Skills

G

goalgo

backtthefuture / goalgo

GoalGo: turns ordinary requests into verifiable Codex Goals through quick restatement, key follow-up questions and accumulated answers, and can launch directly once the user confirms the final version. Applies to scenarios such as "help me write a Goal", "turn the request into /goal", "ask me questions to fill in the gaps", "wait for my confirmation before running after generating", "start goal mode", and when the user replies "start" or "confirm launch" to a previously pending Goal. By default it only designs; it calls the Goal tool to launch only after showing the current version and receiving explicit confirmation.

G

grill-with-docs

guillermomurillo / memo-flow

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

G

grill-with-docs-smarter

gil-1 / skills

Personal Skills that improve managing large codebase with agents

H

harness-download

fairladyz625 / harness-anything

Guide the user from their first download through getting started with Harness Anything: check the environment, obtain persistent source code, install dependencies, link the full skill set to the selected Agent's user directory, then continue with target repository initialization and first use of the orchestrator skill. Use when the user asks to download, install everything, onboard for the first time, or get Harness set up in one go. Distribution is currently from source; do not assume an npm package has been published.

H

headless-adapters

youdotcom-oss / agent-skills

Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and schema-driven compliance testing.

H

help

andrueandersoncs / skills

Select a specialist for engineering, agent systems, writing, research, planning, or project work when the workflow is unclear.

I

implement-feature

robertderose / dstack

Implement or continue the next ready task in a reviewed Beads feature while keeping code, tests, documentation, evidence, and commits aligned. Use when asked to implement feature work after `start-feature` closes `spec-reconcile`.

I

implement

leek / agent-skills

Implement one work item end to end, or every ticket of a spec in one run: scope and claim it when trackable, TDD at chosen seams, commit, review, verify, resolve it, and open a PR when asked.

I

inbound-triage

bbengamin / skills

Triage inbound Growth Operator Paperclip issues for AFK readiness. Use when reviewing inbound or content-led acquisition work — personal brand, LinkedIn, newsletter, YouTube, publishing-prep, or signal-capture — before delegation.

I

interrogate

q-qp-p / pstack

Use for “interrogate”, “adversarial review”, “multi-model review”, “challenge this”, “stress test this code”, “find blind spots”, or “tear this apart”. Multiple LLM reviewers challenge changes from independent angles.

I

invoking-gemini

oaustegard / claude-skills

Invokes Google Gemini models for structured outputs, image generation, text-to-speech narration, multi-modal tasks, and Google-specific features. Use when users request Gemini, image generation, Gemini TTS or a synthesized voice, structured JSON output, Google API integration, or cost-effective parallel processing.

I

invoking-github

oaustegard / claude-skills

Enables GitHub repository operations (read/write/commit/PR) for Claude.ai chat environments. Use when users request GitHub commits, repository updates, DEVLOG persistence, or cross-session state management via GitHub branches. Not needed in Claude Code (has native git access).

J

javascript-sdk

magentosh / superpowers

JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, human approval. Use for: JavaScript integration, TypeScript, Node.js, React, Next.js, frontend apps. Triggers: javascript sdk, typescript sdk, npm install, node.js api, js client, react ai, next.js ai, frontend sdk, @inferencesh/sdk, typescript agent, browser sdk, js integration

L

laravel-mcp

rawveg / skillsforge-marketplace

Laravel v12 - The PHP Framework For Web Artisans (project, gitignored)

L

litefuse

litefuse / skills

Interact with Litefuse and access its documentation. Use when needing to (1) query or modify Litefuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Litefuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Litefuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.

L

llm-models

magentosh / superpowers

Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3 Pro, Kimi K2, GLM-4.6, Intellect 3. One API for all models with automatic fallback and cost optimization. Use for: AI assistants, code generation, reasoning, agents, chat, content generation. Triggers: claude api, openrouter, llm api, claude sonnet, claude opus, gemini api, kimi, language model, gpt alternative, anthropic api, ai model api, llm access, chat api, claude alternative, openai alternative

L

ln-311-agent-reviewer

levnikolaevich / claude-code-skills

Worker that runs parallel external agent reviews (Codex + Gemini) on Story/Tasks. Background tasks, process-as-arrive, critical verification with debate. Returns filtered suggestions for Story validation.

L

local-models

glebis / claude-skills

Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. Use for cheap/bulk text work (summarize, classify, extract JSON, anonymize PII, translate, proofread, keywords), local embeddings, and offline image description — and prefer it over a cloud API whenever a task is privacy-sensitive, must run offline, is high-volume/low-stakes, or just needs a fast throwaway answer. Provides an `lm` CLI wrapper plus an OpenAI-compatible local server.

L

long-agent

johnlindquist / claude

Manage long-running agent sessions. Use for tracking progress in extended tasks, maintaining context across long sessions, and managing multi-step workflows.

PUA Loop — autonomous iterative development with PUA pressure. Keeps running until task is done, no user interaction needed. Combines Ralph Loop iteration mechanism with PUA quality enforcement. Triggers on: '/pua loop', '/pua:loop', '自动循环', 'loop mode', '一直跑', '自动迭代'.

M

maintain-verification-skill

q-qp-p / pstack

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

M

mcp-harness-repo-maintainer

arenukvern / mcp_flutter

Maintains repo-local action contracts and harness repositories where product CLI and MCP adapters stay thin over core libraries. Use when adopting or improving steward.yaml actions, capability-level adoption evidence, cold-start proof loops, probes, benchmarks, CLI/MCP/core parity, adapter refactors, packages/core boundaries, or sibling harness layout; use repo-quality-system-lifecycle first for general app/library/tool stewardship baselines.

M

mcp

iuliandita / skills

Build and debug Model Context Protocol (MCP) servers, clients, tools, resources, and OAuth integrations.

M

mino-core

my-take-dev / inspired-mino-design-skills

Internal foundation used when sharing Evidence, approvals, common judgments, and requirement tracing across related design Skills. Not for standalone public requests, specialized design as a whole, or small mechanical changes.

M

mino-reproducible-development

my-take-dev / inspired-mino-design-skills

Router used when integrating two or more specialized deliverables, or an end-to-end trace from requirements to implementation, review, and verification. Not for a single design deliverable or small mechanical changes that do not touch public semantics.

M

mixture-of-experts

arenukvern / mcp_flutter

Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different critical lenses to cross-reference findings and detect flaws, overlap, retention issues, or drift. Use when designing architectures, analyzing complex code, verifying multi-step plans, classifying evidence artifacts, or looking for duplicated intent in a repo.

M

model-first-reasoning

petekp / agent-skills

Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.

M

multi-agent-architecture

aaaaqwq / agi-super-team

Multi-agent architecture design and intelligent spawn system. Use this skill when designing multi-agent systems, configuring specialized agents, implementing intelligent task dispatch, or optimizing concurrent processing capacity.

N

nodumb-loop

hanumatori / nodumbmode

Route nontrivial work among ask-nodumb, nodumb, nodumb-design, edge-hunt, system-feedback, and changelog-discipline, choosing only the check capable of changing the next step. Use at the start of a product or technical task when several skills may apply, when the problem layer changes, or after an unsuccessful check. Do not use for small, obvious edits or when the appropriate specialized skill is already clearly identified.

N

notebooklm-mcp

afonsoft / skills

Use when the user wants to configure, authenticate, or use Google NotebookLM via the nlm CLI or MCP.

N

ntm

boshu2 / agentops

Operate selected NTM agent panes and inspect native state. Use when: persistent tmux roles are requested; pane liveness and prompt delivery are not validation.

O

OpenAI Apps MCP

ovachiever / droid-tings

Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI). Use when: developing ChatGPT extensions, implementing MCP servers, or troubleshooting CORS blocking (allow chatgpt.com), widget 404s (missing ui://widget/), wrong MIME type (text/html+skybridge), or ASSETS binding undefined.

O

openspec-new-change

pbh-btn / peerbanhelper

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, 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", 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

orchestrator

alphaonedev / openclaw-graph

Multi-instance delegation: route to A-H instances, fanout/aggregation, sessions_send/spawn, health checks

O

orchestrator

first-fluke / oh-my-agent

Agent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.

O

outbound-triage

bbengamin / skills

Triage outbound Growth Operator Paperclip issues for level-aware AFK readiness. Use when reviewing lead sourcing, enrichment, personalization, sequences, Instantly, Clay, Grinfi, CRM, reply handling, warm-intro, operator walkthrough booking, or outbound validation work before delegation.

P

peach-skill-feedback

peachsolution / peach-harness

A general-purpose skill that structures problems and know-how found while using Peach skills and documents them in docs/스킬피드백/. Triggered by keywords such as "스킬 개선", "피드백 정리", "문제점 기록", "스킬 리뷰", "개선사항", "스킬 피드백". Applicable to all Peach skills. Structured so that other AI agents can read the documents and improve the skills.

P

plan-plus

ww-w-ai / bkit-claude-code

Brainstorming-enhanced PDCA planning with intent discovery and YAGNI review. For a single feature's plan use /plan-plus; for grouping multiple features under one scope/budget see /sprint master-plan (v2.1.13). Triggers: plan-plus, brainstorm, plan plus, intent

P

planner

jdrhyne / agent-skills

Create structured plans for multi-task projects that can be used by the task-orchestrator skill. Use when breaking down complex work into parallel and sequential tasks with dependencies.

P

planning-patterns

romiluz13 / cc10x

Internal skill. Use cc10x-router for all development tasks.

P

planning-task-execution

b-mendoza / agent-skills

Plans how to execute exactly one already-selected numbered Jira or GitHub task by producing an execution brief, implementation plan, behavior-oriented test specification, and scoped refactoring recommendation. Use for Phase 5 task-execution planning with a workflow key and TASK_NUMBER. Does not decompose the parent work item, plan multiple tasks, implement code, or advance to the next task.

P

plans-kanban

duc01226 / easyplatform

[Planning] Use when you need plans dashboard server with progress tracking and timeline visualization.

P

plugin-marketplace-setup

arenukvern / mcp_flutter

Designs public or private Agent Skill and plugin marketplaces for Cursor, Claude Code, Codex, Zed, Open Plugin, and npx skills—manifest layout, install matrix, and Skill Steward vs product boundaries. Use when setting up a marketplace, distributing skills/plugins to a team, private registry, .cursor-plugin, .codex-plugin, .plugin, .claude-plugin, or skills.sh publishing.

P

principle-build-the-lever

q-qp-p / pstack

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun

P

principle-encode-lessons-in-structure

q-qp-p / pstack

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

P

principle-guard-the-context-window

q-qp-p / pstack

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

P

principle-prove-it-works

q-qp-p / pstack

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

P

professional-behavior

axross / skills

Handling uncertainty, evaluating feedback, and independently reviewing investigation, plan, or design deliverables — the conduct baseline for questions and changes, including read-only work. Triggers on requested drafts or option sets, review findings, proposed corrections, uncertain facts or intent, consequential interpretations of behavior or ownership, "are you sure", "don't guess", "what's the latest", exact version or API claims, and reporting results. Not a change-loop skill; it governs judgment within work already underway. Covers three-source triage, discriminating checks, the clarifying interview, accuracy, bounded deliverable review, feedback judgment, and reporting in the human's language

P

project-memory

timlai666 / skills

Shared cross-agent project memory for costly trial-and-error, hard-won solutions and verified corrections to outdated lessons. This skill MUST be invoked before starting work in an existing project, to load what was already learned there, and MUST be invoked again as that work wraps up, to record what this session learned before it ends. MUST also be invoked on the triggers below to record something new, and SHOULD be invoked whenever the user states something worth remembering about how this project behaves. MUST NOT be used for task lists or open bugs, which belong in the issue tracker or AGENTS.md. Triggers on: 記一下, 之前踩過什麼雷, 學到什麼, 有什麼教訓, remember this, lesson learned, project learnings, 記錄一下, 之前遇過的, 把這個記起來

P

prompt-template-wizard

jawwadfirdousi / agent-skills

Rigorously collects and validates all fields needed to produce a complete, unambiguous prompt template for features and bug fixes. The skill asks targeted questions until the template is fully filled, consistent, and ready to paste into a Codex/GPT-5.2 coding session.

Q

qa-team

laststance / skills

Parallel QA agent team

R

ralph-wiggum

agrimsingh / ralph-wiggum-cursor

Implements the Ralph Wiggum autonomous iteration technique with deliberate context management. Use when building greenfield projects, iterating on well-defined tasks, or when continuous autonomous development is needed. Manages context like memory - tracks allocations, prevents redlining, and knows when to start fresh.

R

recall

joelhooks / joelclaw

Fan-out search across all memory sources when context is unclear or vaguely referenced. Triggers on: 'from earlier', 'remember when', 'what we discussed', 'that thing with', 'the conversation about', 'did we ever', 'what happened with', 'you mentioned', 'we talked about', 'earlier today', 'last session', 'the other day', or any vague reference to past context that needs resolution before the agent can act.

R

recall

q-qp-p / pstack

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for “recall my work on X”, “catch me up”, “what have I been working on”, “where did I leave off”, before starting or resuming work.

R

recover-context

pchalasani / claude-code-tools

Extract full context of the last task from the most recent parent session

R

reflect

q-qp-p / pstack

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect

R

related-skill

magentosh / superpowers

Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions

R

relay-plan

sungjunlee / dev-relay

Use when a relay run needs its review anchor, evaluation channels, or dispatch prompt — always before relay-dispatch, whether AC are explicit, vague, or missing.

R

repository-governance-lifecycle

arenukvern / mcp_flutter

Master orchestration for repository governance, North Star impact, sub-Star boundaries, and repair-first or evidence-first drift checks. Guides an agent through the complete lifecycle of making architectural decisions, documenting them, writing FAQs, and cleaning up stale plans while adhering strictly to repo ethics and brand tone. Use whenever you need to make a structural change, write an ADR, update the doc lattice, or govern repository architecture.