菜单
Generate grounded novel hypotheses from contradictions, complementary claims, and cross-domain mechanism transfers using the unified synthesize tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run the continuous experiment loop, including idea tournament, best-first tree expansion, mandatory literature cadence, bold swings, automatic commits, and memory write-back.
Gather literature, extract structured claims, and verify their sources and codebase relevance as one trust-preserving pipeline.
Run an autonomous research or optimization loop with literature-grounded, verifiable long-term memory. Use for measurable optimization and for ranked research-plan ideation.
Produce the autoresearch report with full idea lineage — paper → claim → hypothesis → patch → metric change → status → memory update. Use to summarize an autoresearch run into an auditable, human-readable report at .autoresearch-vkf/session/report.md.
| name | autoresearch-vkf-synthesize |
| description | Generate grounded novel hypotheses from contradictions, complementary claims, and cross-domain mechanism transfers using the unified synthesize tool. |
Call synthesize with the goal and context. Add a mechanism-framed problem
when cross-domain transfers are useful. It returns three views together:
contradictions, complementary compositions, and transfers with high mechanism
similarity but low context similarity.
Turn the strongest opportunity into one structured hypothesis. Record it with
remember_claim, using origin: contradiction, synthesis, or transfer and
setting derived_from to every source card. Explain the causal mechanism,
intervention, prediction, failure modes, lever, altitude, and why the combination
is not a superficial analogy. Start speculative claims at low-to-medium
confidence, verify what can be verified, then let plan_next_step rank them.
Prefer goal-relevant mechanism/reframe ideas. Novelty without a mechanistic reason is noise.
