baseline-synthesis
Baseline Synthesis consolidates all outputs from a baseline establishment campaign into a single structured report that integrates method inventories, performance tables, condition analyses, discrepancies, and progress curves. Use this skill after completing all prior analysis strategies to generate an actionable baseline document that summarizes the methodological landscape, performance standings, reliability assessments, progress trajectories, and strategic recommendations for a research domain.
git clone --depth 1 https://github.com/yogsoth-ai/de-anthropocentric-research-engine /tmp/baseline-synthesis && cp -r /tmp/baseline-synthesis/skills/baseline-synthesis ~/.claude/skills/baseline-synthesisSKILL.md
# Baseline Synthesis
## Purpose
Synthesize all outputs from the baseline establishment campaign into a single coherent report. Integrates method inventory, performance tables, condition analysis, discrepancy findings, and progress curves into an actionable baseline document.
## Input Schema
| Field | Type | Description |
|-------|------|-------------|
| all_analysis_results | object | Combined outputs from all prior strategies and SOPs |
## Output Schema
```json
{
"report": {
"title": "string",
"task": "string",
"domain": "string",
"date_generated": "string",
"summary": "string"
},
"method_landscape": {
"total_methods": 0,
"method_families": [{"name": "string", "count": 0, "era": "string"}],
"active_methods": 0,
"deprecated_methods": 0
},
"performance_summary": {
"primary_table": {},
"sota": {"method": "string", "score": 0.0, "date": "string"},
"fair_sota": {"method": "string", "score": 0.0, "conditions": "string"},
"pareto_optimal": []
},
"reliability_assessment": {
"high_confidence_baselines": ["string"],
"questionable_baselines": ["string"],
"known_discrepancies": []
},
"progress_assessment": {
"current_status": "saturating|active_progress|early_stage",
"annual_rate": 0.0,
"headroom_remaining": 0.0,
"next_breakthrough_needed": "string"
},
"actionable_insights": [
{
"finding": "string",
"implication": "string",
"recommendation": "string"
}
]
}
```Experiment-specific - summarize the DARE executor's research design into a clean research_result report, forced to write back into the spec file produced by formated-specs.
Experiment-specific - replaces writing-specs, emits DARE's 4-layer call plan as a clean research_graph schema. Last step forces load formated-result.
loss-1 judge - read a sample's full dialogue and decide whether the user simulator semantically enacted its Policy Card. check-blind.
loss-2 judge - pairwise quality comparison across the n rungs within one topic; decide monotonicity and endpoint separation. check-blind, D1-D5 only.
Strategy: 面对异常的最佳解释推理
Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.
Map system architecture to ablatable units for ablation studies
Design ablation studies to isolate component contributions in ML systems