formated-results
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced…
Remove components one by one, observe system changes to reveal hidden
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill ablation-brainstorm --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ablation-brainstormContext preview
The summary Claude sees to decide when to auto-load this skill.
Remove components one by one, observe system changes to reveal hidden
name: ablation-brainstorm description: Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps. execution: strategy dependencies: sops: - ablation-execution - dependency-identification - enumeration-synthesis tactics: - coverage-analysis
Systematically remove components from a system one by one, observe what changes, and use the resulting insights to generate novel ideas.
| Resource | Target | Current | % | |----------|--------|---------|---| | web-search | 20 | 0 | 0% | | web-research | 5 | 0 | 0% | | paper-overview | 20 | 0 | 0% | | paper-search | 12 | 0 | 0% | | paper-research | 5 | 0 | 0% |
Cannot exit strategy until ≥80% of each budget line is consumed OR yield targets are met with justification for remaining budget.
| Tactic | Role | |--------|------| | coverage-analysis | Ensure all components are ablated | | evaluation-filtering | Score and filter ablation-derived ideas |
| SOP | Role | |-----|------| | ablation-execution | Remove components one by one, record responses | | dependency-identification | Extract dependency graph from ablation results | | enumeration-synthesis | Synthesize ablation insights into idea report |
1. **Decompose**: List all components of the target system 2. **Ablate**: Run ablation-execution — remove each component, record effects 3. **Analyze**: Run dependency-identification to find critical dependencies 4. **Ideate**: For each critical dependency, ask "what if this were replaced/eliminated/redesigned?" 5. **Filter**: Apply evaluation-filtering to rank generated ideas 6. **Synthesize**: Produce structured report via enumeration-synthesis
<!-- BEGIN available-tables (generated) -->
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use | | --- | --- | | coverage-analysis | Systematic coverage evaluation pipeline — benchmark inventory, method-problem crossing, and intersection evaluation to map explored vs unexplored solution space. |
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | ablation-execution | Remove components one by one from a system, record the response/impact of each removal. | | dependency-identification | Identify critical dependencies from ablation results, producing a dependency graph and highlighting critical components. | | enumeration-synthesis | Synthesize all systematic enumeration outputs into a structured idea report with prioritized recommendations. |
<!-- END available-tables (generated) -->
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced…
Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply.…
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's…
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the…
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to…
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall…