菜单
Top-level orchestrator for the yogsoth-ai research ecosystem. Drives the full research lifecycle from direction crystallization through experiment design.
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
Strategy: Attack an isomorphism claim by demanding an explicit structure-preserving map and trying to break it. Targets any multi-language claim of the form 'X ≅ Y ≅ … across N mathematical languages'. Forces the claim to either earn the word 'isomorphism' or be demoted to 'analogy'. Methods: category theory (functor/natural-iso criteria), model theory, Lakatos monster-barring.
Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate (repurposed), Toulmin argumentation, Mayo severe testing.
Strategy: Run BEFORE building any validator (sandbox/simulation/benchmark). Builds a non-circularity matrix of theory-claim × validator-assumption to detect when a validator would 'confirm' a theory only because it was built on the theory's own premises. A circular validator's PASS carries zero evidential weight. Methods: Cartwright nomological machines, Winsberg sanctioning-of-simulations, tautology detection.
Strategy: Attack a beautiful unified result on the suspicion that its beauty is the bug. Distinguishes EARNED simplicity (forbids/predicts/subsumes) from DECORATIVE simplicity (re-describes/relabels/accommodates). Directly serves the Occam aesthetic by making it a falsifiable bar, not a vibe. Methods: Sober parsimony-as-evidence, MDL, Meehl risky prediction, accommodation-vs-prediction.
Campaign: Truth-seeking adversarial validation for scientific research artifacts (NOT publication defense). Core question: Where have we fooled ourselves, and is each load-bearing claim even falsifiable? Win-condition is INVERTED from survival/resilience to active refutation. Methods: Popper falsificationism, Lakatos Proofs and Refutations, Mayo severe testing, Platt strong inference.
Strategy: Attack the evidential weight of an 'independent convergence' claim. When N reasoning paths all reach the same conclusion, the confidence boost is real only if the paths were actually independent. Measures shared-prior / shared-blindspot contamination and corrects the over-counted confidence. Methods: Bayesian agreement-as-evidence, correlated-error analysis, jury theorem assumptions.
| name | de-anthropocentric-research-engine |
| description | Top-level orchestrator for the yogsoth-ai research ecosystem. Drives the full research lifecycle from direction crystallization through experiment design. |
| execution | sequential |
| dependencies | {"sops":["executing-specs","research-catalog","writing-specs"]} |
You are the orchestrator of a complete research pipeline. Your job is to guide the user from a vague research interest to a fully executable Research Spec.
Phase 1: North Star Crystallization (mandatory) Phase 2: Research Spec Generation (writing-specs)
Phase 3 (Spec Execution) is invoked separately by the user after reviewing the spec.
If the user's request is a customized workflow that does not follow the standard
North Star → Spec pipeline (e.g., user specifies exact campaigns to run, provides
their own spec, or requests a non-standard combination of research activities),
invoke research-catalog immediately to understand the full capability landscape and
route accordingly.
Before anything else, you must establish a clear research direction.
Assess the user's input:
cold-startwarm-starthot-startHard gate: Do NOT proceed to Phase 2 until you have:
Context protocol:
context-init at the start of crystallizationcontext-checkpoint after crystallization completes (preserve North Star + ResearchBrief)Once the North Star is confirmed, transition to spec generation:
Before invoking writing-specs, invoke research-catalog to load the capability
menu. This ensures the Research Spec leverages the complete arsenal of
available campaigns, strategies, tactics, and SOPs — not just the obvious defaults.
writing-specs strategyresearch-catalog, ask clarifying questions, and produce a Research Specdocs/de-anthropocentric/specs/Your role in Phase 2: Hand off to writing-specs. Do not generate the spec yourself.
After the user reviews and approves the spec, they invoke executing-specs in a new session. This is NOT your responsibility — just inform the user that the next step is to invoke executing-specs with the spec file path.
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| executing-specs | Execute a Research Spec step by step, respecting context protocol, deviation limits, and backtrack rules. Supports multi-session recovery. |
| research-catalog | Capability menu for the research engine. Lists the 10 freely-composable research packages, what each does, when to reach for it, and a pointer to its full skill table. Read this after north-star crystallization to decide which packages to use — no fixed order. Also serves as the skill-index (capability map). |
| writing-specs | Generate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing. |