В каталоге 185 367 навыков в 14 категориях.
Design RESTful APIs following Grey Haven standards - FastAPI routes, Pydantic schemas, HTTP status codes, pagination, fi...
Grey Haven's authentication patterns using better-auth - magic links, passkeys, OAuth providers, session management with...
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...
Multi-agent workflow orchestration with state persistence, handoff patterns, and resumable workflows. Use when building...
Professional writing assistance for blogs, research articles, fiction, essays, and marketing copy. Use when users want t...
Design database schemas for Grey Haven multi-tenant SaaS - SQLModel models, Drizzle schema, multi-tenant isolation with...
Comprehensive data validation using Pydantic v2 with data quality monitoring and schema alignment for PlanetScale Postgr...
Apply Grey Haven database conventions - snake_case fields, multi-tenant with tenant_id and RLS, proper indexing, migrati...
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...
Comprehensive documentation systems design including structure, generation, maintenance, and automation. Use when design...
Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essent...
Handle production incidents with SRE best practices including detection, investigation, mitigation, recovery, and postmo...
Grey Haven's Linear issue workflow - creating well-documented issues, proper branch naming from issue IDs, commit messag...
Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture,...
Identify memory leaks, inefficient allocations, and optimization opportunities in JavaScript/TypeScript and Python appli...
Design and implement long-term memory systems for AI agents using vector stores, knowledge graphs, and hybrid approaches...
Production-ready monitoring, logging, and tracing using Prometheus, Grafana, OpenTelemetry, DataDog, and Sentry. Use whe...
Implement observability and monitoring using Cloudflare Workers Analytics, wrangler tail for logs, and health checks. Us...
Automate developer onboarding with personalized plans, Linear integration, knowledge base setup, and milestone tracking....
Create comprehensive ontological documentation for Grey Haven systems - extract domain concepts from TanStack Start and...
Comprehensive performance analysis and optimization for algorithms (O(n²)→O(n)), databases (N+1 queries, indexes), React...
Generate pull request descriptions following Grey Haven Studio standards with clear summary, motivation, implementation...
Generate production-ready project scaffolds for Grey Haven stack with Cloudflare Workers, React + TypeScript, Python + P...
Organize Grey Haven projects following standard structures for TanStack Start (frontend) and FastAPI (backend). Use when...
Master 26 documented prompt engineering principles for crafting effective LLM prompts with 400%+ quality improvement. In...
Specialized testing for React applications using TanStack ecosystem (Query, Router, Table, Form) with Vite and Vitest. U...
Comprehensive security analysis with vulnerability detection, OWASP Top 10 compliance, penetration testing simulation, a...
Grey Haven's security best practices - input validation, output sanitization, multi-tenant RLS, secret management with D...
Guide for creating effective skills that extend Claude's capabilities. Use when users want to create a new skill, update...
AI-powered intelligent debugging with stack trace analysis, error pattern recognition, and automated fix suggestions. Us...
Apply Grey Haven's TanStack ecosystem patterns - Router file-based routing, Query data fetching with staleTime, and Star...
Master TDD orchestration with multi-agent coordination, strict red-green-refactor enforcement, automated test generation...
Python Test-Driven Development expertise with pytest, strict red-green-refactor methodology, FastAPI testing patterns, a...
TypeScript/JavaScript Test-Driven Development with Vitest, strict red-green-refactor methodology, React component testin...
Comprehensive test suite generation with unit tests, integration tests, edge cases, and error handling. Use when generat...
Grey Haven's comprehensive testing strategy - Vitest unit/integration/e2e for TypeScript, pytest markers for Python, >80...
Design effective MCP tools and Claude Code integrations using the consolidation principle. Fewer, better-designed tools...
GreyCat full-stack development for graph-based language with built-in persistence and MCP server capability. CRITICAL WO...
GreyCat C API and GCL Standard Library reference. Use for: (1) Native C development with gc_machine_t context, tensors,...
GreyNoise API reference. Internet scanner/noise classification for IPs.
Static-Analyse für GreyScript-Quellen VOR greybel-Build. Erkennt fehlende //command-Marker, nicht-erlaubte Builtins (run...
When the user wants to design, optimize, or audit grid layouts for content display. Also use when the user mentions "gri...
Deprecated compatibility entry for Grid construction. This component is now maintained in Bricks; install and use compon...
A square in a grid says what it is in a tooltip, and gets a hover card only where it offers more than one thing to do. A...
CEO. Turns a business goal into sequenced initiatives and bets, makes the build-vs-not call, sets guardrails and budgets...
Growth Hacker. Acquisition and funnel experiments, analytics-driven growth, one variable at a time; leads the marketing...
Explain how to use the-grid (which slash command or subagent to reach for, orchestrators vs specialists, the four factor...
Tech Lead. PRDs, architecture decisions, handing off to specialists and reviewing their output. Use to coordinate a mult...
Use when writing a profit-laddered position-adjustment strategy on Superior Trade — anything described as a grid bot, ra...
Headless spreadsheets with GridCraft (XLSX/CSV/TSV workbooks, formula evaluation, recalculation, PDF export), provisione...
Interpretive guidance for generating OpenSCAD code for Gridfinity desktop/drawer organizers. Provides pattern selection...
Use when creating, redesigning, or reviewing web interfaces that need product-specific structure, clear hierarchy, respo...
This skill should be used when the user asks to "get electricity data", "query grid data", "get LMP prices", "fetch load...
Get through the brutal logistics after a death — who to notify, what accounts and services to close, in what order, and...
Compassionate bereavement support, memorial creation, grief education, and healing journey guidance. Specializes in unde...
Write Go code in the style of Robert Griesemer, co-creator of Go. Emphasizes clean syntax, precise semantics, and well-d...
Read a grievance capture from sector-unity-proto — the F9 debug key that records what the screen actually showed when so...
Handle work while grieving — what to tell your manager and team, how much leave you can take, and how to function (or no...
Trigger: grill me, grill with docs, grill me sdd, grill code, grill docs open, entrevistame, entrevistame sdd. Relentles...
Comprehensive implementation auditor that grills code quality, plugin structure, consistency, and identifies problems. U...
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or u...
Use when a technical writeup, blog post, war story, or "Show HN" is about to go to Hacker News, Lobsters, or any skeptic...
Read-only pre-design interview that surfaces tacit intent before planning. Use on explicit request, or before design whe...
Cut one REALIZED slice into user-testable delivery epics — the handoff from the product model to the delivery pipeline....
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...
Structured questioning to reach shared understanding before action. Walks the decision tree one branch at a time, checks...
Use when a plan is fuzzy and needs hardening before a spec — decision-tree grilling in frontier rounds, every open decis...
分轮追问用户的计划、决定或想法,直到重要未知暴露出来,再动手执行。适用于任何领域,不限于写代码。当用户想理清思路、给想法做压力测试,或者说出这些话时使用:拷打我、追问我、帮我想清楚、帮我理一理、挑挑毛病、有什么没想到的、grill me、s...
Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, an...
Grill the user relentlessly about a plan, decision, or idea to stress-test their thinking. Trigger on:- grill, grill me,...
Use when the user says "brainstorm", "grill me", or "think this through", or a feature lacks a product decision the repo...
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observab...
Grill CURRENT and accepted ADRs for staleness, contradiction, and missing decisions. Use when asked to audit the brain,...
Interview unsettled decisions before writing product or architecture docs.
Review the open tasks of a Kairos initiative as a set before a Ralph loop runs them — slice boundaries, order and risk,...
Converge on a frontend look through rounds of prototypes and grilling verdicts. Use when the user wants to iterate on UI...
Grill the user about a plan (same interview as grilling) and record it — Q→A transcript in grills/, each decision append...
A relentless interview that sharpens a Kairos initiative (or a strategy) and writes each settled answer into the item at...
Adversarial review of an existing intent spec. Walk the spec field-by-field and pressure-test the weakest claims before...
Broad Jev interrogation: generate up to 50 context-specific questions about a plan, spec, design, code artifact, or any...
Hub CLARIFY Phase 0 for BACK|FRONT|INTEG PLAN/CLARIFY — framing grill + frontier interview via grilling primitive. Read...
Use when the user wants an elicitative interview — reaching alignment on a plan, decision, or idea by drawing out their...
A relentless interview to sharpen a plan or design. Use when the user wants a plan or design stress-tested. Triggers on:...
This skill should be used when user ask to "interview me".
Iteratively grill users to clarify vague requirements via layered questioning. Use when requirements are ambiguous, inco...
Stress-test a plan, decision, or idea through a structured interview. Use when the user asks to be grilled or wants rele...
Prompt me with questions, one at a time, until we have a shared understanding. Use this skill when a decision, plan, or...
ユーザーの計画・考えを徹底的に grill し、共通認識を構築するスキル
一场无休止的盘问,用来打磨你的计划或设计。
Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report...
Interview the user relentlessly about a plan, design, or idea until reaching shared understanding, resolving each branch...
A relentless interview to sharpen a plan or design.
针对方案或设计的高强度追问式面试(adversarial design review / grill session),暴露假设漏洞与缺失约束,过程中同步维护领域模型(术语表和 ADR)。手动调用 /grill-me。
仅当用户显式调用 `$grill-me`,或明确要求"追问我""挑战这个方案""拷打这个设计"时使用。通过高强度逐问逐答检验方案,并同步沉淀术语表和 ADR。不要因普通设计讨论自动触发。
A relentless interview to sharpen a plan or design. Use before committing to an approach, or on any 'grill me' trigger p...
User-invoked grilling. Use when the user says "grill me", wants to be interviewed on their thesis, or asks to stress-tes...