and evidence-based analysis. Cues: 用 arena, 讨论一下, 审核一下, 交叉审核, 第二意见, 完全体 arena, 伴随子代理, 边做边检查, companion review. Discussions start with independent proposals; a named draft/diff is reviewed directly. Bare 继续 resumes an unfinished Arena checkpoint. Supports supervised execution and persistent concurrent companion checks. Not for trivial lookups or formatting; an enabled companion still accompanies ordinary work.

A

agent-browser-automate

owenleezy / agent-browser-skill

[INTERNAL TEMPLATE] Task automation execution protocol. Called by agent-browser orchestrator.

OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.

A

agent-browser

onsager-ai / dev-skills

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.

A

agent-harness

wangdahoo / agent-harness

Framework for long-running AI agents across multiple context windows. USE WHEN user types /agent-harness or mentions sprint planning, feature breakdown, multi-session projects. Subcommands: init, sprint, code, 996, status, archive, force-archive.

A

agent-review

civitai / civitai

Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.

A

agently-dynamic-task

agentera / agently-skills

Use when the user needs Agently TaskDAG / Dynamic Task, model-generated or app-submitted DAG planning, TaskDAG validation, TaskDAGResolver handlers, TaskDAGExecutor execution, or the Agently.create_dynamic_task compatibility facade. TaskDAG is the DAG foundation capability; Dynamic Task is the convenience facade over it and uses TriggerFlow as the execution substrate.

A

ai-sdk

midudev / autoskills

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

A

ai-switching-models

lebsral / dspy-programming-not-prompting-lms-skills

Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a cheaper model, stop depending on one vendor, compare models side-by-side, a model update broke your outputs, you need vendor diversification, or you want to migrate to a local model. Also use when your prompt broke after a model update, prompts that work for GPT-4 do not work for Claude or Llama, or you need to do a model migration. Covers DSPy model portability with provider config, re-optimization, model comparison, and multi-model pipelines. Also used for migrate from OpenAI to Anthropic, GPT to Claude migration, try Llama instead of GPT, model comparison framework, multi-provider AI setup, avoid vendor lock-in for AI, prompts break when switching models, model-agnostic AI code.

A

aliyun-qwen-coder

cinience / alicloud-skills

Use when code generation, repository understanding, or coding-agent tasks need Alibaba Cloud Model Studio Qwen Coder models (`qwen3-coder-next`, `qwen3-coder-plus` and related coder variants).

A

aliyun-qwen-deep-research

cinience / alicloud-skills

Use when a task needs Alibaba Cloud Model Studio Qwen Deep Research models to plan multi-step investigation, run iterative web research, and produce structured reports with citations or evidence summaries.

A

aliyun-qwen-generation

cinience / alicloud-skills

Use when generating or reasoning over text with Alibaba Cloud Model Studio Qwen flagship text models (`qwen3-max`, `qwen3.5-plus`, `qwen3.5-flash`, snapshots, and compatible open-source variants). Use when building chat, agent, tool-calling, or long-context text generation workflows on Model Studio.

A

assistant

iskron-ai / skills

A human's secretary: summarizes tasks; records their words and assignments verbatim in the tasks. Triggers: “what are my tasks,” “what's waiting for me,” “how are things,” “what's left,” “any questions?,” “what's up with this task,” “what about #N,” “who's doing what,” “what's urgent,” “what's new,” “where are we,” “did you say …?,” “pass on …,” “what is …?,” “assign a task to an agent,” “delegate to an agent,” “tell the agent to do,” “what's in progress,” “what did I assign,” “what tasks are outstanding,” “clean up abandoned tasks,” “assistant.” Requires iskron_*.