de-anthropocentric-research-engine

Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.

Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed.

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 backprop attribution is a judgment call.

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.

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.

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.

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.

Use the DARE research engine to crystallize research goals, write executable research specs, and execute staged research workflows.

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.

Strategy: Systematic adversarial probing retuned for truth-seeking. Threat surface = the set of load-bearing claims. Output is NOT a resilience score and NOT a hardening list — it is, per claim, the specific observation/computation that would refute it, plus which attacks succeeded. Methods: UFMCS Key Assumptions Check (repurposed), CIA Devil's Advocacy, Platt strong inference.

Mechanism-Gap Hunting Campaign — hunt the specific link where scientific progress is BLOCKED, not where literature is empty. Use this instead of gap-analysis whenever the goal is truth-seeking / AI4S research rather than finding a publishable white-space — i.e. when the user asks "where is progress actually stuck", "what mechanism is blocking this", or wants a complete blocker set rather than a ranked gap list. 4 stages over reused deep-insight SOPs, with injected per-stage directives. Exhaustive (no prioritization/ranking).

Generate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing.

Top-level orchestrator for the yogsoth-ai research ecosystem. Drives the full research lifecycle from direction crystallization through experiment design.

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).

SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/

Campaign: Compile a context/ research record into an ARA (Agent-Native Research Artifact) and run a Level-2 epistemic review — no LaTeX, no narrative paper

SOP: Run the external ARA rigor-reviewer (Seal Level 2, six-dimension semantic review) over ../ara/ and pass its level2_report.json to the user

Tactic: Compile the feeding plan into an ARA via the external compiler, then run Level-2 rigor review over it

SOP: Read context/INDEX.md and sort the whole directory into three ARA material types (report line, process line, images), locate the north-star file, and draft a feeding plan for the ARA compiler

Tactic: Review a context/ directory — sort material into ARA types, locate and align the north-star, and produce a feeding plan for the compiler

SOP: Deep-read the original north-star context, distill this ARA's overall direction, and align it with the user via the reused present-and-ask / present-candidates dialogue SOPs

What limits us — identify bottlenecks, quantify constraints, analyze dependencies, resolve conflicts before experiment execution

Synthesize constraint analysis into actionable report with priorities

SOP: synthesize complete experiment design report

Synthesize complete execution report from all results, tests, and reproducibility data

Transform validated hypotheses into rigorous, executable experiment designs

Plan execution path, produce executable plan, dispatch subagents, collect and analyze results

What might the future look like — construct multiple future scenarios, assess research approach robustness under different assumptions

Comprehensive scenario analysis report synthesizing all scenario work

Execute the plan by dispatching fresh subagents per task, monitoring status, and collecting results

Dispatch execution subagent — select model by complexity, construct prompt with full task context

Format task plan as bite-sized executable tasks following superpowers:writing-plans conventions

Format critical path and prerequisites into bite-sized executable plan following superpowers:writing-plans conventions

Orchestrate task execution via fresh subagents with dispatch, monitoring, and result collection

Construct the strongest counter-argument against a specific assumption and propose alternatives.