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…
Present obstacles with their severity assessments and proposed mitigations
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill ask-obstacle-acceptance --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ask-obstacle-acceptanceContext preview
The summary Claude sees to decide when to auto-load this skill.
Present obstacles with their severity assessments and proposed mitigations
name: ask-obstacle-acceptance description: Present obstacles with their severity assessments and proposed mitigations to the user. Ask whether they can accept these obstacles. If unacceptable after 2 rounds, return to present-candidates. execution: dialogue
Get user's acceptance of the obstacle landscape.
Dialogue — inline, no subagent.
Each obstacle with:
Optional — may use the 5 imported skills if user raises new concerns that need investigation.
Signal to tactic that direction needs to change (return to present-candidates in direction-narrowing tactic).
User's acceptance decision + any new concerns raised.
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…