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.
Self-review the North Star + ResearchBrief for completeness, consistency, and clarity before presenting to user. If issues found, return to specific tactic/SOP for targeted fix. If passes, present final output to user for confirmation.
Idioma do texto original: inglês
Express the user's chosen research direction as a formal goal statement in the format: 'Achieve [what], such that [effect], under [constraints]'. Confirm with user before proceeding to decomposition.
Idioma do texto original: inglês
SOP for finding structural gaps in the ontology — missing concepts, thin branches, disconnected clusters.
Idioma do texto original: inglês
Estimate theoretical/practical ceiling vs current SOTA gap
Idioma do texto original: inglês
SOP for inspecting the current hierarchy structure — query graph to display parent-child relationships.
Idioma do texto original: inglês
SOP for documenting an intervention — what happens when a causal variable is manipulated.
Idioma do texto original: inglês
SOP for documenting a feedback loop — classify, describe dynamics, identify break points.
Idioma do texto original: inglês
SOP for exporting the dimensional matrix as a readable document or structured data.
Idioma do texto original: inglês
SOP for creating a causal mechanism edge — documents how one variable causes changes in another.
Idioma do texto original: inglês
SOP for identifying near-duplicate concepts that should be merged.
Idioma do texto original: inglês
Identify all relevant methods via literature, leaderboards, citation chains
Idioma do texto original: inglês
SOP for finding gaps in the causal model — missing variables, unexplained effects, weak links.
Idioma do texto original: inglês
SOP for exporting ontology summary — generate a readable overview of the current ontology state.
Idioma do texto original: inglês
Assemble unified comparison table with confidence interval annotations
Idioma do texto original: inglês
Present the field panorama to the user and gather their preferences — which fields interest them, which they reject, and why. A dialogue SOP that bridges landscape-synthesis output to user decision.
Idioma do texto original: inglês
Analyze sub-directions within the user's chosen field and present ranked candidates. Combines sub-direction identification, skill-gap matching, and presentation into a single SOP. Depth scales by start mode: cold-start shows broad sub-directions, warm-start…
Idioma do texto original: inglês
Construct performance-over-time visualization data
Idioma do texto original: inglês
SOP for generating research questions from promising gaps in the design space.
Idioma do texto original: inglês
SOP for documenting rebuttals and counter-claims — create rebuttal pages with typed contradiction edges and source attribution.
Idioma do texto original: inglês
Assess paper completeness against ML Reproducibility Checklist
Idioma do texto original: inglês
Verify result reproducibility via re-runs with different seeds and ICC comparison
Idioma do texto original: inglês
Collect experiment outputs — metrics, logs, artifacts — into structured result set
Idioma do texto original: inglês
Structured questioning SOP to determine research boundaries, depth, and breadth. Used during spec generation.
Idioma do texto original: inglês
Extract (Task, Dataset, Metric, Score, Conditions) tuples from a paper
Idioma do texto original: inglês
Collect historical scores, fit saturation curves, detect inflection points
Idioma do texto original: inglês
SOP for finding seed concepts in existing vault and web sources to anchor ontology construction.
Idioma do texto original: inglês
Complete Six Hats rotation (White→Red→Black→Yellow→Green→Blue) to force systematic perspective diversity.
Idioma do texto original: inglês
Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.
Idioma do texto original: inglês
Quality gate for Research Specs. Checks for placeholders, consistency, scope, ambiguity, context protocol, and quantification. Mandatory before user review.
Idioma do texto original: inglês
Execute statistical tests — bootstrap, permutation, Bayesian ROPE — on experiment results
Idioma do texto original: inglês
SOP for assigning calibrated strength scores to claims — evaluate evidence weight, count independent sources, check defeaters, produce scored assessment.
Idioma do texto original: inglês
SOP for producing argument synthesis reports — aggregate evidence, resolve contradictions, identify surviving claims, write structured summary.
Idioma do texto original: inglês
SOP for generating a causal model validation report — summarize coverage, confidence, gaps, contradictions.
Idioma do texto original: inglês
SOP for creating a variable page in the causal model — documents a measurable quantity with its properties.
Idioma do texto original: inglês
SOP wrapping vault_add_edge — create a typed relationship between two vault pages.
Idioma do texto original: inglês
SOP for wiki page creation/update — create or update a synthesized wiki page with edges and index update.
Idioma do texto original: inglês
SOP for auditing wikilink coverage — scans all edges and reports which source pages are missing [[dir/slug]] wikilinks to their targets.
Idioma do texto original: inglês
SOP wrapping vault_query_graph — traverse knowledge graph from a node to explore its neighborhood and context.
Idioma do texto original: inglês
SOP for source page creation — write immutable source page capturing raw material, then update search index.
Idioma do texto original: inglês
SOP wrapping vault_lint — run batch validation, report issues, optionally auto-fix safe problems.
Idioma do texto original: inglês