{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=SQMCtZX3trg",
  "slug": "the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b",
  "url": "https://feed7.dev/p/the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b",
  "title": "The Dark Arts of Skill Engineering — Paul Bakaus, Renaissance Geek (Impeccable)",
  "why_included": "Reliable agent skills need more than prompts: use hooks as automatic guardrails, test across models, and compile harness-specific variants when instruction-following differs.",
  "summary": "Impeccable grew from a normalization prompt into a design skill with **two-agent critiques**, scripts and design hooks. Its hooks support Claude Code, Cursor, Codex and GitHub Copilot, while model- and harness-specific builds adjust instructions and tool syntax.",
  "practical_implication": "Treat skills as executable harness components. Put recurring checks into **pre-tool or post-tool hooks**, personalize them with project rules, and test each target model instead of assuming one prompt behaves consistently everywhere.",
  "agent_context": "Impeccable grew from a normalization prompt into a design skill with **two-agent critiques**, scripts and design hooks. Its hooks support Claude Code, Cursor, Codex and GitHub Copilot, while model- and harness-specific builds adjust instructions and tool syntax.\n\nTreat skills as executable harness components. Put recurring checks into **pre-tool or post-tool hooks**, personalize them with project rules, and test each target model instead of assuming one prompt behaves consistently everywhere.\n\nPre-tool blocking may be necessary for weaker instruction followers, but it is more restrictive. Cross-harness packaging also remains fragmented: common installers do not preserve Impeccable's provider-specific directory layout, so it uses a custom CLI.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=SQMCtZX3trg",
    "published_at": "2026-09-21T19:00:10.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "skills",
    "harness-engineering",
    "subagents"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Pre-tool blocking may be necessary for weaker instruction followers, but it is more restrictive. Cross-harness packaging also remains fragmented: common installers do not preserve Impeccable's provider-specific directory layout, so it uses a custom CLI."
  ],
  "connected_context": {
    "meaning": "This sharpens skill engineering from prompt writing into software maintenance: recurring checks can live in hooks, critiques can use multiple agents, and each model or harness may need its own instructions and tool syntax. Portability therefore requires target-specific testing and packaging; stricter pre-tool enforcement may improve compliance but also constrains execution.",
    "corpus_size": 843,
    "generated_at": "2026-09-22T09:08:40.206Z",
    "connections": [
      {
        "title": "On the Maintenance and Co-evolution of Agent Plugins: An Empirical Study of Claude Code Plugin Marketplaces",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.28497v1",
        "feed7_url": "https://feed7.dev/p/2608-28497v1-1mlcj09",
        "reason": "The marketplace study provides ecosystem-scale support for treating skills as evolving software whose instructions and scripts require coordinated maintenance, matching Impeccable’s hooks, scripts, and provider-specific builds."
      },
      {
        "title": "WorldFlowAI/everything-claude-code",
        "source_name": "GitHub",
        "source_url": "https://github.com/WorldFlowAI/everything-claude-code",
        "feed7_url": "https://feed7.dev/p/everything-claude-code-11d9320",
        "reason": "The harness kit demonstrates the same combination of skills, hooks, subagents, rules, and evals, while its context warning reinforces selective adoption rather than enabling every component."
      },
      {
        "title": "Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=32nrHU6zHU8",
        "feed7_url": "https://feed7.dev/p/agents-are-where-microservices-were-in-2015-roberto-milev-uday-kanagala-1pk4hle",
        "reason": "Navan’s independently testable skills and tool-boundary guardrails reinforce Impeccable’s use of hooks and per-target testing, while adding persistence, traces, and trajectory tests as production requirements."
      },
      {
        "title": "Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=zCJtYuqwm7E",
        "feed7_url": "https://feed7.dev/p/coding-agents-don-t-scale-themselves-neither-do-your-teams-patrick-deboi-1tkeyjb",
        "reason": "Impeccable exposes the provider-specific maintenance burden behind shared skills; the team-systems view makes curation, evaluation, and guardrail ownership an organizational consequence of that burden."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-21T19:00:10.000Z",
  "modified_at": "2026-09-21T19:00:10.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b",
    "json": "https://feed7.dev/p/the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b.json",
    "markdown": "https://feed7.dev/p/the-dark-arts-of-skill-engineering-paul-bakaus-renaissance-geek-impeccab-1athv5b.md"
  }
}