Search: "anything"

Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity invariants. Use whenever tests should cover a whole input domain instead of a hand-picked list of examples: encode/decode and serialize/deserialize pairs, parsers, canonicalizers and normalizers, validators, numeric and Decimal types, comparators and sort order, data structures, and smart-contract state invariants. Also use when adding cases to an existing @given, fast-check, or proptest suite, when judging whether existing property tests assert anything real, and when a generator has shrunk a counterexample and you need to tell a wrong property from a genuine bug. Not for coverage-guided binary fuzzing (libFuzzer, AFL), mutation-testing campaigns, static analysis, benchmarking, or end-to-end UI tests.

Use for anything related to EAS Observe - adding `expo-observe` to an Expo project (AppMetricsRoot/ObserveRoot HOC, markInteractive and ObserveInteractiveMarker, the useObserve hook, the Expo Router / React Navigation integrations for per-route metrics, user-defined events via `Observe.logEvent`, error reporting via ObserveErrorBoundary and `Observe.reportError`, and runtime config such as sampleRate and dispatchInDebug), querying via the EAS CLI (`eas observe:metrics-summary`, `observe:metrics`, `observe:routes`, `observe:events`, `observe:session`, `observe:versions`), interpreting the resulting metrics (cold/warm launch, TTR, TTI, navigation cold/warm TTR, update download, and the TTI frameRate/device/network params for triaging slow startups), or shipping an Observe integration inside a third-party package.

Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right — should it animate, which thread it runs on, which properties, spring or timing, how the gesture hands off, how it degrades. Writes the implementation with Reanimated, Gesture Handler, Expo Router and expo-haptics. Use when animating anything in an Expo app, adding gestures, sheets, screen transitions, press feedback or haptics, or fixing motion that stutters on device. For web animation use `animate`.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

Reverse engineer anything with agents, from app behavior down to native binaries.

Use this skill when an agency operator wants to draft outreach to partners for a brand: a re-engagement message to a partner who has gone quiet, or a recruitment sequence to a prospective partner. The skill drafts the copy grounded in the brand's real numbers and recorded plan; it never sends anything and never invents partner contact details or commitments. Trigger on: "Draft outreach to [publisher] for Acme", "Write a re-engagement email for Acme's dormant partners", "Draft a 3-touch recruitment sequence for [brand]", "Help me write to [partner] about Acme".

Use this skill to run affiliate-mcp's day-to-day company operations on a schedule in prepare-and-approve mode: gather everything waiting for the operator's approval (across GitHub, Buffer, and Gmail), collect new inbound feedback and headline metrics, and assemble one daily brief. It prepares drafts and surfaces decisions; it never sends, posts, or merges anything itself. Trigger on: "run the daily company brief", "what needs my approval today", "run company ops", "prepare today's operations brief", "daily ops run".

Use this skill to measure the gap between partnerships on the books and partnerships producing anything, on either side of the market. For a publisher: how many programmes they have joined, how many actually earned in a period, and which are dead weight. For an advertiser or agency: how many publishers are on the programme's roster, how many produced a transaction, and how concentrated the revenue is among the few that did. The output is a read-only worklist; it never applies to, leaves, approves, or contacts anyone. Trigger on: "how many programmes have I joined?", "which of my affiliate programmes are dead?", "how many of our publishers actually sell anything?", "which publishers have never produced a sale?", "audit my joined programmes", "dormant programme sweep", "how concentrated is our partner revenue?".

Use this skill to triage inbound customer and user feedback for affiliate-mcp in prepare-and-approve mode: read new and updated GitHub issues and the support inbox, draft grounded replies from the repo's own docs, propose triage labels, and escalate anything ambiguous, tense, or money-related to the operator. It drafts replies and proposes labels; it never posts a public comment or sends an email itself. Trigger on: "triage the support queue", "draft replies to new issues", "any new user feedback?", "handle customer service", "what did users report today?".

Use this skill when a publisher or agency wants to find brands on Awin they have not yet joined and decide which ones to apply to next, ranked by fit. Discovery only: it reads the joinable programmes from the Awin API and produces a prioritised shortlist with reasons. It does not apply to anything. Trigger on: "Which brands should I apply to on Awin?", "Find new programmes to join", "Build my Awin application shortlist", "What programmes can I still join?", "Prioritise brands to apply for".

Operating procedure for Adako, the MCP server and REST API that connects this assistant to the user's Google Ads, Meta Ads, LinkedIn Ads and ChatGPT Ads accounts (TikTok Ads tools are listed but not available yet). Use it whenever the user asks about ad spend, performance, campaigns, ad sets, ad groups, keywords, search terms, audiences, budgets, pixels, creatives, monitors or briefs on those platforms, and whenever they ask to create, pause, resume, re-budget or otherwise change anything in those accounts. It defines the safety contract (read before write, every write becomes a proposal the user approves, created objects are always paused), the tool-call contract (233 tools, read routers for lookups and _write routers for changes, ids are strings, budgets are decimals in the account currency, dates are YYYY-MM-DD or a preset), the tool map per platform, and the standard workflows for performance reviews, wasted-spend cleanup, campaign launches, monitors, approvals and error recovery. Do not use it for platforms Adako does not cover.