Audits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or human-authored plan, design proposal, implementation outline, task breakdown, or architecture plan and the user wants a standalone audit report without overwriting the source plan.
npx skills add https://github.com/b-mendoza/agent-skills/tree/main/skills/validate-implementation-planAudits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or human-authored plan, design proposal, implementation outline, task breakdown, or architecture plan and the user wants a standalone audit report without overwriting the source plan.
Practitioner-judgment skill for Claude Code, Codex, and AI agents under ambiguity, trade-offs, and incomplete information.
Harness for DeepSeek V4-Pro / V4-Flash. Python lib (pip install deepseek-harness) + dsh CLI + MCP server (npx @deepseek-harness/mcp) + Anthropic SKILL.md. 16 documented protocol quirks, 12 probes, 270+ trials.
Codex skill for polishing frontend UI, responsive behavior, interaction states, and production-grade implementation
Provide adaptive Claude Code skills that guide system design, coding, and task management through principle-based decision frameworks.
UnoCSS instant atomic CSS engine, superset of Tailwind CSS. Use when configuring UnoCSS, writing utility rules, shortcuts, or working with presets like Wind, Icons, Attributify.
Claude Code / Codex / AI configs for the expert Solana builder. CLAUDE.md, agents, commands, hooks, rules, skills and settings across Web, Anchor, Pinnochio, Unity, Mobile, security and more.