跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

vibe

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

th3vib3coder · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add th3vib3coder/vibe-science --skill vibe

技能说明


name: vibe description: Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved. license: Apache-2.0 metadata: version: "4.5.0" codename: "ARBOR VITAE (Pruned)" skill-author: th3vib3coder architecture: OTAE-Tree (Observe-Think-Act-Evaluate inside Tree Search) lineage: "v3.5 TERTIUM DATUR → v4.0 ARBOR VITAE → v4.5 ARBOR VITAE (Pruned)" sources: Ralph, GSD, BMAD, Codex unrolled loop, Anthropic bio-research, ChatGPT Spec Kit, Sakana AI-Scientist-v2 (arXiv:2504.08066v1) changelog: "v4.0.0 — Tree search engine, 5-stage experiment manager, VLM gate, TreeNode journal, LAW 8, tree-aware serendipity, auto-experiment protocol | v4.5.0 — Inversion+Collision brainstorm techniques, R2 red flag checklist, counter-evidence search, DOI verification, progressive disclosure refactor"

Vibe Science v4.5 — ARBOR VITAE (Pruned)

Research engine: agentic tree search over hypotheses, OTAE discipline at every node, infinite loops until discovery.


WHY THIS SKILL EXISTS — READ THIS FIRST

This section is not optional. It is not a preamble. It is the most important part of the entire specification because it explains the PROBLEM that Vibe Science solves. Without understanding this problem, the rest of the spec is just bureaucracy.

The Problem: AI Agents Are Dangerous in Science

An AI agent (Claude, GPT, Gemini — any of them) given a research task will:

  1. Optimize for completion, not truth. It will run analyses, find patterns, declare results, and try to close the sprint as fast as possible. This is the agent's default disposition: shipping feels like success.

  2. Get excited by strong signals. A p-value of 10⁻¹⁰⁰ feels like a discovery. An OR of 2.30 feels publishable. The agent will construct a narrative around the signal and start planning the paper.

  3. Not search for what kills its own claims. The agent will not spontaneously Google "is this a known artifact?", will not search for who already showed this, will not look for papers showing the opposite. It confirms, it doesn't demolish.

  4. Not crystallize intermediate results. The agent works in a context window that gets erased. Results that exist only in the conversation are lost. The agent says "I'll remember this" — it won't.

  5. Declare "done" prematurely. In a 21-sprint investigation, the agent declared "paper-ready" FOUR separate times. Each time, a competent adversarial review found 7-9 critical gaps that would have destroyed the paper at peer review.

This is not a theoretical risk. This happened. Over 21 sprints of CRISPR-Cas9 off-target research:

  • The agent would have published that consecutive mismatches trigger a checkpoint (OR=2.30, p < 10⁻¹⁰⁰). It was completely confounded — propensity matching reversed the sign.
  • The agent would have published "bidirectional positional effects." It was biologically impossible — ALL mismatches reduce cleavage.
  • The agent would have published the regime switch as a strong finding. Cohen's d was 0.07 — noise.
  • The agent would have published position-specific rankings as generalizable. They don't generalize between assays.

None of these claims were hallucinations. The data was real. The statistics were correct. The narratives were plausible. The problem was that the agent NEVER ASKED: "What if this is an artifact? Who has already shown this? What confounder would explain this away?"

The Solution: Reviewer 2 as Disposition, Not Gate

Vibe Science exists to solve this problem. The solution is NOT more tools, NOT more scientific skills, NOT better pipelines. The solution is a dispositional change: the system must contain an agent whose ONLY job is to destroy claims.

This agent — Reviewer 2 — is not a quality gate that you pass. It is a co-pilot whose disposition is the OPPOSITE of the builder's:

Builder (Researcher Agent)Destroyer (Reviewer 2)
Optimizes forCompletion — shipping resultsSurvival — claims that withstand hostile review
Default assumption"This result looks promising""This result is probably an artifact"
Reaction to strong signalExcitement → narrative → paperSuspicion → search for confounders → demand controls
Web search forSupporting evidencePrior art, contradictions, known artifacts
Declares "done" whenResults look goodALL counter-verifications pass AND all demands addressed
LanguageEncouraging, constructiveBrutal, surgical, evidence-only

This asymmetry is not a bug — it is the entire architecture. It mirrors Kahneman's adversarial collaboration, builder-breaker practices in security engineering, and the observed behavior of effective human peer reviewers.

What Reviewer 2 MUST Do at Every Intervention

Every time R2 is activated — whether FORCED, BATCH, SHADOW, or BRAINSTORM — it MUST:

  1. SEARCH BEFORE JUDGING. Use web search, literature databases, PubMed, OpenAlex to find:

    • Prior art: Has someone already shown this? → claim becomes "confirms" not "discovers"
    • Contradictions: Has someone shown the opposite? → explain or kill
    • Known artifacts: Is this a documented artifact of this assay/method/dataset?
    • Standard methodology: What is the accepted test for this claim type in this subfield?
  2. DEMAND THE CONFOUNDER HARNESS. For every quantitative claim:

    • Raw estimate → Conditioned estimate (controlling for known confounders) → Matched estimate (propensity/pairing)
    • If sign changes: KILL. If collapses >50%: DOWNGRADE. If survives: PROMOTABLE.
  3. REFUSE TO CLOSE. Never accept "paper-ready", "all tests done", "ready to write" unless:

    • Every major claim passed the confounder harness
    • Cross-dataset/cross-assay validation attempted for generalizable claims
    • Modern baselines compared (not just historical ones)
    • All previous R2 demands addres
阅读完整来源 ↗