{
  "markdown": "# TechKnowmad AI Skills\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![Claude Code](https://img.shields.io/badge/Claude_Code-Plugin-orange.svg)](https://github.com/TECHKNOWMAD-LABS/techknowmad-ai-skills)\n[![Skills](https://img.shields.io/badge/Skills-20-green.svg)](#whats-inside)\n\n> **20 enterprise-grade skills for autonomous AI/ML research lab operations.**\n> Custom-built skills + composable combination skills. Designed for [Claude Code](https://docs.claude.com).\n\n## What's Inside\n\n### Custom Skills (10) — Purpose-Built\n\nOriginal skills addressing gaps in the Claude Code ecosystem:\n\n| Skill | What It Does | Priority |\n|-------|-------------|----------|\n| `research-commander` | Full research lifecycle orchestrator — literature review → hypothesis → experiment → paper → submission | P0 |\n| `swarm-commander` | Multi-agent swarm coordination with consensus protocols and result aggregation | P0 |\n| `model-evaluator` | Automated benchmark suite runner with leaderboards and regression detection | P0 |\n| `agent-debugger` | Trace agent decision chains, replay failures, diagnose root causes | P1 |\n| `self-healing-agent` | Autonomous recovery — detect degradation, auto-fix, escalate when needed | P1 |\n| `prompt-evolution` | Genetic algorithm-based prompt optimization across generations | P1 |\n| `skill-factory` | Meta-skill that auto-generates new skills from detected patterns | P1 |\n| `patent-researcher` | AI/ML patent prior art search, claim drafting, FTO analysis | P2 |\n| `cost-optimizer` | Cross-cloud spend analysis, GPU strategies, token cost reduction | P2 |\n| `knowledge-distiller` | Compress large documents into optimal skill prompts | P2 |\n\n### Combination Skills (10) — Composable Pipelines\n\nSkills composed from multiple base skills for compound capabilities:\n\n| Skill | Composes | What It Does |\n|-------|---------|-------------|\n| `multi-agent-research-swarm` | Research Commander + Swarm Commander + arXiv | 10 agents review papers in parallel, synthesize into one review |\n| `red-team-ai-models` | Pen Tester + AI Security + Model Evaluator | Adversarial security testing for your own ML models |\n| `self-evolving-skill-ecosystem` | Skill Factory + Workflow Miner + Telemetry | Skills that create skills that create skills |\n| `academic-output-pipeline` | Research Commander + Paper Writer + Grant Writer | Experiment results → paper → poster → slides → grant proposal |\n| `antifragile-ai-ops` | Chaos Engineer + Self-Healing + Debugger | Break agents, watch them self-recover, learn from it |\n| `pareto-prompt-optimizer` | Prompt Evolution + Model Evaluator + Cost Optimizer | Find Pareto-optimal prompts (accuracy vs cost vs latency) |\n| `zero-touch-ml-pipeline` | Data Pipeline + n8n + Ruflo + Self-Healing | Fully autonomous data → train → deploy → monitor → retrain |\n| `startup-creative-automation` | Brand Architect + fal.ai + Presentation Architect | Brand identity → visual assets → pitch deck in one pipeline |\n| `compliance-as-code` | Compliance Automator + GRC + Audit Support | Continuous SOC2/ISO/GDPR compliance with auto-evidence |\n| `ip-aware-competitive-intel` | Patent Researcher + Literature + Competitive War Room | Patents + papers + products in one competitive landscape view |\n\n## Installation\n\n### As a Claude Plugin\n\n```bash\nclaude plugin add TECHKNOWMAD-LABS/techknowmad-ai-skills\n```\n\n### Quick Install (All Skills)\n\n```bash\nchmod +x scripts/install-techknowmad-skills.sh\n./scripts/install-techknowmad-skills.sh\n```\n\n### Manual Install (Individual Skills)\n\n```bash\n# Copy a single skill\ncp -r custom-skills/research-commander ~/.claude/skills/research-commander\n\n# Or symlink (preserves git updates)\nln -s \"$(pwd)/custom-skills/research-commander\" ~/.claude/skills/research-commander\n```\n\n### Restart Claude Code\n\n```bash\n# Close and reopen Claude Code to load new skills\nclaude\n```\n\n## Prerequisites\n\nThese skills are designed to work with the **TechKnowmad MCP stack**. They reference MCPs like arXiv, fal.ai, Langfuse, Ruflo, etc. Skills will still function without all MCPs installed — they gracefully fall back when a referenced MCP isn't available.\n\n## Repo Structure\n\n```\ntechknowmad-ai-skills/\n├── .claude-plugin/          ← Plugin metadata\n│   ├── plugin.json\n│   └── marketplace.json\n├── custom-skills/           ← 10 original skills\n│   ├── research-commander/SKILL.md\n│   ├── swarm-commander/SKILL.md\n│   ├── model-evaluator/SKILL.md\n│   ├── agent-debugger/SKILL.md\n│   ├── self-healing-agent/SKILL.md\n│   ├── prompt-evolution/SKILL.md\n│   ├── skill-factory/SKILL.md\n│   ├── patent-researcher/SKILL.md\n│   ├── cost-optimizer/SKILL.md\n│   └── knowledge-distiller/SKILL.md\n├── combination-skills/      ← 10 composed skills\n│   ├── multi-agent-research-swarm/SKILL.md\n│   ├── red-team-ai-models/SKILL.md\n│   ├── self-evolving-skill-ecosystem/SKILL.md\n│   ├── academic-output-pipeline/SKILL.md\n│   ├── antifragile-ai-ops/SKILL.md\n│   ├── pareto-prompt-optimizer/SKILL.md\n│   ├── zero-touch-ml-pipeline/SKILL.md\n│   ├── startup-creative-automation/SKILL.md\n│   ├── compliance-as-code/SKILL.md\n│   └── ip-aware-competitive-intel/SKILL.md\n├── scripts/\n│   └── install-techknowmad-skills.sh\n├── manifest.json            ← Skill registry\n├── CONTRIBUTING.md\n├── SECURITY.md\n└── LICENSE\n```\n\n## Why This Exists\n\n**For teams**: A curated, version-controlled skill ecosystem — shareable across team instances, iteratively improvable.\n\n**For the community**: Reference architecture for building a research lab skill stack. These skills represent patterns that don't exist elsewhere:\n\n- Multi-agent research swarms (parallel paper review with consensus synthesis)\n- Self-evolving skill ecosystems (recursive self-improvement)\n- Antifragile AI ops (chaos engineering for agents)\n- Pareto prompt optimization (multi-objective prompt engineering)\n- Zero-touch ML pipelines (fully autonomous model lifecycle)\n\n## Security\n\nSee [SECURITY.md](SECURITY.md) for vulnerability disclosure policy.\n\n## License\n\nMIT — Use, modify, distribute freely. Attribution appreciated.\n\n## Contributing\n\nPRs welcome. Each skill must include:\n\n- `SKILL.md` with Role, Trigger Conditions, and structured instructions\n- Integration points listing required MCPs\n- At least one example invocation\n\n---\n\n*Built by [TechKnowmad AI](https://techknowmad.ai) — Powering autonomous intelligence development.*\n",
  "bytes": 6367,
  "sha": "c8a426b2b845686a4bae322c581d663c81ca7c25735a6fc601b665c9fe83e307",
  "repo_slug": "techknowmad-labs/techknowmad-ai-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_techknowmad_labs_techknowmad_ai_skills_t_c31d86e2/readme"
}