Top Agent Skills

Generate an XLSX employee report with departments, salaries, hire dates, and currency formatting.

Extract structured fields from ksef faktura documents.

Extract property, owner, legal description, liens, mortgages, easements, and tax status from title search reports.

Generate an XLSX timesheet with logged hours, hourly rates, per-entry amount formulas, and totals for client billing or payroll.

Extract structured fields from bill of entry documents.

Use after solving a non-trivial bug or making a non-obvious decision, to capture it as durable, searchable documentation so the next session doesn't re-derive it from scratch - and use at the start of related work to check whether that documentation already exists.

n8n Public API skill. Use when working with n8n Public for audit, credentials, executions. Covers 59 endpoints.

Etsy Open API v3 API skill. Use when working with Etsy Open API v3 for application. Covers 103 endpoints.

Asana API skill. Use when working with Asana for access_requests, allocations, attachments. Covers 222 endpoints.

HHS Media Services API skill. Use when working with HHS Media Services for resources.json, resources. Covers 31 endpoints.

RAWG Video Games Database API skill. Use when working with RAWG Video Games Database for creator-roles, creators, developers. Covers 30 endpoints.

ZEIT API skill. Use when working with ZEIT for integrations, domains. Covers 5 endpoints.

Val Town API skill. Use when working with Val Town for alias, me, blob. Covers 36 endpoints.

elmah.io API skill. Use when working with elmah.io for deployments, heartbeats, installations. Covers 24 endpoints.

Loket.nl API skill. Use when working with Loket.nl for providers, automaticpayroll, authorizationmodel. Covers 1087 endpoints.

Render Public API skill. Use when working with Render Public for blueprints, owners, disks. Covers 196 endpoints.

Stytch API skill. Use when working with Stytch for connected_apps, b2b, users. Covers 184 endpoints.

Mistral AI API skill. Use when working with Mistral AI for models, conversations, agents. Covers 71 endpoints.

Braze Endpoints API skill. Use when working with Braze Endpoints for email, campaigns, sends. Covers 68 endpoints.

Files.com API skill. Use when working with Files.com for sessions, action_logs, action_notification_exports. Covers 324 endpoints.

Noosh API application API skill. Use when working with Noosh API application for 1.1. Covers 3 endpoints.

Slack Web API skill. Use when working with Slack Web for admin.apps.approve, admin.apps.approved.list, admin.apps.requests.list. Covers 174 endpoints.

Twitter OpenAPI API skill. Use when working with Twitter OpenAPI for 1.1, 2, graphql. Covers 39 endpoints.

X API v2 API skill. Use when working with X API v2 for 2. Covers 156 endpoints.

Billbee API skill. Use when working with Billbee for api. Covers 87 endpoints.

Docker HUB API skill. Use when working with Docker HUB for users, auth, access-tokens. Covers 54 endpoints.

Auditoria leitora estrita. Compara requirements, roadmap e actions, reporta inconsistências com severidade CRITICAL, HIGH, MEDIUM, LOW. JAMAIS altera os artefatos analisados. Use quando o usuário digitar "/reversa-audit", "reversa-audit" ou pedir para fazer cross-check entre os três documentos da feature ativa. Etapa opcional do ciclo forward.

Retoma uma feature pausada (listada em paused-features de active-requirements.json) e a torna ativa. Use quando o usuário digitar "/reversa-resume", "reversa-resume", "retomar feature pausada" ou pedir para voltar a uma feature anterior. NÃO cria features novas, apenas troca a ativa pela escolhida e (quando faz sentido) move a ativa atual para paused-features.

Orquestrador do pipeline de evolução do Reversa. Detecta o estágio físico da feature ativa em `_reversa_forward/` e sugere o próximo agente do ciclo forward (requirements, clarify, plan, to-do, audit, quality, coding). Use quando o usuário digitar "/reversa-forward", "reversa-forward", "iniciar evolução", "iniciar pipeline forward" ou pedir para conduzir o ciclo de uma feature do zero ao código. Não escreve artefatos de feature por conta própria, apenas roteia.

Cria ou atualiza os princípios duradouros do projeto e propaga sugestões de ajuste nos templates dependentes. Princípios são raros, mudam pouco e influenciam todos os artefatos. Use quando o usuário digitar "/reversa-principles", "reversa-principles", "definir princípios" ou pedir para criar/alterar/aposentar um princípio do projeto. Pode rodar antes mesmo da primeira feature.

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Create GitHub Pull Request for feature request from specification file using pull_request_template.md template.

Redux store wiring for the chota-react-saga template — single createStore, combineReducers per domain, applyMiddleware(sagaMiddleware), composeWithDevTools, and a one-line `sagaMiddleware.run(rootSaga)` at boot. Use when scaffolding the root store or auditing how slices and middleware compose.

Plain-object Redux actions for the chota-react-saga template — three-phase async triples (REQUEST / SUCCESS / ERROR) per CRUD verb, single-phase actions for sync ops, UPPER_SNAKE type constants, and explicit hand-written action creators (no createAsyncThunk).

Redux middleware — the `store => next => action => {}` pipeline for side effects, logging, analytics, and async (thunk/saga). Use when writing custom middleware, wiring async thunks, ordering middleware in configureStore, or keeping side effects out of reducers.

Design product metric trees, North Star metrics, input metrics, and instrumentation needs.

Turn sprint inputs into a kickoff-ready brief with goals, tickets, risks, and team context.

Map product assumptions by risk, confidence, evidence, and next validation step.

Create a slide-by-slide roadmap review structure for planning and leadership conversations.

Build the PRINCE2 Initiating a Project pack: project initiation documentation, business case, project plan, controls, management approaches, product descriptions, and baseline decisions.

Design product experiments around hypotheses, audience, metrics, guardrails, and decisions.

Write product-facing technical specs that clarify decisions, constraints, dependencies, and rollout.

Plan customer discovery conversations with hypotheses, prompts, probes, and capture fields.

You are a data triager that answers data questions by routing them across a network of skills and agents. These questions may involve pulling data from a Snowflake warehouse, computing metrics, locating relevant tables or fields, diagnosing a metric change, or performing exploratory analysis. Your job is to determine how to answer a question and which skills and subagents to invoke.

Use this skill when creating or updating PR descriptions. Provides detailed guidelines for writing clear, comprehensive pull request descriptions with proper Summary and Testing sections.

Querying Google Search Console for search performance — top queries and pages, clicks/impressions/CTR/position over a date range, sitemap status, and URL indexing inspection.

BluOS CLI (blu) for discovery, playback, grouping, and volume.

Control Philips Hue lights and scenes via the OpenHue CLI.

Query Google Places for text search, place details, resolve, reviews, or scriptable JSON via goplaces.

Create, search, and manage Bear notes via grizzly CLI.

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

Search and analyze your own session logs (older/parent conversations) using jq.

Debug Python with pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Use for all ClawSweeper work: MarketingClaw issue/PR sweep reports, commit-review reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.

Use when testing, fixing, or extending the MarketingClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

Add a redacted agent transcript section to GitHub PR or issue bodies during MarketingClaw agent-created PR/issue workflows.

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

QQBot rich media send and receive support. Use <qqmedia> tags only for explicit media send/view requests, treating inbound attachment paths as private current-conversation context.

QQBot scheduled reminders. Use only for explicit user requests to create, list, or cancel one-time or recurring QQ reminders; ask for missing time, content, or timezone before scheduling.