Skills

P

pipeline-router

willoscar / research-units-pipeline-skills

Route an unbound research Goal to one Workflow or materialize its initial C0 kickoff block; use during initial binding, not for later checkpoint summaries or approval.

P

plan-validate

duc01226 / easyplatform

[Planning] Use when you need to validate a plan with critical questions interview.

P

principle-prove-it-works

ericlitman / open-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

prompt-generator

iuliandita / skills

Write or improve one-off LLM prompts, system prompts, and prompt templates from rough notes.

P

promptmateio

membranedev / application-skills

Promptmate.io integration. Manage Prompts, PromptSets, Variables, Templates, Models, Users and more. Use when the user wants to interact with Promptmate.io data.

R

re-feedback

dslsdzc / rev-skills

Meta-gateway for experience feedback. Collects from three sources (session reviews/article scans/manual input) → distills and anonymizes → categorizes → handles in three ways (publish an issue/store locally/do not store). Trigger terms: feedback experience, save experience, submit experience, experience review, capture lessons, lessons learned

R

reasoning

alicoder001 / agent-skills

Chain-of-thought reasoning, self-reflection, and systematic problem-solving patterns for AI agents. Use before any complex task to ensure logical and accurate solutions.

R

reconnaissance

kucherenko / gangsta

Use when beginning a new heist — deploys associates to survey the target codebase, existing tests, dependencies, documentation, and the ledger to produce a reconnaissance dossier for the don's review

R

research

c0nant / skills

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

R

research-step

allenai / asta-plugins

Plan and execute autonomous research as a graph of typed tasks tracked in beads. Use when working from a mission.md to drive multi-step research with explicit dependencies and structured outputs.

R

roblox-studio-mcp

flatbedj / roblox-skills

Use when driving or inspecting Roblox Studio through the Studio MCP tools — running Luau in Studio, play/stop, screenshots, reading/searching the datamodel or scripts, generating meshes/materials/models, inserting assets, moving the character, or when the MCP link is dead (no Roblox tools show up). A capability menu + gotchas + connection troubleshooting.

S

screen-control-operator-v3

breverdbidder / life-os

Autonomous browser control with Cowork-style skill recording. Use when user requests "control my screen", "record workflow", "verify Lovable", "test scrapers", "debug DOM", "autonomous testing", or any browser automation task. Uses CDP + Accessibility Tree for 10x faster, 100% reliable element targeting. NO screenshots.

S

sdd-apply

fearovex-labs / agent-config

Implements SDD plan tasks following specs and design, marking progress in tasks.md as it goes. Trigger: /sdd-apply <change-name>, implement change, apply SDD tasks, write code for change.

S

session-handoff

robsonrung / rar-skills

Create an immutable session handoff or orient from a selected handoff. Use when the user asks to hand off current work, save continuity notes, resume from a handoff, or inspect available handoffs. Do not use for an ordinary session summary.

S

session-memory

chachamaru127 / claude-code-harness

Internal sub-skill for cross-session handoff, durable learning, and memory persistence. Invoked by session/memory workflows only. Do NOT load for: implementation, review, ad-hoc notes, or SSOT editing.

S

setup-agent-skills

nstaab1 / nathan-agent-skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

S

shadscan-pre-commit

theorcdev / skills

AI-agent commit protocol that establishes a Shadscan baseline and reruns the audit immediately before every agent-created commit without installing dependencies or configuring Git. Use when an agent is asked to commit work in a React shadcn project, prevent UI regressions during an agent task, or run Shadscan before commits.

Ship an approved spec on a dedicated branch through native tracker transitions, separate implementation commits, independent review gates, and a linked draft pull request.

S

skill_creator

vuralserhat86 / antigravity-agentic-skills

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-audit

sickn33 / agentic-awesome-skills

Pre-install review framework for AI agent skills: inspect complete content, permissions, dependencies and suspicious behavior before activation.

S

skill-creator

project-n-e-k-o / n.e.k.o

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-design-philosophy

majesticlabs-dev / majestic-marketplace

Core philosophy for designing Claude Code skills - when to use skills vs agents, the knowledge test, and what makes skills valuable. Use when deciding component type or evaluating skill quality.

S

skill-native-escalation-routing

nyldn / claude-octopus

Use when choosing native or multi-LLM handling for init, review, or security requests

S

skill-ship

nyldn / claude-octopus

Package and finalize completed work for delivery — use when a feature is done and ready to ship

S

skills-manager

ananddtyagi / cc-marketplace

Universal consolidation & audit skill for Claude Code skills. Analyzes project state, detects redundancies, and safely manages skills with backup, confirmations, and rollback capabilities. Never assumes without verifying actual code and usage patterns.

S

skills-registration

bytedance / agentkit-samples

Registers a local skill to the AgentKit platform by uploading it. Invoke when the user wants to publish, upload, or register a skill they have created

S

space-xhs-buddy

spacezephyr / creator-buddy

The central console for Xiaohongshu content creation. Determines which stage the user is currently stuck at, routes to the corresponding specialized skill, and strings multi-step workflows together for execution. Triggers when the user says "do Xiaohongshu", "help me run Xiaohongshu", "walk through Xiaohongshu from start to finish", "I want to start doing Xiaohongshu", "the full Xiaohongshu process", "I don't know where to start", "help me with Xiaohongshu", or raises needs spanning multiple stages at once (e.g. "help me come up with topics and write them out with images ready"). For needs limited to a single stage, use the corresponding specialized skill directly rather than this skill.

S

subagent-driven-development

ganyuanran / aegis

Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

S

subagent-driven-development

zenobi-us / dotfiles

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

T

team-coordinate

catlog22 / claude-code-workflow

Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on "Team Coordinate ".

T

titan

simota / agent-skills

Delivering working code fastest via build-first product delivery through minimum agent chains; S/M scopes skip planning and build immediately. Use when compressing time-to-first-PR.

T

to-spec

nstaab1 / nathan-agent-skills

Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.

T

to-tickets-agentic

nstaab1 / nathan-agent-skills

Break a plan, spec, or conversation into tracer-bullet tickets assigned to autonomous or attended lanes, with pre-agreed test seams, blocking edges, and overlap-safe execution frontiers. Use when preparing work for unattended coding agents as well as human-guided implementation.

T

to-tickets

nstaab1 / nathan-agent-skills

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

T

token-diet

kulaxyz / token-diet

Cut token usage across the whole session without losing correctness or substance — concise user replies, lean tests/docs/plans/comments, tight code, disciplined context and tool use, and cheap sub-agent delegation. Load when the user wants less verbosity, lower cost, fewer tokens, or a "token diet" / "lean mode"; also triggered by /token-diet or "token diet on".

T

token-efficiency

superclaude-org / superclaude_framework

Activate ultra-compressed output mode for maximum token efficiency. Use when context is running low, user requests brevity, or dealing with large-scale operations.

T

tool-hooks-doctor

heyvhuang / ship-faster

Detect whether Claude Code evolution hooks are installed/enabled, and print a copy-paste fix. Use when you expect runs/evolution artifacts but nothing is being written. Triggers: hooks, evolution, runs/evolution, settings.json, PreToolUse, PostToolUse.

T

tres-request-skill-update

anthropics / claude-plugins-community

Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's working well. Use this skill whenever the user wants to share any kind of feedback about the plugin, its skills, or the TRES MCP. Trigger phrases include: "submit feedback", "report a bug", "request a feature", "suggest an improvement", "I have an idea", "something is broken", "the skill isn't working", "I love this skill", "this worked great", "the MCP is returning wrong data", "the flow is confusing", "can you fix the skill", "file a skill request", "give feedback", "this could be better". Also trigger proactively when the conversation appears to be wrapping up — e.g. the user says "thanks", "that's all", "looks good", "we're done", "nothing else", or any other signal that the task is complete. In that case, offer a brief feedback prompt instead of launching the full guided flow. Do NOT trigger for general questions about how a skill works — only when the user wants to submit feedback or the conversation is ending.

T

triage

dyrits / skills

Move tasks and external PRs through triage roles: categorize, verify, refine, and write agent-ready briefs. Use when the user asks to triage, or when a published request needs verification and a maintainer decision.

T

triage

nstaab1 / nathan-agent-skills

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

T

turn-based-discovery

alber70g / skills

Use the AskUserQuestion tool (the same multiple-choice mechanism plan mode uses) to get clarity from the user. Each question is multiple-choice plus a free-format "Other" escape. Ask in small batches — up to 4 questions per call (the tool's max), more if needed across calls. Use when scoping work, resolving ambiguity, or surfacing answers a research pass already raised. Triggers: `/turn-based`, `ask me`, `clarify`, `discovery mode`, `interview me`.

T

twitter-agent

ohmyskyhigh / threadwave-skill

Run a review-gated Twitter/X agent for normal daily growth: initialize strategy, create daily plans, present strategy/plan/task/draft reviews, inspect scheduler state, and summarize outcomes through ThreadWave. Use for Twitter agent, X agent, daily Twitter automation, account growth, content planning, tweet scheduling, draft review, or normal daily run requests.

U

update-aegis

ganyuanran / aegis

Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

U

use-other-model

ruan-cat / monorepo

Use when the user or agent asks to delegate work to another model/provider such as OpenCode, Claude Code, MiniMax, Gemini, or an independent reviewer; when the goal is token savings, batch or multi-file work, a task expected to run longer than 5 minutes, independent verification or security audit, model-tier routing, provider/model identity checks, OpenCode default/headless model checks, or choosing between MCP tools, an independent Claude Code session, OpenCode provider mode, and OpenCode default/internal-model mode.

V

verify

jayden-dang / skills

Use when about to say anything that implies success — "done",

V

verifying-skill-accuracy

trilwu / secskills

Fact-check LLM-drafted technical content against primary sources — source hierarchy, programmatic existence probes for tool and plugin names, class-before-instance error triage, the truncated-negative trap, adversarial re-checking, and the verified-stamp discipline. Use when auditing a SKILL.md for factual errors, before stamping a skill verified, when a command or artifact claim needs confirming against upstream documentation, or when reviewing any drafted content whose specifics were written from model memory.

Review repository-native specs, code diffs, PRs, docs, workflow artifacts, or skill changes as a shared readiness gate. Use when deciding whether a spec can move to planning, whether a code change is safe to continue or commit, whether a workflow artifact is coherent, or whether review findings should block the next step.

Create or update compact repository-native feature specs from rough requirements, issues, notes, product discussions, prototypes, screenshots, existing drafts, or substantial skill/workflow/protocol optimization requests. Use when turning ambiguous product or workflow intent into a concise spec under the repository's feature artifact root, including repository context discovery, active clarification, shared terminology, goal, rules, acceptance evidence, and open questions before review or development planning.

W

wait-what

nstaab1 / nathan-agent-skills

Stop. That last message did not land: re-pitch it

W

wayfinder

carlitose / agent-skills

Maintain a persistent map and investigation frontier for huge or vague work, using canonical normalized tickets and opt-in compatibility.

W

wayfinder

nstaab1 / nathan-agent-skills

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear

W

work-intake

nicepkg / ai-workflow

Entry point for ALL work requests - triages scope from trivial to massive, asks clarifying questions, and routes to appropriate planning skills. Use this when receiving any new work request.

W

workflow-project-intake

heyvhuang / ship-faster

Use when you need to clarify requirements and route to the right workflow (idea → executable input). Project intake + routing: help the user brainstorm and clarify intent, persist goal/context artifacts, then dispatch to the right workflow or step skill. Default route is workflow-ship-faster (Next.js 16.1.1) for idea/prototype→launch. Triggers: project kickoff, requirements clarification, brainstorm, ideas, discovery, intake.

W

writing-for-agents

nstaab1 / nathan-agent-skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md

W

writing-skills

ganyuanran / aegis

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Y

ydc-langchain-integration

youdotcom-oss / agent-skills

Integrate LangChain applications with You.com tools (web search, content extraction, retrieval) in TypeScript or Python. Use when developer mentions LangChain, LangChain.js, LangChain Python, createAgent, initChatModel, DynamicStructuredTool, langchain-youdotcom, YouRetriever, YouSearchTool, YouContentsTool, or You.com integration with LangChain.

A

academic-pipeline

cleardry / academic-research-skills

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 9-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.

A

afk-slice-worker

ykdz / skills

AFK slice execution: complete one design, implementation, verification, or fix action within given boundaries and return evidence

A

ag2-a2a

ag2ai / ag2-skills

Expose an AG2 `Agent` over the Agent-to-Agent (A2A) protocol so any A2A-compliant client (or another AG2 agent) can call it across process/host boundaries. Wrap the agent with `A2AServer(agent)` and serve it via `build_jsonrpc(...)`, `build_rest(...)`, or `build_grpc(...)` — each returns a ready-to-serve ASGI/gRPC object that publishes an A2A `AgentCard` (built by `build_card`) at `/.well-known/agent-card.json`. Use when you want an AG2 agent reachable as a standard networked A2A service — interop with non-AG2 A2A clients, multi-transport (JSON-RPC / REST / gRPC) endpoints, declared auth schemes, push notifications, or multi-tenancy. To consume a remote A2A agent from AG2 instead, point an `Agent` at `A2AConfig(card_url=...)`. Covers `A2AConfig`, `A2AServer`, `build_card`, security schemes (`bearer_scheme`/`api_key_scheme`/`oauth2_scheme`/`require`), and the in-process `testing.py` helpers (`make_test_client_factory`, `make_test_rest_client_factory`).

A

agent-engineering

ckorhonen / claude-skills

Battle-tested engineering principles for AI coding agents. Covers plan-first workflow, subagent delegation, self-improvement loops, verification gates, elegant solutions, autonomous bug fixing, and structured task management. Use when configuring agent behavior, writing AGENTS.md files, or improving agent reliability and code quality.