analyze
FreeConvert run artifacts into calibrated interpretation and next decisions.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for baseline-repro. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Read these first:
../../../.agents/references/context-layering-policy.md../../../.agents/references/contract-gating-rule.md../../../.agents/references/pre-training-rule.md../../../.agents/references/run-artifact-contract.md../../../.agents/references/language-policy.md../../../.agents/references/documentation-evidence-rule.md../../../.agents/references/documentation-style.md./references/baseline-report.md../../../PROJECT_STATE.json../../../docs/Refined_Idea.md if it exists../../../docs/30_evidence/Baseline_Table.md if it exists../../../docs/10_contract/Evaluation_Contract.md if it exists../../../docs/10_contract/Baseline_Contract.md if it exists../../../docs/35_protocol/Research_Protocol.md if it existsUse this skill for WF5 when the user wants baselines reproduced fairly before new method implementation.
docs/Refined_Idea.md, docs/30_evidence/Baseline_Table.md, and project state. For legacy projects, fall back to docs/Technical_Spec.md when no refined idea exists.## Environment section in CLAUDE.md.docs/Dataset_Stats.md and project context to align data and evaluation conditions.docs/Baseline_Report.md using the canonical template.docs/30_evidence/Baseline_Table.md as the
human-readable Conclusion Evidence table for baseline repos, papers,
configs, reproduced metrics, logs, and skip reasons.docs/20_facts/Codebase_Map.md exists, keep it synchronized when
baseline directories, scripts, configs, or durable entry points change.PROJECT_STATE.json baseline metricsPROJECT_STATE.json evaluation protocol or tracked metrics for later WF10 comparisonproject_map.json baseline status and entry pointCLAUDE.md environment facts and baseline referencedocs/30_evidence/Baseline_Table.md source-artifact oriented; it is
human-readable Conclusion Evidence, not an .evidence/** Evidence Chain.NOT_RUN with the reason.../../../.agents/references/language-policy.md unless a field is explicitly English-only.$baseline-repro flow.Follow the local prompt, baseline report template, and language policy instead of simplifying the reproduction stage.
temporary drafts.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Convert run artifacts into calibrated interpretation and next decisions.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for auto-paper. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for auto-paper-argument. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for auto-paper-citation. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for auto-paper-data. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.
Internal Harness instruction source for auto-paper-figure. Route through visible Harness aliases instead of invoking directly.
The English summary is being prepared. Showing the original description.