{"agent":"ionwarp","title":"IonWarp Docs","marketplace_url":"https://ionwarp.com/docs/skills/marketplace.json","version_contract":"`version` is the sha256 of the whole SKILL.md file and equals the platform catalog's executed_hash — the bytes published here are the bytes the platform executes. Cache on it: same version, no refetch. It does NOT prove that any agent has actually refreshed its own copy.","skills":[{"id":"skill.review-study","name":"review-study","description":"Daily quality grading for IonWarp's PR reviews. The head-to-head half (§0) is the point of the skill: pick ONE real PR where at least two review bots commented, read what each bot ACTUALLY WROTE, and grade them head-to-head against our own rubric — judging false positives and MISSED bugs, which no counter can see. §1-§5 add the fleet reliability strip (n, err%, latency, cost) from reviewers_telemetry. Never uses IonWarp's own self-grade as a quality verdict — that number counts findings, and volume is not quality. Read-only — never launches reviews, never writes pins, never posts to GitHub.","category":"analytics","docs_url":"https://ionwarp.com/docs/skills/review-study","distribution":"public","version":"ab09994926110824922e02c9841363d3731ee936f481299e095361bbc8ad4e93","zip_url":"https://ionwarp.com/docs/skills/review-study-ab0999492611.zip","skill_url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/SKILL.md","files":[{"path":"references/grading-rubric.md","bytes":5044,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/references/grading-rubric.md"},{"path":"references/judge_call.py","bytes":7705,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/references/judge_call.py"},{"path":"references/render_digest.py","bytes":11268,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/references/render_digest.py"},{"path":"references/validate_snapshot.py","bytes":17583,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/references/validate_snapshot.py"},{"path":"SKILL.md","bytes":40910,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/review-study/SKILL.md"}]},{"id":"skill.reviewer-model-lab","name":"reviewer-model-lab","description":"The IonWarp reviewer model lab. Per run: at most TWO trials against the newest review-study snapshot — trial 1 chases an open lead (or grading's top recommendation), trial 2 is one web-researched frontier candidate confirmed on OpenRouter. REPORT ONLY: it measures and recommends, and NEVER changes a pin — a model switch is an operator decision, proposed in the digest with its evidence.","category":"model-lab","docs_url":"https://ionwarp.com/docs/skills/reviewer-model-lab","distribution":"public","version":"a1fb433f3d0d5f849e25a323db4b80c563bb8e539cb1b1d05e8a8b2628450974","zip_url":"https://ionwarp.com/docs/skills/reviewer-model-lab-a1fb433f3d0d.zip","skill_url":"https://ionwarp.com/docs/raw/skills/ionwarp/reviewer-model-lab/SKILL.md","files":[{"path":"references/candidates.json","bytes":8099,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/reviewer-model-lab/references/candidates.json"},{"path":"SKILL.md","bytes":55119,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/reviewer-model-lab/SKILL.md"}]},{"id":"skill.scorecard-model-lab","name":"scorecard-model-lab","description":"The IonWarp scorecard lab — one run across the configured projects: ≤2 refresh slots (never-run > restore > stale > top-up) on the resolved pin, then ≤1 model trial against a ≤7-day committed baseline. A scan counts only when its projection COMMITTED. REPORT ONLY — it proposes pin changes with their evidence and never writes one; a paused project is never unblocked.","category":"model-lab","docs_url":"https://ionwarp.com/docs/skills/scorecard-model-lab","distribution":"public","version":"ad761a3595b376158bd76627373e45a50a6680b9ed555b4c2ee90992037d8f6a","zip_url":"https://ionwarp.com/docs/skills/scorecard-model-lab-ad761a3595b3.zip","skill_url":"https://ionwarp.com/docs/raw/skills/ionwarp/scorecard-model-lab/SKILL.md","files":[{"path":"SKILL.md","bytes":35111,"url":"https://ionwarp.com/docs/raw/skills/ionwarp/scorecard-model-lab/SKILL.md"}]}]}