MCP App StoreMCP App StoreThis skill guides the user through a structured specification process: a mandatory six-question Step 0 gate, a clarifying requirements interview, complexity tiering, CVA analysis (when relevant), and generation of durable PRD artifacts (REQ/DESIGN/TASK). It produces verifiable, EARS-style acceptance criteria ready for engineering work.
Use when you need to transform a problem, ticket, or idea into a formal, testable requirements document before implementation — e.g., preparing a PRD, splitting work for engineers, or validating scope with stakeholders. It is blocking for cases that require clear demand/signal evidence (Step 0).
This is a monolithic 63K-char SKILL.md that transforms problem statements into testable requirements with acceptance criteria. It implements a rigorous multi-step process (Steps 0–9+) with gate logic, hedge-phrase detection, tier classification, and references to multiple sub-skills (threat-modeling, slo-designer, adr-generator, etc.). No scripts to run. The instructions are exceptionally detailed and precise, but the entire skill is one massive file with no separation into scripts/ or references/. It references external sub-skills and files like @CLAUDE.md that won't exist outside its original repo, making it non-portable.
Security is clean — pure instruction document, no code execution. The skill is well-thought-out and comprehensive for its original context (rjmurillo/ai-agents repo with Claude/Copilot), but severely lacks architectural separation. A 63K SKILL.md defeats the purpose of progressive disclosure. The skill is deeply coupled to its home repo's sub-skill ecosystem and won't work standalone. Usefulness is limited to teams using that specific multi-skill setup.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
GraphQL Inspector — Validate
Validate GraphQL operations against a schema with configurable depth, complexity, alias and directive limits to catch errors before runtime.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
WeChat MP Article Writer & Publisher
End-to-end toolchain for drafting, rendering, validating and publishing WeChat Official Account articles using templates, image planning and pipeline scripts.
API and Interface Design
Guides design of stable, predictable APIs and interfaces — contract-first patterns, error semantics, pagination, and naming conventions for robust integrations.
