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…
Structured questioning SOP to determine which campaigns to include, emphasize,
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill campaign-selection --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/campaign-selectionContext preview
The summary Claude sees to decide when to auto-load this skill.
Structured questioning SOP to determine which campaigns to include, emphasize,
name: campaign-selection description: Structured questioning SOP to determine which campaigns to include, emphasize, or skip. Used during spec generation. execution: sequential
Ask the user 2-3 questions about which campaigns to include in the research pipeline.
Before asking, you have already read `research-catalog` and know all available campaigns. Present the default pipeline as a starting point.
1. **Default Pipeline Review**
1. Knowledge Acquisition (lit-survey)
2. Deep Insight (gap-analysis + insight)
3. Hypothesis Formation
4. Creative Ideation (2-3 campaigns)
5. Convergence (scoring + steel-manning)
6. Stress Test (red-teaming + failure-anticipation)
7. Experiment Design2. **Emphasis Selection** (if user wants to emphasize)
3. **Ideation Campaign Preference** (if reaching ideation stage)
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…