Menu
Skills dans ce dépôt
SkillsMP a collecté 961 skills depuis yogsoth-ai/de-anthropocentric-research-engine. Ouvrez un skill pour examiner sa source et ses détails.
yogsoth-ai/de-anthropocentric-research-engineAffichage de 40 skills collectés sur 961.
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
SOP for finding structural gaps in the ontology — missing concepts, thin branches, disconnected clusters.
Langue du texte source : anglais
Estimate theoretical/practical ceiling vs current SOTA gap
Langue du texte source : anglais
SOP for inspecting the current hierarchy structure — query graph to display parent-child relationships.
Langue du texte source : anglais
SOP for documenting an intervention — what happens when a causal variable is manipulated.
Langue du texte source : anglais
SOP for documenting a feedback loop — classify, describe dynamics, identify break points.
Langue du texte source : anglais
SOP for exporting the dimensional matrix as a readable document or structured data.
Langue du texte source : anglais
SOP for creating a causal mechanism edge — documents how one variable causes changes in another.
Langue du texte source : anglais
SOP for identifying near-duplicate concepts that should be merged.
Langue du texte source : anglais
Identify all relevant methods via literature, leaderboards, citation chains
Langue du texte source : anglais
SOP for finding gaps in the causal model — missing variables, unexplained effects, weak links.
Langue du texte source : anglais
SOP for exporting ontology summary — generate a readable overview of the current ontology state.
Langue du texte source : anglais
Assemble unified comparison table with confidence interval annotations
Langue du texte source : anglais
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.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Construct performance-over-time visualization data
Langue du texte source : anglais
SOP for generating research questions from promising gaps in the design space.
Langue du texte source : anglais
SOP for documenting rebuttals and counter-claims — create rebuttal pages with typed contradiction edges and source attribution.
Langue du texte source : anglais
Assess paper completeness against ML Reproducibility Checklist
Langue du texte source : anglais
Verify result reproducibility via re-runs with different seeds and ICC comparison
Langue du texte source : anglais
Collect experiment outputs — metrics, logs, artifacts — into structured result set
Langue du texte source : anglais
Structured questioning SOP to determine research boundaries, depth, and breadth. Used during spec generation.
Langue du texte source : anglais
Extract (Task, Dataset, Metric, Score, Conditions) tuples from a paper
Langue du texte source : anglais
Collect historical scores, fit saturation curves, detect inflection points
Langue du texte source : anglais
SOP for finding seed concepts in existing vault and web sources to anchor ontology construction.
Langue du texte source : anglais
Complete Six Hats rotation (White→Red→Black→Yellow→Green→Blue) to force systematic perspective diversity.
Langue du texte source : anglais
Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.
Langue du texte source : anglais
Quality gate for Research Specs. Checks for placeholders, consistency, scope, ambiguity, context protocol, and quantification. Mandatory before user review.
Langue du texte source : anglais
Execute statistical tests — bootstrap, permutation, Bayesian ROPE — on experiment results
Langue du texte source : anglais
SOP for assigning calibrated strength scores to claims — evaluate evidence weight, count independent sources, check defeaters, produce scored assessment.
Langue du texte source : anglais
SOP for producing argument synthesis reports — aggregate evidence, resolve contradictions, identify surviving claims, write structured summary.
Langue du texte source : anglais
SOP for generating a causal model validation report — summarize coverage, confidence, gaps, contradictions.
Langue du texte source : anglais
SOP for creating a variable page in the causal model — documents a measurable quantity with its properties.
Langue du texte source : anglais
SOP wrapping vault_add_edge — create a typed relationship between two vault pages.
Langue du texte source : anglais
SOP for wiki page creation/update — create or update a synthesized wiki page with edges and index update.
Langue du texte source : anglais
SOP for auditing wikilink coverage — scans all edges and reports which source pages are missing [[dir/slug]] wikilinks to their targets.
Langue du texte source : anglais
SOP wrapping vault_query_graph — traverse knowledge graph from a node to explore its neighborhood and context.
Langue du texte source : anglais
SOP for source page creation — write immutable source page capturing raw material, then update search index.
Langue du texte source : anglais
SOP wrapping vault_lint — run batch validation, report issues, optionally auto-fix safe problems.
Langue du texte source : anglais