Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHAN — from…
Post-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHAN — from…
Understand and work with mortgage document types and classification. Use when asking about document types, adding new document support, debugging classification, or understanding…
Use when documentation drift is detected. Comprehensively audits codebase and creates/updates Swagger, features docs, and general documentation to achieve full sync.
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides.
.NET AI integration with Microsoft.Extensions.AI, Semantic Kernel, MCP servers, embeddings, vector search, and agent frameworks
Simulates command execution in dry-run mode without file modifications. Sets dry_run flag, executes command with read-only constraint, then resets flag.
Write end-to-end tests with Symfony Panther 2.4 for browser automation or Playwright for complex scenarios
Reviews spec implementation with E2E visual browser validation via Playwright. Triggers on keywords: e2e review, visual review, spec review, browser validation
Template generator for E2E test definitions. Creates structured test files for use with test-e2e skill. Triggers on keywords: e2e template, test template, create test definition
Execute end-to-end tests for Nikita using Telegram MCP, Gmail MCP, Supabase MCP, Chrome DevTools MCP, and gcloud CLI.
Generate e2e tests from spec or code analysis with accessibility-first locators and POM conventions.
Use when testing Effect code including Effect.gen in tests, test layers, mocking services, and testing error scenarios. Use for writing tests for Effect applications.
Intent-based code interpretation across all languages — SQL, Python, JS, YAML, Bash, and beyond
Production Stage 3 — takes a saved eng-flow spec and domain model and produces the technical design — tech stack, a tech-labeled system diagram, API contracts, quantified…
Production Stage 6 — reviews an implemented diff (branch vs. base, or a specific story's commits) across five axes before it ships.
Production Stage 2 — takes a saved eng-flow spec and turns its named domains into a domain model, data flows, and a conceptual system diagram.
Production Stage 3.5 — reviews a saved architecture.md against engineering-leadership judgment before it becomes epics/stories/tasks.
Production Stage 4 — turns a spec's domains and journeys, cross-checked against the architecture's system diagram, into epics and stories in a project-level backlog (not per-spec…
Production Stage 8, terminal — ships a feature branch. Gate-checks Stage 6/7 verdicts (code-review.md, qa-report.md) instead of re-reviewing, merges base before a final regression…
Inteligência de workflow para o agente axehub-harness — classifica solicitações em feature/bugfix/refactor/pesquisa e executa o fluxo correto de planejamento e delegação
Batch-enrich astrolabe index cards. Use when the user asks to enrich, classify, or describe documents in the astrolabe index, or when list_docs(stale=true) shows unenriched cards.
GLAW Entity Architect — the firm's dedicated corporate-structuring specialist that designs the entity stack and feeds /glaw-structure.
Cria e gerencia Enums PHP 8.1+ com archtechx/enums e suas 7 traits helpers. Use quando precisar criar enums, adicionar traits de enum, ou trabalhar com enums tipados em L — from…
Cria e gerencia Enums PHP 8.1+ com archtechx/enums e suas 7 traits helpers. Use quando precisar criar enums, adicionar traits de enum, ou trabalhar com enums tipados em Laravel.
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical…
Expert in error handling, Error Boundaries, Sentry integration, logging strategies, error recovery, user-friendly error UI, and debugging tools
Apply rapport-based elicitation to resistant or semi-cooperative humans and agents. Use when coercive prompting or brittle handoffs damage cooperation.
Cria exceções customizadas renderable e reportable para HTTP e logging em Laravel. Use quando precisar criar exception handlers, exceções de domínio, ou melhorar o tratamento de…
Arquitecto de Software Senior autónomo. Se activa automáticamente para: decisiones técnicas, validación de código, corrección de errores, elección de frameworks, arquitectura,…
Use Codex and Gemini CLIs as external reviewers for gated review chunks. They read prompt files and write reports.
Use when FastAPI async patterns for building high-performance APIs. Use when handling concurrent requests and async operations.
Use when FastAPI validation with Pydantic models. Use when building type-safe APIs with robust request/response validation.
Fetch unresolved PR review comments using GitHub GraphQL API, filtering out resolved and outdated feedback.
Find all CPython internal headers and structs used in the codebase, particularly for profiling functionality.
An end-to-end method for drafting and finalising a complex, multi-pillar regulated fintech agreement — from intake to signature.
Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language prompts or code.
Write Fish shell functions in idiomatic fish syntax with delightful UX. Use when (1) Creating new Fish functions, (2) Refactoring or improving existing functions, (3) Adding…
Flask API development including blueprints, extensions, and REST patterns. Activate for Flask apps, Python web APIs, and lightweight API development.
Expert-level Flask web development, REST APIs, extensions, and production deployment
Workflow-backed Jarvis control panel. Runs the deterministic `hangar` workflow with verb=needs (discover → enrich → prioritize), renders the Jarvis HUD from its render-ready…
发布后文档更新。读取所有项目文档，与 diff 交叉对照， 更新 README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md 使之匹配已发布内容， 润色 CHANGELOG 语气，清理 TODOS，可选地更新 VERSION。
QA 验收与测试报告。纯验收模式：测试+报告，不修代码。 两种调用模式： Mode A（完整 QA）：test-spec 生成 → 10 维度 Playwright 断言引擎 → 智能分析。 Mode B（单 bug 修复回归）：配合 forge-bugfix 的 P6 调用，读取 docs/bugfix/reviews/BF-XX.md， 针对 Bug…
Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client checks, config…
Restrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path.
Lightweight web fuzzing via ffuf — directory discovery, parameter testing, subdomain enumeration.
Foreign exchange exposure analysis and hedging strategy skill with hedge effectiveness testing
Review a plan thoroughly before implementation. Challenges scope, reviews architecture/code quality/tests/performance, and walks through issues interactively with opinionated…
GCP-specific infrastructure and services expertise for cloud operations and architecture
Sets up and configures Google Kubernetes Engine (GKE) clusters for production use. Use when creating new GKE clusters, choosing between Autopilot vs Standard modes, configuring…
Configures comprehensive logging, metrics, distributed tracing, and alerting for GKE applications. Use when setting up Cloud Logging, creating dashboards in Cloud Monitoring,…
Systematically diagnoses and resolves common GKE issues including pod failures, networking problems, database connection errors, and Pub/Sub issues.
Implements Workload Identity for secure, keyless authentication between GKE pods and Google Cloud services.
Interactive GCP Cloud Build + Cloud Run setup. Provisions APIs, AR, SAs, IAM, secrets, and triggers.
Run gdUnit4 tests for Godot projects. Use after implementing features, fixing bugs, or modifying GDScript files. USE PROACTIVELY to verify code changes. — from engineering/testing
Work with Gemini File API for document caching and efficient multi-query workflows. Use when discussing file uploads, caching strategies, token optimization, or comparing File API…
Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI.
Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI.
Helpt bij het ontwerpen en bouwen van applicaties volgens de GEMMA referentiearchitectuur, Common Ground principes en het Gemeentelijk Gegevensmodel (GGM) voor Nederlandse…
Provides comprehensive code review feedback based on best practices, style guides, and potential bug detection.