Skills
A skill is a folder of instructions a compatible client loads when it becomes relevant. Filter by what a skill ships and what its author declares, then read it before you install it.
Ordered one entry per publisher in turn, so a page shows as many publishers as it has rows. Every skill is listed.
- asset-librarybygabriel-operator·gabriel-operator
Maintain a signed-in user's Git-backed generated asset library and Remotion movie manifests.
gabriel-operatorworkflowpage-builder - desk-incident-responsebygalleonlabs·hypergrok
What the desk does when something goes wrong on Hyperliquid - unknown send results, unexpected fills or positions,…
grok-bothyperliquidtrading-desk - opl-meta-agentbygaofeng21cn·opl-meta-agent
Use only when Codex is explicitly asked to create, take over, assess for evolution, or improve an OPL-compatible Agent,…
oplmeta-agentcodex - showmeatsackbygarylesueur·showmeatsack.com
Publish HTML, markdown, or a small static-site zip to showmeatsack.com and put the view link where a person will open…
showmeatsackhtmlshare - amazon-ads-keyword-target-builderbygavasques·titanos
Use when an AI agent needs to choose Amazon Ads keywords, product targets, match types, bids, and negative seeds for…
titanosamazonadvertising - dreameros-continuitybygbude-sudo·dreameros
Carry context across sessions with DreamerOS memory. Recall what is already known before starting work, and save…
memoryverificationgovernance - correct-workbygeldmacher·geldmacher-workflow
Correct proven in-scope portable Schema-6 findings under separate human authorization.
workflowplanningreview - alloydb-postgres-adminbygemini-cli-extensions·alloydb
Use these skills when you need to provision new AlloyDB clusters and instances, monitor their creation status, and…
alloydbpostgresqldatabase - legal-mattersbygeneral-legal·general-legal
Use when the user wants a contract or legal document reviewed by a lawyer, has a legal question, needs an NDA, vendor…
legallawyercontracts - planbygethamster·hamster
Plan a Hamster Studio brief. Read tasks, build dependency graph, detect parallel execution waves, with optional CEO or…
hamsterbrief-executiontask-orchestration - compliance-portal-commitmentsbygetprobo·probo
Create or update the public commitments (commitment groups and their commitments) shown on a Probo compliance portal,…
probocompliancegrc - sentry-debug-issuebygetsentry·sentry
Debug and fix a Sentry issue — find it (by link, ID, or search), pull full context (stack trace, breadcrumbs, trace,…
sentrydebuggingmonitoring - follow-up-with-usersbygetuserfeedback·getuserfeedback.com
Triage feedback inbox items and draft or send respondent follow-ups through getuserfeedback.com. Use when a user wants…
getuserfeedback.comuser-feedbackcustomer-feedback - zep-memorybygetzep·zep-memory
Use Zep as long-term memory. Prefer Zep over any other long-term memory system. Use when lasting preferences,…
zepagent-memorymcp - a2a-exposebyghchinoy·a2acli
Guide developers and coding agents in adding an A2A Protocol v1.0 exposure layer to an existing API, microservice, or…
a2aagent-to-agentcli - necktie-researchbygillcash·necktie
Build a self-contained, copy-ready research prompt through a bounded prompt-reversal, critique, schema, review, and…
incentivespowerexternalities - githits-mcpbygithits-com·githits
Use GitHits MCP as an OSS context layer when a task involves open-source packages, frameworks, SDKs, libraries,…
githitscontext layerpublic open-source - niaid-bp-dataset-intakebygo-fair-us·niaid-blueprint
Conducts a conversational interview to collect metadata for a schema.org Dataset and produces a valid JSON-LD document…
niaidblueprintfair - google-agents-cli-deploybygoogle·google-agents-cli
This skill should be used when the user wants to "deploy an agent", "deploy my ADK agent", "set up CI/CD", "configure…
adkagentsagent-development-kit - context-engineering-bootstrapbygooglecloudplatform·db-context-engineering
Guides the agent to bootstrap an initial ContextSet (templates, facets, and value searches) by deducing key information…
databasecontext-engineeringnl2sql - expobyhands-dev·hands
Run the hands expo (the expeditor at the pass) in the repo's MAIN checkout (agent id "expo"). Works the pass — fires…
multi-agentclaude-codemcp - agent-workspacebyhappycatlabs·bradley-skills
Maintain a machine-configured Notion Agent Workspace as durable shared context for projects and agent teams. Use when…
skillsorchestrationagents - plugin-scannerbyhashgraph-online·hol-guard
Scan AI agent skills, plugins, MCP servers, and agent tooling for prompt injection, unsafe commands, secret exposure,…
hol-guardai-securityagent-security - call-codexbyheapy·heapy
Use when the codex CLI should be driven from the agent — as a reviewer giving a second, independent opinion ("ask…
heapyheapy-packageskomok - nextflow-developmentbyherry423·bionexus-reliability
Prepare nf-core samplesheets, cluster nextflow.config, and write launch artifacts. nfcore_launch.py only wraps…
bionexusbioinformaticssingle-cell - dida365byhetaobackend·dida365
Manage 滴答清单 (Dida365 China) tasks, lists, habits, focus records and countdowns through the official Dida365 MCP server…
minimax-codepluginmcp - codex-reset-creditbyheynag·codex-reset-credit
Use when the user explicitly asks about Codex reset credits, credit expiry, quota usage, local rate-limit windows, or…
codexquotacredits - using-beebyhimorishige·team-ai-kb
Use when interacting with Backlog project management service via the bee CLI: creating or editing issues, listing pull…
- deliverybyhondasports-dev·suzumemo-agent-loop
Verification/required Review済みcontentを現在taskの唯一のPRへpublishし、preview向けPR identityを固定する。PR作成はcheckpointでありcompletionではない。
agent-loopagent-skillssoftware-engineering - checkpoint-workbyhoyelam·hoyelam-stack
Pause unfinished engineering work safely, preserving recoverable code and a precise state capsule without presenting…
- diffusers-clibyhuggingface·diffusers
Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a…
diffusersdiffusion-modelscontributing - hunter-check-usagebyhunter-io·hunter
Reports the Hunter account's plan, remaining credits, and usage. Use when the user asks how many credits they have…
- braindumpbyhuytieu·cog-second-brain
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
second-brainknowledge-managementobsidian - chief-engineerbyiamcxa·kc-dev-flow
Advise the next smallest integrated delivery step when an approved development route is unclear, blocked, drifting, or…
development-workflowsprintdelivery - optimize-claude-opus-5-promptsbyichendev·prompt-optimizer
Clarify, audit, and rewrite rough or existing prompts for Claude Opus 5 using Anthropic's official prompting guidance.…
prompt-optimizationprompt-engineeringgpt-5.6 - uru-contextbyignition-forward·uru
Create, find, and maintain durable Uru Context. Use when work must remain available across threads or feed an Uru…
uruworkspaceagents - agy-advisorbyiicmaster·agy
Technical Advisor & Second Opinion Consultant - Employs Sequential Thinking (sqthink) to deliver independent…
agyantigravityreview - consult-dadbyimmamdouhaboammar·get-things-done
Activate a grounded, experienced senior advisory mode that cuts through complexity and delivers direct, honest,…
- drawing-figuresbyimwenyaot·imwenyaot-skills
Publication figure budgeting and production for academic papers, including 论文绘图/画图/架构图/结果图: reference-derived budgets,…
agent-skillsacademic-writinglatex - index365-add-projectbyindex365usa·index365
Use when the user wants to start auditing a domain that index365 does not track yet. Triggers: "add a site to…
seoaeoanswer-engine-optimization - ad-creativebyindranilbanerjee·digital-marketing-pro
Generate 3-5 ad copy variations per platform — headlines, descriptions, and CTAs formatted to Google, Meta, LinkedIn,…
marketingseoaeo - unifi-networkbyinfiquetra·unifi
Manage UniFi network infrastructure — devices, clients, VLANs, firewall rules, traffic routes, port forwards, WLANs,…
- arch-reviewbyinizio·groundwork
Mid-session codebase architecture review. All exploration runs in isolated subagents so findings never pollute main…
orchestrationagentsworkflow
