Skills

A

ask-nova

ohyeh / agent-scripts

Interview-driven flow picker. Use when the user is unsure which skill/flow/pipeline fits—new project kickoff, cross-domain work, or a fuzzy situation. Reads the three routers live and recommends ONE flow. Not for tasks whose owner is already obvious.

A

atomic-tasks

thebeardedbearsas / claude-craft

Pattern GSD (Get Shit Done) - découper en tâches atomiques avec contextes subagent frais pour combattre le context rot. Use when planning complex work or working past 50% context usage.

A

audit-choices

dzhng / skills

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might be a point fix.

A

automatic-stateful-prompt-improver

curiositech / some_claude_skills

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate

B

BMad Master

aj-geddes / claude-code-bmad-skills

Core BMAD Method orchestrator and workflow manager

C

cco-clean

egorfedorov / claude-context-optimizer

Clean up old tracking data and reset statistics

C

create-plans

glittercowboy / taches-cc-resources

Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.

Use when you (an agent in a sesh thread) need to handle assigned work tickets — find your tickets, read a ticket's prompt/instructions, or update its status (e.g. mark it done). Covers the `sesh ticket` find → read → report loop.

E

expert-panel

ericosiu / ai-marketing-skills

Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".

I

inbox

aibtcdev / skills

x402-gated agent inbox — send paid messages to any agent's inbox, read received messages, and check inbox status. Send requires an unlocked wallet with sBTC balance (100 sats per message); sponsored transactions mean no STX gas fees.

P

pomasa

extremeprogramming-cn / pomasa

Generate declarative multi-agent systems (MAS) using POMASA pattern language. Use when building agent pipelines, orchestrating multiple AI agents, or creating research automation workflows. Supports patterns like Prompt-Defined Agent, Orchestrated Pipeline, Filesystem Data Bus, and Verifiable Data Lineage

R

rag-pipeline

brightdata / skills

Build a RAG (retrieval-augmented generation) pipeline or a custom search engine on top of Bright Data's Discover API, using intent-ranked web results and parsed page content as the retrieval/ingestion layer for an LLM or vector store. Use when the user wants to “build a RAG pipeline,” “add web search to my LLM/agent,” “ground my model in live web data,” “build a search engine over the web,” “ingest web content into a vector DB / knowledge base,” or “give my chatbot retrieval.” Covers both live retrieval (Discover at query time as a web-grounded retriever) and ingestion (Discover → chunk → embed → vector store → retrieve). Built on the `discover-api` skill. For a one-off written report use `live-research`; for raw markdown of specific known URLs use `scrape`.

S

skill-coach

curiositech / some_claude_skills

Guides the creation of high-quality Agent Skills with domain expertise, anti-pattern detection, and progressive disclosure best practices. Activate on keywords: create skill, review skill, skill

S

socratic-brainstorm

thebeardedbearsas / claude-craft

Socratic brainstorming before coding: clarify the problem with targeted questions rather than jumping to a solution. Use when requirements are ambiguous or before starting a non-trivial feature.

T

trace-grader

rheinmir / setup

Score the PATH an agent took (tool choice, ordering, retries, repeatability, grounding) — not just its final answer — to catch "corrupt success" (right answer via a bad/unsafe path) and flakiness. Deterministic trace schema + pass^k repeatability + config-driven rule checks (forbidden tool, out-of-order, retry-storm, excessive steps, edited-without-read grounding). Parses canonical traces.json, hooklib.audit / code-logger events.jsonl, OR a full Claude Code session transcript (--transcript, richest source: recovers retrieval args + observation + per- step ok). Trigger when the user says "grade the trajectory", "score the path not the answer", "did it cheat / take a bad path", "did it look before it acted / grounding", "corrupt success", "is this flaky / does it repeat", "pass^k", "grade a session transcript", "trace grader", or invokes /trace-grader.

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

8

801-regulations-eu-ai-act

jabrena / plinth

Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance for an AI agent with enterprise tools; Add human oversight and auditability to LLM workflows; Assess RAG or model-driven decision support before production release. Part of Plinth Toolkit

A

ai-engineer

curiositech / some_claude_skills

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use proactively

A

autoplan

prathamdby / skills

autoplan to produce a grounded implementation plan without questions; gated design uses upfront-design.

B

behavioral-modes

vudovn / ag-kit

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

B

book-to-skill

huntsyea / thinking-skills

Converts .txt book files into leverageable Claude Code skills. Use when transforming books, articles, or written expertise into structured skills with frameworks, workflows, and reference material.

B

bro-think-with-me

irpsv / ai-bro

Помогает совместно прояснить задачу, проверить идею, найти корневую причину проблемы или выбрать подход без реализации. Используй, когда пользователь просит обсудить задачу, разобраться в проблеме, сравнить варианты или задаёт вопросы «что думаешь?» и «как лучше сделать?». Не используй, когда пользователь явно просит составить план, реализовать задачу, проверить изменения кода или сохранить знания проекта.

D

deep-interview

yeachan-heo / oh-my-codex

Socratic deep interview with mathematical ambiguity gating before execution

E

ecosystem-tools

thebeardedbearsas / claude-craft

Third-party Claude Code token/context/code-review tools. Use when choosing or recommending an external tool to reduce token usage, manage context, or review large codebases (caveman, code-review-graph, token-savior, context-mode...).

F

find-skills

nkchivas / openclaw-skill-find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Load this skill when you are required to check source code outside of this codebase, or users give you a GitHub repo spec follows <owner-name>/<repo-name> spec. Use it when the current directory is not the target project, when another local project is needed, or when multiple projects are involved.

G

godot-agent-vision

thedivergentai / game-design-agentic-skills

Agentic eyes for Godot work: cross-platform screenshot CLI (asset/region/window/screen) to budgeted WebP, TEMP editor viewport bridge under .gdskills/, and Taste Receptor Atlas v2 (~237 micro-receptors × 0–2: hierarchy, contrast, typography×41, affordance, space, color, icon, composition, light/FX, motion-tells, anti-slop, originality, identity). Use when agents must see UI, assets, or the editor — not for in-game screenshot Autoloads. Keywords: agent vision, screenshot, WebP, visual QA, taste receptors, typography, UI review, asset sheet, editor viewport, anti-slop

Shared execution rules for hhzz-cli: handles configuration, authentication, command discovery, permissions, write confirmation, result verification, unified business results, and error handling. Must be read before using any Heihu Zhizao business Skill. Does not replace specific business Skills or the CLI contract.

S

setup-pstack

mdsmithaustin / pstack

Check installed pstack personas, optionally register native agents, configure which models pstack uses per role and at what reasoning budget, and set up a repository PR template. Use for /setup-pstack, "configure pstack models", "pstack budget", "set up pstack PR templates", or changing pstack's model choices.

S

skill-development

aiskillstore / marketplace

Use this skill when the user wants to “create a skill,” “add a skill to a plugin,” “write a new skill,” “improve a skill description,” or “organize skill content,” or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

U

user-profile-keeper

dongshuyan / compass-skills

Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses. Use only when the user explicitly invokes $user-profile-keeper to create, initialize, update, query, correct, delete, export, or audit a local persistent user profile. It can extract durable collaboration preferences, requirement-expression habits, capability boundaries, recurring omissions, risk preferences, privacy boundaries, and typical events from the current session into auditable, confirmable, retractable local profile data. Do not auto-invoke, upload profile data, or replace task-clarifier's normal clarification flow

V

vibe-to-agentic-framework

shanraisshan / claude-code-best-practice

The conceptual framework behind the presentation — what "Vibe Coding to Agentic Engineering" means, why the journey is structured the way it is, and how every slide fits the narrative arc

W

write-report

fellowship-dev / dogfooded-skills

Use when writing a mission report to the gateway DB from any operator mission

W

writing-skills

posthog / posthog

Guide for writing PostHog agent skills — job-to-be-done templates that teach agents how to use MCP tools to achieve a goal. Use when adding new product functionality that agents should know how to work with, creating a new skill, or updating existing skills in products/*/skills/ or .agents/skills/.

A

al

paleo / alignfirst

Execute the AlignFirst AAD protocol

A

alicloud-platform-openclaw-setup

cinience / alicloud-skills

Install and configure OpenClaw with DingTalk, Feishu, Discord, and additional channels with Bailian/DashScope models on Linux hosts. Use when provisioning a new OpenClaw node, troubleshooting gateway/channel startup, standardizing openclaw.json mapping, or automatically discovering extra channels from https://docs.openclaw.ai/channels.

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

browser-use

steipete / agent-scripts

Control the user's existing signed-in Chrome: callable Codex Chrome plugin first, then OpenClaw extension-backed mcporter, with direct DevTools attachment only as a last fallback.

C

cco-digest

egorfedorov / claude-context-optimizer

Show weekly/daily efficiency digest with score and trends

C

ce:work-beta

everyinc / compound-engineering-plugin

[BETA] Execute work with external delegate support. Same as ce:work but includes experimental Codex delegation mode for token-conserving code implementation

C

codeck

hiyeshu / codeck

codeck entry point. Scans local files for materials, shows pipeline dashboard with diagnostic intelligence, guides user to the next step. Use when the user says "codeck", "new deck", "make a presentation", "make a deck", "new slides", "build a presentation", "export", "speech", "script", or wants to start or continue a presentation project. /codeck is the user-facing entry; legacy sub-skills are internal modules.

C

composio-mcp

lunchpaillola / pipa-skills

Use the Composio MCP with Pipa to discover and operate external app tools safely.

C

context-engineering

siviter-xyz / dot-agent

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques, compression strategies, memory architectures, multi-agent patterns, evaluation, tool design, and project development.

D

daily-report

fellowship-dev / dogfooded-skills

Use when writing the daily/rollcall team report — defines 5 sections, quality rules, and a minimal idle card

E

eli5

nathanksou / eli5

Explain Like I'm 5 mode. Simplifies explanations with a patient, friendly parent voice while still compressing output tokens. Three levels: easy (full analogies, beginner), chill (plain language, default), quick (minimal, advanced). Use when user says "eli5", "explain like I'm 5", "simple mode", or invokes /eli5. Also triggers on explicit requests like "explain simply" or "make it simpler".

M

mcp-builder

aiskillstore / marketplace

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).

P

pipa-manage

lunchpaillola / pipa-skills

Use when the user wants to manage Pipa configuration across profile setup, connectors, company brain or memory, permissions, automations, triggers, loops, or access audits. Route profile setup to pipa-setup and connector setup/status to pipa-connectors. Do not use for business work or an action in an already-connected app.

P

publish

harbor-framework / harbor

Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.

V

vercel-ai-sdk

op0ai / claude-skills

Guide for Vercel AI SDK v6 implementation patterns including generateText, streamText, ToolLoopAgent, structured output with Output helpers, useChat hook, tool calling, embeddings, middleware, and MCP integration. Use when implementing AI chat interfaces, streaming responses, agentic applications, tool/function calling, text embeddings, workflow patterns, or working with convertToModelMessages and toUIMessageStreamResponse. Activates for AI SDK integration, useChat hook usage, message streaming, agent development, or tool calling tasks.

W

windows-path-troubleshooting

josiahsiegel / claude-plugin-marketplace

Complete Windows file path troubleshooting knowledge for Claude Code on Git Bash and Windows environments. PROACTIVELY activate for: (1) file path errors on Windows, (2) backslash vs forward slash issues, (3) Edit/Write/Read tool failures, (4) MINGW path resolution, (5) cross-platform path conversion, (6) MSYS_NO_PATHCONV usage, (7) double-slash escape patterns (//c/foo), (8) UNC and long path limits, (9) WSL vs native Windows interop. Provides: path-conversion rules, troubleshooting flowchart, MSYS env-var recipes, double-slash escape patterns, and Windows file-operation best practices.

A

agent-tracing

lobehub / lobehub

Use for agent traces by operation ID (pull production tracing): failed tools, arguments/results, available tools, execution location, LLM calls and context

C

cco-git

egorfedorov / claude-context-optimizer

Show git-aware context suggestions for current working directory

E

expectations

citypaul / .dotfiles

Decide where a learning, gotcha, or decision should live so it is not lost, and capture it there while context is fresh. Use when the user says they just discovered, learned, or found out something non-obvious, asks where a fact should be recorded, written down, or go, wants a setup gotcha, workaround, or decision kept for the next person or the next agent session, or asks whether something belongs in CLAUDE.md, a README, an ADR, tests, a glossary, or a reusable skill. Routes each fact to its durable owner and decides whether it is reusable or project-local. For the prose of the document itself see technical-writing; for recording a domain term see ubiquitous-language.

G

gsd-quick-batch

open-gsd / gsd-core

Batch several `/gsd-quick`-shaped tasks together — planned, dispatched, and merged as one run

M

mindos

geminilight / mindos

MindOS: local knowledge assistant and shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, and preferences across sessions and agents. Core features: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, and distill lessons. NOT for app source or paths outside KB. Triggers: save/record, search notes, update files, organize, run workflow, capture decisions, append CSV, hand off context, check past discussions, distill lessons. Proactive: (1) search first for stored context, (2) offer to save after valuable work, (3) suggest persisting key decisions.

P

pipefy-skill-template

pipefy / ai-toolkit

Copy this file when authoring a new Pipefy skill. Replace placeholders, then rename the folder so it matches the frontmatter name.

S

skill-architect

curiositech / some_claude_skills

Design, create, audit, and improve Claude Agent Skills with expert-level progressive disclosure. Use when building new skills, reviewing existing skills, debugging activation failures, encoding

S

solo-founder-gtm

chadboyda / agent-gtm-skills

Use when a solo founder is building their GTM motion, wants to scale without hiring, or needs to design an AI agent team for go-to-market. Also use when the user mentions “solo founder,” “one-person startup,” “solopreneur,” “bootstrapped,” “no team,” “AI agents as team,” “scaling without hiring,” “founder-led sales,” “lean GTM,” “one-person company,” or “no employees.” This skill covers the complete solo founder GTM playbook, from stack selection through agent team design, revenue-stage transitions, time allocation, and when to finally hire.

U

using-godot-prompter

jame581 / godotprompter

Bootstrap skill — establishes how to find and use GodotPrompter skills, with platform-specific tool mapping

W

wrap-up

rohitg00 / pro-workflow

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.