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