“spec-driven development”

Spec-driven 4-phase development process (需求→设计→开发→交付) with structured docs, TDD workflow, gate checks, and knowledge retention.

Use when designing, reviewing, adding, enabling, disabling, installing, configuring, or debugging a plugin, bundle, feature, page, panel, tool, or MCP…

Development environment, building, debugging, testing, Kubernetes deployment, and admin REST API for managing realms, users, clients, LDAP federation…

Use this skill for the legacy `.claude/commands/` file-based slash command format specifically — when the user asks to "create a slash command", "add a…

This skill should be used when the user asks to "analyze a Dockerfile", "optimize Docker layers", "validate docker-compose", "check container best practices"…

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…

Complete senior software engineering workflow playbook.

This skill should be used when the user asks to "optimize Snowflake queries", "analyze Snowflake SQL performance", "size Snowflake warehouses", "review…

Reverse-engineer OpenSpec specs from a repository's git history.

Comprehensive guide for building high-performance Solana programs using Pinocchio - the zero-dependency, zero-copy framework.

Angular framework development, migration, and component generation.

Bootstrap, inspect, repair or upgrade a repository that consumes NewHeap Platform packages.

Build, bootstrap, upgrade, test, debug or review applications that consume NewHeap Platform packages.

Shared MiniApp 小程序 and 面板 development and release workflow for TuyaOpen and TuyaOS, including Ray and 需求 hand-offs, using IDE Agent Tools and Capability Broker.

Use when the user wants to design Codex agent equivalents (specialized workers/profiles/prompt files), define triggering conditions, or build reusable agent…

AI-powered synthetic population simulator with clean architecture, Python type safety, and professional dashboard design patterns

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based…

Use when the user wants to create Codex workflow hooks (pre/post run gates, tool-use validators, stop checks) or needs guidance on hook scripts and hooks.json…

Use when turning a PRD, specification, contract, or acceptance brief into falsifiable requirements, acceptance criteria, verification methods, or…

Use for end-to-end software execution in an unfamiliar or complex repo: orienting the codebase, choosing an execution model, planning and verifying changes…

Use when adding, debugging, or hardening Cloudflare D1 usage in a Workers app.

Run a complete Ralph-style autonomous coding workflow in any git repository: stress-test a plan, create a PRD and prd.json, prepare repository-local handoff…

Use for product strategy and product management work: PRDs, prioritization, roadmaps, discovery summaries, experiment plans, release criteria, decision memos…

Build an automated evaluation pipeline that tests a Python LLM application end-to-end with pixie test — real code paths, real LLM calls, instrumented external…