Skills

B

boring-mode

hachej / boring-stack

The worker's router in a repository run by the Boring Factory. Use at the start of every task from a work packet (a task issue, its acceptance lines and their proof): it picks the playbook, the principles and the proof the pull request must carry. Adapted from pstack's poteto-mode.

B

browser-automation

galiprandi / skills

Control a dedicated browser via agent-browser (Vercel). Use when automating web apps, scraping authenticated sites, filling forms, or navigating SPAs. Do NOT use for desktop apps or API-only integrations.

B

browserforce

ivalsaraj / browserforce

Drive the user's real Chrome — their tabs, logins, cookies, extensions. Use for any browser, web page, or web app task. Open a website, click a button, fill out a form, take a screenshot, scrape a page, log into a site, test this web app, or check what a page actually renders. Other tools launch a fresh Chromium with none of the user's sessions. Prefer BrowserForce over any other browser, headless, or web-fetch tool.

B

browserman

browserman-run / skills

Use BrowserMan when an agent needs the user's real browser environment, optimized official scripts, or Agent-authored/community scripts running through BrowserMan's standard context.

B

browserwing-admin

memtensor / memos

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

B

building-agent-team-prompts

frontboat / agent-teams

Provides a prompt template and best practices for building Claude Code agent teams. Covers team composition, teammate spawn prompts, task breakdown, file ownership, communication protocols, and delegate mode. Use when creating an agent team, spawning teammates, parallelizing work across multiple Claude Code instances, or deciding whether an agent team is the right approach.

B

but-for-real

shpigford / skills

Force a skeptical second pass on your own work. Because 'it should work' has never once been true.

C

cargo-skills

getcargohq / cargo-skills

Master skill index for the Cargo CLI. Use this file to understand which skill to load, how the skills relate to each other, and how to chain them together to accomplish end-to-end revenue automation tasks on the Cargo platform.

C

changelog-review

laurigates / claude-plugins

Claude Code changelog analysis for plugin impact. Use when checking new features, breaking changes, or upgrade opportunities from a Claude Code release.

C

claude-blog-sources

laurigates / claude-plugins

Fetch Claude Blog and official Claude Code docs. Use when researching Claude Code capabilities, CLAUDE.md optimization, memory hierarchy, or @import patterns.

C

clawroom

heyzgj / clawroom

Coordinates the owner's AI agent with another person's AI agent in a bounded room and closes with a clear, structured agreement each owner can read. Use when the owner asks to sync, align, reconcile, pre-align, or coordinate with someone else's agent; to let the two agents "talk first" and brief their humans before (or instead of) a meeting; when a ClawRoom invite URL arrives; when the owner forwards a pasted instruction block mentioning ClawRoom; or when an agent-to-agent task needs owner approval mid-conversation.

C

cm

dicklesworthstone / agent_flywheel_clawdbot_skills_and_integrations

CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.

C

codex-gemini

mathruffian-dot / codex-lazy-packs

Configure the Gemini free API in Codex. Load when the user says "configure Gemini API".

C

coding-agent

cowork-os / cowork-os

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

C

cold-read

iliyasone / skills

Write agent-facing files (SKILL.md, AGENTS.md, CLAUDE.md, READMEs, runbooks) so they survive a first-time reader with no shared history. Use when creating or editing any such file, or reviewing one for noise.

C

collaborative-plan-with-file

catlog22 / claude-code-workflow

Serial collaborative planning with Plan Note - Multi-domain serial task generation, unified plan-note.md, conflict detection. No agent delegation.

C

confess

b-open-io / prompts

Proactive self-audit covering incomplete changes, untested assumptions, pattern violations, buried concerns, and cleanup debt. Invoke before ending a session, marking a task done, or saying "complete", and when the user asks "are you sure?", "did you miss anything?", "anything else?", or "audit your work". Do not wait to be asked.

C

configure-repo

jayden-dang / skills

Sets up docs/agents config so this skill set can run in an existing repo.

Turn a finished plan, spec, or decision map into a build effort with ready-for-agent tickets, or resume its filing and check progress. Use when asked to file the build tickets, break this spec into issues, turn the plan into tickets, slice the work, resume filing build tickets, check progress and close out a build effort, or /conjure.

C

context-audit

garrytan / gbrain

Token-hygiene audit of the always-loaded context stack — CLAUDE.md, AGENTS.md, auto-memory MEMORY.md, and the bootstrap-rendered identity files (SOUL.md, USER.md, ACCESS_POLICY.md, HEARTBEAT.md) or their harness equivalents. Finds redundancy, contradictions, stale content, compression candidates, and skill-extraction candidates; produces a ranked action list sorted by token savings with a risk class per finding. REPORT-ONLY: this skill never edits any audited file. Recommendations for bootstrap-rendered files target the interview answer bank / templates, never the rendered output. Judging routes through `gbrain eval cross-modal` (single cheap model by default; full multi-model panel is explicit opt-in).

C

context-engineering

composio-community / opencode-skills

Workflow for managing, structuring, compressing, and orchestrating context effectively for Claude and AI agent systems to improve reasoning quality, execution consistency, and long-term workflow scalability.

C

context-pack

wojons / skills

Pack codebases, folders, or ZIP archives into LLM-friendly context format with smart filtering, file selection, and markdown structure

C

cowork-setup

indranilbanerjee / digital-marketing-pro

Set up DMP for team use in Cowork: sandbox check, Drive folders, saved routing. “set up DMP for my team in Cowork”

C

create-boss

vogtsw / boss-skills

Distill a real boss into an AI skill, or generate a boss skill from a famous entrepreneur archetype such as Elon Musk, Steve Jobs, Jeff Bezos, or Jensen Huang, or build a persona from free public sources (papers, GitHub, Wikipedia) for a mentor or PI. Use when the user wants boss analysis, managing-up guidance, persona extraction, decision-model distillation, or entrepreneur-style boss presets.

C

create-skill

tailcallhq / forgecode

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 your capabilities with specialized knowledge, workflows, or tool integrations.

C

creative-problem-solver

tkersey / dotfiles

Generate a compact five-tier strategy portfolio when the next task is choosing among materially different paths. Implicitly invoke for explicit requests for options, alternatives, trade-offs, reframing, or help escaping repeated failure. A name-only or meta mention does not authorize the portfolio route. Do not activate for direct implementation, single-answer advice, skill analysis/tuning, repository-evidence opportunity mining, or detailed planning ($plan).

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file. Covers crit comment, crit share, crit unpublish, crit pull, crit push, review file format, and resolution workflow. Not for invoking an interactive review loop — that's the `/crit` command.

C

cron

agentscope-ai / qwenpaw

Use this skill only for scheduled or recurring tasks. Manage jobs with qwenpaw cron list/create/get/state/update/pause/resume/delete/run, and always pass --agent-id explicitly.

Reference skill for building production-ready crw integrations. Covers verb selection, call surfaces (CLI/MCP/REST), post-filtering strategies, context-window hygiene, Hybrid RAG patterns, common pitfalls, and crw-specific operational considerations (search backend limits, renderer pool, proxy rotation). Load this when writing application code that embeds crw, designing a multi-step agent workflow, or debugging an integration that isn't behaving as expected.

C

curate-skills

nesnilnehc / ai-cortex

Govern skill inventory through output-contract and acceptance-criteria checks, lifecycle assignment, and overlap detection. Core goal — produce verifiable status and normalized documentation for all skills in repository.

D

davinci-resolve-computer-use-training

chaiwithjai / davinci-resolve-claude-skills

Use when the user wants Codex to learn DaVinci Resolve through Blackmagic Design lesson homework, operate the Resolve UI with Computer Use, validate skills against real Resolve behavior, or build a capstone workflow that turns local/T7 media into Instagram and YouTube cuts.

D

design-prompt-generator-v2

bear2u / my-skills

Advanced 7-step hierarchical design prompt generator for AI web development tools (Lovable, Cursor, Bolt). Generates domain-aware, user-journey-based design prompts with emotional design considerations. Triggers on "디자인 프롬프트", "웹 디자인", "Lovable 프롬프트", "랜딩페이지 만들어줘", or any AI web builder prompt requests.

D

deskctl

harivansh-afk / deskctl

Non-interactive X11 desktop control for AI agents. Use when the task involves controlling a Linux desktop - clicking, typing, reading windows, waiting for UI state, or taking screenshots inside a sandbox or VM.

D

develop-pyrevit-extensions

oriashkenazi / ai-pyrevit-developer-template

Build, plan, review, and document pyRevit extensions. Use when Codex needs the pyRevit development workflow, templates, prompts, checklists, or scripts for creating or updating pyRevit commands in this repo. Pair with a version-specific Revit skill (e.g., 2023/2024/2025) for API constraints.

D

distill-response

sjunepark / agent-scripts

Distill a prior AI response into a standalone, navigable explanation, or elaborate an item from an earlier distillation.

Create or update AGENTS.md after code generation or an overall task is complete. Use this skill when you have finished writing code (adding components, changing logic, refactoring files), or when the user mentions "update docs", "update AGENTS", or "create AGENTS". Even if the user does not explicitly mention AGENTS.md, whenever you have just modified a code file you should check whether the documentation needs to be updated to match.

Sync Feishu (Lark) contacts into USER.md so the agent can identify DM senders by name. Use when setting up Feishu identity recognition, updating contacts after HR changes, or configuring multi-user agent access. Feishu DMs only include open_id (no sender name), so this skill embeds an open_id→name lookup table directly in USER.md for zero-tool-call identification.

F

first-principles-review

ganyuanran / aegis

Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.

F

fix-decision-router

majesticlabs-dev / majestic-marketplace

Post-documentation decision menu for fix-reporter. Routes to critical patterns, skill updates, cross-references, or discovery enablement.

F

fleet

rysweet / amplihack

Fleet orchestration for distributed coding agents across Azure VMs. Invoked as `/fleet <command>`. Covers all fleet operations: status, scout, advance, adopt, watch, snapshot, dry-run, start, add-task, queue, auth, dashboard, tui, and more. Use when: user mentions fleet, agents, VMs, sessions, or asks "what are my agents doing".

F

fstack-build

flaviocopes / fstack

Execute an approved PLAN.md one step at a time. Use when the plan is approved and the user says to build.

F

fstack-learn

flaviocopes / fstack

Capture one lesson from recent work into LEARNED.md. Use after shipping, when something surprising happened, or when a non-obvious fix would save future time.

G

game-studio-harness

akillness / jeo-skills

Five-role game production studio harness: director, numeric-balance designer, revenue-band PM, verification-strict programmer, archetype-rotation QA. Runs the 3-stage operating cycle (concept/presentation/core build → balance/core-loop/novelty → ops stability/play impact) behind 8 numeric quality gates with survey-grounded trends, signed designer↔PM negotiation records, and QA broadcast discipline. Writes the repository rule file (CLAUDE.md/AGENTS.md) so the contract outlives the session, and keeps one live `_workspace/current/` beside a read-only archive.

G

goal

gabriel-lafrance / skills

Stateless Cursor goal loop: grill, plan, implement, gather acceptance evidence, and review one verifiable outcome using in-chat execution context. Use when the user wants a feature or outcome built end to end. Nested under /just-do-it when that parent owns shipping.

G

grill-me

sammcj / agentic-coding

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

G

grill-with-docs

mxyhi / ok-skills

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

G

grilling

taecontrol / skills

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

H

handoff

csark0812 / toolbox

Agent-to-agent cross-session transfer — pointers not bodies. Channel prompt (user /handoff) or artifact (model-invoked subagent). Pack and Goal are open vocabulary. Orchestrator for continuing work in a fresh chat. Not same-session continuation without a new chat.

H

herdr-remote-channel

czinegeroland / herdr-remote-channel

Use the `hrc` command line to communicate with another Herdr user across machines: draft notes, questions, and delegation requests, build context packages, read approved inbox content, and diagnose synchronization problems. Use when the user wants to reach a remote collaborator or their agent, check an HRC inbox or channel, or set up an HRC channel. Gather what you need by asking, then run it, and send the user to a Herdr pane for the decisions only a person may make rather than to a terminal. Do not use it to read a private key, to approve another person's decision, or to reach anything on their machine: none of that is possible here.

I

implement

toy-crane / skills

Implement or resume settled work from a selected spec folder as one handoff bundle. Use when the user provides a `docs/specs/SLUG/` folder and wants its settled spec or approved tasks completed in the current checkout with verification, one completed and triaged automated code review, and a runnable product handoff when the repository exposes one through a local server.

I

improving-prompts

joshuadavidthomas / agent-skills

Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files — diagnose the concrete failure first, then apply current documented Anthropic best practices (explicit instructions, context/motivation, examples, output and verbosity control, thinking/effort, CLAUDE.md size and skill-description rules) instead of inventing improvements. Triggers when a prompt isn't followed, a skill won't activate, CLAUDE.md is too long or ignored, or migrating prompts to current Claude models.

K

kntnt

kntnt / skills

Manage this collection — which skills are Enabled, in Global and in each Project.

K

krypton-planning

jturntdev / krypton

Use when a user has a feature request, bugfix, refactor, migration, architecture change, or product goal and needs an implementation plan before coding. Use especially when wrong ownership, duplicate paths, stale contracts, weak evidence, or unclear cutover would make plausible agent work dangerous.

L

langchain-agent

rebyteai-template / rebyte-skills

AI agent with tools (search, calculator) using LangGraph and AI SDK.

L

langchain-oss-primer

langchain-ai / skills-benchmarks

ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any code. Covers framework selection (LangChain vs LangGraph vs Deep Agents), agent archetypes, dependency setup, and which skills to load next based on your decisions.

L

LG-token-saver

jnbno1163 / lg-token-saver

Save 87% token usage. Zero install. Input+Output+Context optimization. 8 rules. 6 months production verified.

Intelligent search for agents. Multi-source retrieval with confidence scoring - web, academic, and Tavily in one unified API.

O

openspace

akillness / jeo-skills

Install and route through OpenSpace, the skill management layer for AI agents, so a host agent can retrieve/rank/load the right SKILL.md out of this jeo-skills catalog (~150 installed skills), then evaluate skill quality from real execution evidence and evolve skills via FIX/DERIVED/CAPTURED updates. Covers install-as-skill-finder, retrieve-a-skill, evaluate-quality, evolve-skills, and local-first hub share/import. Triggers on: openspace, skill finder, skill retrieval, find the right skill, rank skills, skill discovery, skill quality, evolve skill, FIX DERIVED CAPTURED, skill hub, openspace-mcp, DiscoverSkills, skill-discovery, delegate-task.

O

orchestrate-with-handoff

yahyabedirhan / skills

Pick up an effort from a handoff document and orchestrate it to a pull request.

P

parallel-execution

noobygains / godmode

Use when facing 2+ tasks that share no state and have no sequential dependencies - enables concurrent investigation or implementation by dispatching one agent per isolated problem domain