qiyuey/harness-skills
Generic LLM workflow harness methodology skills (Claude Code / Codex): audit, fix, and extend multi-step agent workflows for resumability, programmatic QC, observability, and failure contracts.
Generic LLM workflow harness methodology skills (Claude Code / Codex): audit, fix, and extend multi-step agent workflows for resumability, programmatic QC, observability, and failure contracts.
npx skills add qiyuey/harness-skillsGeneric LLM workflow harness methodology skills (Claude Code / Codex): audit, fix, and extend multi-step agent workflows for resumability, programmatic QC, observability, and failure contracts.
Recently updated GitHub repository for AI agent skills and workflows: 13097266080/agent-skills-pack.
Open-source local Agent orchestration for self-improving agent teams: run agents, review work, and turn feedback into reusable skills.
Simplify complex browser automation by enabling AI to control multi-step tasks without snapshot and action loops for reliable workflows.
Python configuration management via environment variables and typed settings. Use when externalizing config, setting up pydantic-settings, managing secrets, or implementing environment-specific behavior.
Automation of SDLC agent using Claude, LangGraph, LangChain, Python FastMCP, Fast API
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".