Menu
Skills neste repositório
O SkillsMP coletou 961 skills de yogsoth-ai/de-anthropocentric-research-engine. Abra uma skill para revisar a origem e os detalhes.
yogsoth-ai/de-anthropocentric-research-engineMostrando 40 de 961 skills coletadas.
Sum NOS's item-level stars and bucket into good (≥7)/fair (4-6)/poor (≤3) — a fixed threshold lookup, structurally distinct from worst-case-lookup's take-the-worst-value approach. Use this after star-awarding has produced the per-item stars; this is NOS's…
Idioma do texto original: inglês
Classify each pre-segmented text unit independently against a fixed label set (Argumentative Zoning, CoreSC, PubMed-RCT, Swales move/step, CODA-19, TDMS, or CSFCube's facet labels), single-layer with no cross-unit dependency. Use this after unit-segmentation…
Idioma do texto original: inglês
Take the single most severe domain/item judgment as the overall verdict, for RoB2 (3-value), ROBINS-I (5-value), or AMSTAR-2 (pre-filtered by critical-domain status before worst-case). Use this after domain-level-judgment (for RoB2/ROBINS-I) or…
Idioma do texto original: inglês
SOP for gathering source material relevant to the ontology domain — fetch papers and web pages into source pages.
Idioma do texto original: inglês
Quick web scanning — discover pages, get snippets, find URLs. For orientation only, not substantive analysis.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Generate a complete, executable Research Spec from North Star + user input. Strategy-level skill that orchestrates questioning, outline, and spec writing.
Idioma do texto original: inglês
Top-level orchestrator for the yogsoth-ai research ecosystem. Drives the full research lifecycle from direction crystallization through experiment design.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/
Idioma do texto original: chinês
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
Idioma do texto original: chinês
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
Idioma do texto original: chinês
Tactic: Compile the feeding plan into an ARA via the external compiler, then run Level-2 rigor review over it
Idioma do texto original: chinês
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
Idioma do texto original: chinês
Tactic: Review a context/ directory — sort material into ARA types, locate and align the north-star, and produce a feeding plan for the compiler
Idioma do texto original: chinês
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
Idioma do texto original: chinês
Synthesize constraint analysis into actionable report with priorities
Idioma do texto original: inglês
SOP: synthesize complete experiment design report
Idioma do texto original: inglês
Synthesize complete execution report from all results, tests, and reproducibility data
Idioma do texto original: inglês
Plan execution path, produce executable plan, dispatch subagents, collect and analyze results
Idioma do texto original: Vários idiomas
Comprehensive scenario analysis report synthesizing all scenario work
Idioma do texto original: inglês
Execute the plan by dispatching fresh subagents per task, monitoring status, and collecting results
Idioma do texto original: chinês
Dispatch execution subagent — select model by complexity, construct prompt with full task context
Idioma do texto original: chinês
Format task plan as bite-sized executable tasks following superpowers:writing-plans conventions
Idioma do texto original: chinês
Format critical path and prerequisites into bite-sized executable plan following superpowers:writing-plans conventions
Idioma do texto original: Vários idiomas
Orchestrate task execution via fresh subagents with dispatch, monitoring, and result collection
Idioma do texto original: chinês
Construct the strongest counter-argument against a specific assumption and propose alternatives.
Idioma do texto original: inglês
Systematically surface hidden assumptions underlying a decision with confidence levels.
Idioma do texto original: inglês
Identify bottleneck dimensions from radar data with severity ranking.
Idioma do texto original: inglês
Simulates diverse stakeholder perspectives and their strongest objections/support arguments. Shared across steel-manning and consensus campaigns.
Idioma do texto original: inglês
Paper landscape scan at abstract level — discover MCDA, voting theory, Delphi, and optimization methodology papers.
Idioma do texto original: inglês