{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=7jjudsEhBtM",
  "slug": "skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o",
  "url": "https://feed7.dev/p/skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o",
  "title": "Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet",
  "why_included": "FactSet treats skills as versioned product features and the harness as their runtime. Routing descriptions, model-specific evals, access controls, and governance matter as libraries grow.",
  "summary": "A minimal skill-capable harness needs **a registry, a system prompt, and file reading**; executable skills also need a sandbox. The registry exposes names, descriptions, and paths, while the agent progressively loads only the instructions needed for a task.",
  "practical_implication": "Write descriptions as distinct routing signals tied to user intent, and organize skills around jobs rather than internal data models. Rerun evals after model changes because skills are **contracts versioned to a model**, not passive documentation.",
  "agent_context": "A minimal skill-capable harness needs **a registry, a system prompt, and file reading**; executable skills also need a sandbox. The registry exposes names, descriptions, and paths, while the agent progressively loads only the instructions needed for a task.\n\nWrite descriptions as distinct routing signals tied to user intent, and organize skills around jobs rather than internal data models. Rerun evals after model changes because skills are **contracts versioned to a model**, not passive documentation.\n\nPutting every skill in the prompt stops scaling. The talk suggests shortlisting beyond roughly **10 skills** and adding hierarchy, metadata, ownership, lifecycle rules, audits, and tool allowlists when a library reaches hundreds.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=7jjudsEhBtM",
    "published_at": "2026-07-29T18:00:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "skills",
    "harness-engineering",
    "context-engineering"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Putting every skill in the prompt stops scaling. The talk suggests shortlisting beyond roughly **10 skills** and adding hierarchy, metadata, ownership, lifecycle rules, audits, and tool allowlists when a library reaches hundreds."
  ],
  "connected_context": {
    "meaning": "This turns skills from Markdown conveniences into model-bound product contracts with routing, evaluation, ownership, security, and lifecycle requirements. It confirms progressive loading as the scaling mechanism, while narrowing simple skill-pack approaches: once libraries grow, descriptions must support reliable selection and executable skills require sandboxing, allowlists, audits, and reevaluation after model changes.",
    "corpus_size": 297,
    "generated_at": "2026-07-31T10:07:27.765Z",
    "connections": [
      {
        "title": "affaan-m/ECC",
        "source_name": "GitHub",
        "source_url": "https://github.com/affaan-m/ECC",
        "feed7_url": "https://feed7.dev/p/ecc-0438yju",
        "reason": "ECC’s 261-skill breadth makes the talk’s hierarchy, shortlisting, selective installation, and duplicate-control requirements concrete rather than optional."
      },
      {
        "title": "addyosmani/agent-skills",
        "source_name": "GitHub",
        "source_url": "https://github.com/addyosmani/agent-skills",
        "feed7_url": "https://feed7.dev/p/agent-skills-0d3lx1j",
        "reason": "The portable Markdown pack exemplifies the minimal registry-and-file-loading model, while the talk adds that portability does not remove model-specific evaluation obligations."
      },
      {
        "title": "We Vetted 2000 AI Skills Before They Reached Developers — Lucas Palma, Nubank",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=iKQ78wyJEXU",
        "feed7_url": "https://feed7.dev/p/we-vetted-2000-ai-skills-before-they-reached-developers-lucas-palma-nuba-0k4ehkz",
        "reason": "Nubank’s scanning and marketplace gates implement the supply-chain audits and lifecycle controls required when executable skill libraries expand."
      },
      {
        "title": "WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=8G_1-3IO4ZQ",
        "feed7_url": "https://feed7.dev/p/wtf-is-the-context-layer-the-missing-infrastructure-for-production-agent-0t47xqf",
        "reason": "A shared, versioned context layer offers infrastructure for the metadata and portability this skill-centric harness requires across changing agents."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-07-29T18:00:06.000Z",
  "modified_at": "2026-07-29T18:00:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o",
    "json": "https://feed7.dev/p/skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o.json",
    "markdown": "https://feed7.dev/p/skills-are-new-features-building-skill-centric-harness-yogendra-miraje-f-0lp4c7o.md"
  }
}