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.
- proppi-evidence-briefby proppiaiPrepare a concise property evidence brief from documents or notes the user provides. Use for maintenance timelines,…
- proven-onboardingby provenaiConduct or simulate PROVEN's adaptive skincare onboarding: understand the customer's skin and priorities, support valid…
- provod-mcpby provod-aiUse when routing work through the hosted Provod MCP.
- enlivenby proxysoulMake an Electron or web app measurably faster without losing a feature, and prove it. The agent builds a repeatable A/B…
- notebooklmby proyecto26Interact with Google NotebookLM (notebook.google.com) notebooks — chat with the AI, generate artifacts (slides, audio,…
- OctoparseSponsoredNo-code web scraping, on a schedule.Scrape with Octoparse
- triage-investigatorby pseudogonInvestigate the production-support triage queue. Lists every Linear issue currently in Triage, follows each one's…
- context-decayby pskoettRevalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain,…
- psmodule-module-development-orchestrationby psmoduleCoordinate substantial PSModule development across a parent session and narrowly scoped child sessions while preserving…
- add-a-facilityby psmoorePut a pool facility's published schedule into Pool Relay, lane by lane. Use when someone asks to add, import, build or…
- architectby pstack-portsSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use…
- channel-brainsby pu11enCreate, resume, monitor, inspect, or query Channel Brains indexes of public YouTube captions. Use when a signed-in user…
- chatgpt-book-metadataby publicalaSearch non-transactional ebook and audiobook bibliographic metadata on EbooksDepository by title, author, publisher, or…
- korean-law-researchby publicdata-streamFind and quote Korean statutes, ordinances and court precedents from the OpenLegal corpus with exact provenance. Use…
- publish-funby publishfunSubmit, revise and track a research paper at Publish.fun, the AI-reviewed research journal, through its REST API or MCP…
- huddoby puffo-aiJoin and take part in Huddo group chats (shared rooms where people and AI agents talk together) through the huddo MCP…
- autodlby puiching-memory使用本地自建 AutoDL Direct 插件查询余额和 Pro 实例、创建或开关机 GPU 实例、保存镜像，并配合系统 SSH 上传代码、训练、查看日志和取回结果。用户提到 AutoDL GPU 工作流时使用。
- okf-harnessby pumblusUnified OKF Harness entrypoint. Use when the user asks to create, find, select, repair, check, ingest into, reconcile,…
- agentdeck-reportby puritysbRead, claim and report an explicitly shared AgentDeck request using its request ID through an already approved local…
- get-startedby puzzlefinFirst run with Puzzle. Use right after the user connects Puzzle, or when they ask what Puzzle can do here or how to get…
- daily-brief-loopby pyranthus-hqUse only when the user explicitly asks to run, sync, advance, or persist Mora's durable daily brief. Executes the…
- create-technical-drawingby pzfreoCreate, inspect, revise, or download a Draftwright technical drawing from a STEP model. Use when the user asks for a…
- create-first-agentby qaml-aiCreate a first camelRun agent from a plain-language description, try it with a message, and explain how to keep using…
- qawolf-startby qawolfUse before any QA Wolf work, including onboarding an application, choosing a first test, outlining or creating a flow,…
- korean-writingby qb20nhWrite, copyedit, and restructure Korean prose while preserving meaning, evidence, and authorial voice. Use for Korean…
- setupby qdrantConfigure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables,…
- remote-grok-buildby qervasUse this when bridging Grok Bot chat to local Grok Build (the grok CLI) on a linked Windows PC: mission control,…
- check-handoffby qianqiulpValidate handoff manifests and evidence files for AI task交接
- ai-agent-architecture-auditby qingye-labSpecialized architecture audit for AI-agent systems and AI-enabled products. Use for agent runtimes, tool-using…
- coprogrammer-active-syncby qiu-guanzongCoordinate coding windows through dependency-aware task claims, edit guards, conversations, bounded waits, leases and…
- cli-designby qjcgDesign, review, and improve CLI interfaces following clig.dev guidelines. Use when building CLI tools, commands, flags,…
- bugsby qlaneaiShow what Qlane found on a pull request or a recent test run — defects, failing and blocked cases, the steps to…
- sb-demand-captureby qntwebDiagnostic over three terms: the destination's demand, the searches on the property's own booking engine, and actual…
- qodo-codebase-wisdomby qodo-aiUnderstand how code works, how a change was done before, and which repos are coupled — to answer a question, plan a…
- qol-sessionsby qol-toolsUse when an architect must create or drive an implementation agent in another terminal through event-signalled…
- feature-brief-authoringby qqwasqqsProduces a complete, validated Feature Brief for a software feature - source precedence, gap analysis before drafting,…
- gepa-omni-skillby qredenceAutomatically improve any scorable text artifact—prompts, programs, configs, specs, regex/SQL/schemas, agent scaffolds,…
- qrxby qrxcodesMakes branded, print-ready art QR codes that always scan, using QRX (qrx.codes). Use when the user wants a QR code for…
- aws-saas-infraby quantabridges-solutionsManage AWS infrastructure for a QBS SaaS project using Terraform. Covers first-time setup, adding resources (Lambda,…
- cairn-assertby quarkosAssert typed Cairn facts via cairn_assert after a decision, deploy, URL, or command actually lands. Unique…
- claim-ledgerby quattro-commasUse when an AI coding agent reports that work is finished, when deciding whether to believe a completion claim, when…
- qiby qubie-orgEntry point for working on the qi repository — a local-first text river running IBM Granite 4.1 via llama.cpp, with…
- investigator-sheetby questportalOpen, populate, revise and roll guest Call of Cthulhu 7th edition investigator sheets. Use for single or batch…
- greetby quetzal-rivasGreet the user and offer help.
- photoshoot-mapby quinntynebrownCreate illustrated photoshoot maps for a supplied location, with numbered shooting spots, routes, and lens and lighting…
- transcripted-companionby r3dbarsUse Transcripted on this Mac to retrieve saved meetings, dictations, and writing; control a meeting when asked; or…
- agent-evalsby raandreeUse this skill when a Copilot skill, prompt, or agent changes and someone needs evidence that it works rather than one…
- shallnotby rachidchabaneRequirement-to-test traceability with the `shallnot` CLI. Use in any repository that has a `shallnot.yaml`, whenever…
- link-managementby radaarioCreate and manage shortened URLs using RADAAR's URL shortener. Use when the user wants to shorten links, track link…
