AI Agent Skills

🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码：架构、Agent 循环、上下文工程、工具系统等

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove th…

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task wi…

Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, polar chart (polar/radial l…

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents ne…

Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the…

Fact-checks OpenSpec user documentation with a fresh-context subagent that re-runs commands and checks claims against source. Manually triggered; not part of the draftin…

FLOW framework integration: evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts…

Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomo…

Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions…

Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.

Mermaid diagrams (.mmd) from natural language with validation loop. 11+ types, multi-backend (mmdc / Kroki), PNG/SVG/PDF, multi-agent.

Architecture-first skill lifecycle for AI agents. 6 modes: CREATE / IMPROVE / VALIDATE / REVIEW / OPTIMIZE / PACKAGE. BinEval binary scoring with threshold-blind, cross-…