Loading...
Loading...
Found 97 Skills
Guide spec-driven feature development using a structured three-phase workflow: Requirements → Design → Tasks. Use this skill whenever the user wants to plan a feature, write a spec, or do structured design before coding. Trigger on phrases like "let's spec this out", "write a specification" or "help me think through this feature".
Use when the user wants to set up spec-driven development (OpenSpec + superpowers-bridge) in a project, or when initializing a new project that needs the SDD workflow. Idempotent. Runs the bundled scripts/run.sh.
Guide spec-driven development using collaborative interrogation and iterative Q&A to build production-ready specifications. Use when the user wants to build specifications, plan features, gather requirements, create technical blueprints, or asks about spec-driven development, requirements gathering, feature planning, or specification writing.
Use this when planning new features, starting spec-driven development workflows, or when the user mentions OpenSpec, SDD, or spec-driven development. It also applies when the user asks about feature specifications, change proposals, or wants to organize development workflows.
A skill that implements the SDD-RIPER methodology into strictly executable processes. It is applied in code/architecture tasks for "function-level and project-level CodeMap generation, full-modal requirement context bundling, Spec-driven R&D, and RIPER phase gate advancement", and is suitable for multi-round collaborative development with Claude/Codex/other CLI Agents.
Creates project constitution files (CLAUDE.md/AGENTS.md) that serve as always-loaded context for coding agents. Use when setting up a new project for spec-driven development, configuring agent instructions, writing CLAUDE.md or AGENTS.md, or establishing project-wide coding standards and constraints.
Extract formal spec and comprehensive test suites from existing MoonBit implementations. Use when asked to "extract spec from implementation", "generate tests from code", or "create spec-driven tests for existing package". Analyzes existing code to produce spec.mbt with `declare` keyword stubs and organized test files (valid/invalid).
Creates agent-optimized technical design documents with context-layer-aware progressive disclosure for architecture decisions, component design, and data models. Use when writing technical designs, architecture docs, defining system components, or making technology choices for spec-driven development.
Initialize the .specify/ directory structure for Spec-Driven Development in the current project
Spec-driven development pipeline orchestrator. Given a URL or text description, automatically generates specs, implements code, runs codex review, applies security gate, executes tests, syncs docs, and notifies via Telegram. Triggers on: /start-workflow, start workflow, build feature, implement feature, spec-driven, start pipeline.
Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the user mentions "loop factory", a "spec-driven loop", an "agent factory", wants repeatable/reviewable agent work, or when a repo has a factory/specs/inbox or factory/specs/active directory. Also covers installing and scaffolding the loop-factory CLI into a project.
DEPRECATED - Use chatkit-backend skill instead. SSE streaming is now part of the chatkit-backend skill for ChatKit integration.