{
  "id": "skl_alirezarezvani_claude_skills_agent_launc_cb5b0ac6",
  "kind": "skill",
  "category": "ferramentas",
  "name": "grade-iterate",
  "tagline": "Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an i",
  "body": "Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop. Define a CMA outcome (a required markdown rubric graded by an isolated grader), read each verdict, decide the next move (sharpen / re-run / promote to schedule), and once a version passes, run held-back eval cases in parallel. Use when the user says \"grade my agent\", \"make it pass the rubric\", \"iterate until it's good\", \"is it good enough\", or when the orchestrator routes phase=grade-iterate. outcome_builder.py builds the user.define_outcome payload (rubric required, max_iterations clamped 1..20 — never unbounded); verdict_reader.py reads the grader result and recommends the next move; eval_scaffold.py generates held-back cases + a parallel run plan (capped at the 25-thread CMA ceiling). Distinct from stage-launch (first launch) and run-without-you (scheduling).",
  "url": "https://github.com/alirezarezvani/claude-skills/blob/main/agent-launcher/skills/grade-iterate/SKILL.md",
  "status": "live",
  "origin": "directory",
  "origin_id": "alirezarezvani/claude-skills/agent-launcher/skills/grade-iterate",
  "install": "https://raw.githubusercontent.com/alirezarezvani/claude-skills/main/agent-launcher/skills/grade-iterate/SKILL.md",
  "source": "https://github.com/alirezarezvani/claude-skills",
  "transporte": "",
  "ns": "alirezarezvani",
  "versao": "",
  "oficial_status": "",
  "repo_host": "github.com",
  "topico": "files",
  "linguagem": "Python",
  "licenca": "MIT",
  "repo_topics": " agent-plugins agent-skills agentic-ai ai-coding-agent anthropic-claude claude-ai claude-code claude-code-plugins claude-code-skills claude-skills codex-skills coding-agent-plugins cursor-skills developer-tools gemini-cli-skills openai-codex openclaw openclaw-plugins openclaw-skills prompt-engineering ",
  "repo_slug": "alirezarezvani/claude-skills",
  "stars": 25892,
  "forks": 3649,
  "prs_abertos": 11,
  "pushed_at": "2026-08-30T09:46:16Z",
  "repo_estado": "ativo",
  "likes": 0,
  "comments": 0,
  "visits": 0,
  "readme_bytes": 26017,
  "readme_api": "https://agentalog.com/api/listings/skl_alirezarezvani_claude_skills_agent_launc_cb5b0ac6/readme",
  "readme_fonte": "repo",
  "created_at": "2026-08-30 01:59:06",
  "updated_at": "2026-08-30 01:59:06",
  "mine": false,
  "api": "https://agentalog.com/api/listings/skl_alirezarezvani_claude_skills_agent_launc_cb5b0ac6",
  "go": "https://agentalog.com/api/go/skl_alirezarezvani_claude_skills_agent_launc_cb5b0ac6",
  "comments_api": "https://agentalog.com/api/listings/skl_alirezarezvani_claude_skills_agent_launc_cb5b0ac6/comments",
  "readme_sha": "f7a1b881bc5abf370e6eb83eaf1a34488b9595a6464de7613d1ec6207acb8195",
  "readme_em": "2026-08-31 06:31:51",
  "payload": {
    "skill": "grade-iterate",
    "repo": "alirezarezvani/claude-skills",
    "path": "agent-launcher/skills/grade-iterate",
    "commit": "19392f7a08264ed00486a251f5b2098321771f94",
    "provider_declarado": "nginity",
    "categoria": "development",
    "license": "MIT",
    "tipo": "full",
    "manutencao": "active",
    "qualidade": 70,
    "requer_mcp": false
  }
}