/comparison-executor
Execute a pairwise comparison between two candidates, producing a judgment
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill comparison-executor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/comparison-executor
Context preview
The summary Claude sees to decide when to auto-load this skill.
Execute a pairwise comparison between two candidates, producing a judgment
SKILL.md
comparison-executor.SKILL.mdname: comparison-executor description: Execute a pairwise comparison between two candidates, producing a judgment with winner, confidence, and reasoning. execution: subagent prompt: ./prompt.md input: pair(array), context(object) dependencies: sops: - spawn-agent
Comparison Executor
Executes a single pairwise comparison between two candidates. Produces a structured judgment indicating the winner, confidence level, and detailed reasoning supporting the decision.
Execution
Runs as a subagent. Receives a pair of candidates and evaluation context, returns a judgment.
Why Subagent
Each comparison requires focused deliberation on the specific pair without being influenced by prior ranking expectations. Isolation prevents anchoring bias from the current leaderboard.
HARD-GATE
Output MUST declare exactly one winner from the pair (no ties unless context explicitly permits ties). Confidence MUST be a value in [0.5, 1.0]. Reasoning MUST reference specific attributes of both candidates.
<!-- BEGIN available-tables (generated) -->
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use | | --- | --- | | spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |
<!-- 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
Other skills on de-anthropocentric-research-engine.
- /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 block in your reply. Do not execute the research.
Open skill - /formated-specs
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. Replaces the generic spec-writing step.
Open skill - /injection-fidelity
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 per-axis pressure. Judge enactment of the card, never whether the research is good.
Open skill - /ladder-quality-order
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 harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.
Open skill - /optimization-loop
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 one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the
Open skill - /acu-nugget-recall
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 checks; cannot run without a target summary.
Open skill