Навыки: Разработка

Professional Graphql Server Expert skill. Build performant, secure, and scalable backend logic and RESTful or GraphQL AP...

Modify GraphQL queries and regenerate types. Use when editing .graphql files, adding fields to queries, or seeing TypeSc...

When the user wants to implement GRASP — multi-start greedy randomized construction with a restricted candidate list fol...

Use for software implementation, debugging, refactoring, review, migration, and other repository-changing engineering wo...

Calculate option Greeks (delta, gamma, theta, vega) and implied volatility for specific options. Use when user asks abou...

Use when reviewing test suites, after test runs pass, or when user asks about test quality - performs exhaustive line-by...

Monitors urban green space coverage changes using NDVI/EVI vegetation indices from multi-temporal remote sensing imagery...

Plan a new frontend project or first vertical slice from a product idea, with approval gates before scaffolding. Exclude...

Bootstrap a new project's Hero workspace with stack-appropriate conventions, decisions, and initial specs.

Agent-assisted text search. Converts natural language intent into explicit, auditable ripgrep parameters and executes de...

Runs the Greptile CLI on the current local branch. Triages every finding against the actual code, fixes what survives, a...

Reference for the Greptile CLI (`greptile`): reviewing a local branch before pushing, reading structured `--json` findin...

Executes natural language codebase queries against indexed repositories via Greptile API. Use when investigating code ar...

Design RESTful APIs following Grey Haven standards - FastAPI routes, Pydantic schemas, HTTP status codes, pagination, fi...

Multi-mode code quality analysis covering security reviews (OWASP Top 10), clarity refactoring (readability rules), and...

Apply Grey Haven Studio's TypeScript/React and Python/FastAPI coding standards from production templates. Use when writi...

Format commit messages according to Grey Haven Studio's actual commitlint configuration (100 char header, lowercase subj...

DevOps and infrastructure troubleshooting for Cloudflare Workers, PlanetScale PostgreSQL, and distributed systems. Use w...

6-phase verification system ensuring code matches documentation with automated alignment scoring (signature, type, behav...

Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture,...

Automate developer onboarding with personalized plans, Linear integration, knowledge base setup, and milestone tracking....

AI-powered intelligent debugging with stack trace analysis, error pattern recognition, and automated fix suggestions. Us...

Master TDD orchestration with multi-agent coordination, strict red-green-refactor enforcement, automated test generation...

Design effective MCP tools and Claude Code integrations using the consolidation principle. Fewer, better-designed tools...

Static-Analyse für GreyScript-Quellen VOR greybel-Build. Erkennt fehlende //command-Marker, nicht-erlaubte Builtins (run...

Get through the brutal logistics after a death — who to notify, what accounts and services to close, in what order, and...

Handle work while grieving — what to tell your manager and team, how much leave you can take, and how to function (or no...

Use when the user wants a plan, design, or PRD stress-tested before any build — relentlessly interrogates one decision a...

Use when the user says 先討論 / wants to align on a fuzzy idea before building, or before any non-trivial implementation wh...

Use when a plan is fuzzy and needs hardening before a spec — decision-tree grilling in frontier rounds, every open decis...

Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, an...

Adversarial review of an existing intent spec. Walk the spec field-by-field and pressure-test the weakest claims before...

Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report...

User-invoked grilling. Use when the user says "grill me", wants to be interviewed on their thesis, or asks to stress-tes...

Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or us...

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the...

Interview the user in batches of 10 questions with recommended answers to sharpen a plan, an idea or an app before build...

Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowle...

Use when someone asks to grill me on this, stress-test this plan or idea, poke holes in this, or make sure I've thought...

Turns a build ask into a confirmed plan file through numbered question rounds, each with a recommended answer, settling...

Use before building anything from a vague request — a feature, an app, an agent, an automation, a page. Trigger when the...

Use when the user brings a task, ticket, or vague intent touching an existing codebase and wants interrogation to shape...

Use when the user asks to grill or stress-test a plan, decision, or idea.

Interview the user relentlessly to stress-test a plan or design before building. Use on any "grill" phrasing.

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, w...

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, o...

Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or us...

Use when work has to keep going with NO session alive — "run this in a loop overnight", "grind loop", "start the loop an...