all publishers

yogsoth-ai

@yogsoth-ai source repo

1,755 published skills · page 9 of 18

  1. ▌
    Atomic Unit Recall Aggregate · yogsoth-ai bundle
    Aggregate per-unit ACU/Nugget match judgments into a final recall score — normalized length-penalized recall for ACU, or V_strict/A_strict (+ run-level ranking, with an explicit per-topic-unreliability caveat) for Nugget. Use this as the final step of the atomic-unit chain, after atomic-unit-matching; this SOP's existence closes a gap the original pipeline design was missing — without it, per-unit match judgments were never actually summed into the score the source methodologies report.
    512 repo stars
  2. ▌
    Reporting Standard Checklist · yogsoth-ai bundle
    Check whether a paper reports each item from PRISMA, CONSORT, STROBE, ARRIVE, SPIRIT, or TRIPOD (per whichever study-design-tool-gate dispatched to), citing where each item is or isn't addressed — including a/b sub-item hierarchy where the standard defines one. Use this after study-design-tool-gate has dispatched to one of these 6 reporting standards; this checks report completeness (did they say where), not methodological quality (was the study done well) — there is no overall synthesis step, judgment per item is the terminal output.
    512 repo stars
  3. ▌
    Rhetorical Structure Quality · yogsoth-ai bundle
    (Proposal, unverified) Judge whether argumentative relations between unit-classification's rhetorical labels actually hold in a paper (e.g. is an AIM label adequately substantiated by BACKGROUND labels) — a second-order quality judgment over already-classified units, not raw text. Use this after unit-classification has labeled a paper's units with a rhetorical/argumentative label set, when the user wants to know if the paper's argument structure is actually sound, not just what role each sentence plays.
    512 repo stars
  4. ▌
    Signalling Question Answering · yogsoth-ai bundle
    Answer per-domain signalling questions (5-value scale: Yes/Probably yes/Probably no/No/No information) for RoB2, ROBINS-I, or QUADAS-2, per whichever variant study-design-tool-gate dispatched to. Use this after study-design-tool-gate has dispatched to one of these three tools; this SOP produces only the raw signalling answers, not any domain-level or overall roll-up — that happens in domain-level-judgment next.
    512 repo stars
  5. ▌
    Multi Stage Cascade Extraction · yogsoth-ai bundle
    Run a multi-stage extraction cascade (mention detection, document-level coreference clustering, optional saliency judgment, N-ary relation/triple extraction) directly over a paper's full text — covers SciERC, SciREX, and NLP Contribution Graph. Use this whenever cross-sentence or document-level entity/relation extraction is needed (e.g. SciREX-style Task-Dataset-Metric-Score tuples); do NOT use unit-classification for this, since these methods reason over the whole document's mentions, not independently-classified sentence units.
    512 repo stars
  6. ▌
    Deep Read · yogsoth-ai
    Deep-reading strategy that turns a single specified academic paper into a structured, source-anchored bundle (problem, method, key results, limitations) ready for fact-checking and article drafting. Use this whenever the user names one specific paper (by arXiv ID, URL, or title) and wants it read, summarized, explained, or turned into content — this is the entry point of the paper-reading pipeline.
    512 repo stars
  7. ▌
    Hook Crafting · yogsoth-ai bundle
    Write a WeChat article's opening 1-3 sentence hook using one of four formula families (curiosity, story, value, contrarian), grounded in the verified bundle so the hook doesn't overpromise. Use this after angle-selection has chosen the article's framing, before section-drafting-with-style writes the full piece.
    512 repo stars
  8. ▌
    Marketing Led · yogsoth-ai
    Mass-audience 公众号 writing path — selects an angle, crafts a hook, drafts the article with a pre-set style constraint, and revises via a 3-sweep editing pass. Use this as the default (and, in v1, only) audience-first-writing tactic whenever the target is a public WeChat account audience rather than a professional/academic readership.
    512 repo stars
  9. ▌
    Reproducibility Third Party Verification · yogsoth-ai bundle
    (Proposal, unverified) Attempt to verify a paper's reported results by actually executing its released code/scripts against its own reported configuration — the only SOP in this package whose action type is code execution rather than text reading/judgment. Use this after unit-classification has extracted the paper's reported configuration/hyperparameters as classified units; "not_attempted" is a correct, common output when the paper's own reporting is too incomplete to run, not a failure of this SOP.
    512 repo stars
  10. ▌
    Angle Selection · yogsoth-ai bundle
    Pick which candidate angle to write the article around, cross-checked against the verified bundle so the chosen angle is actually substantiated by the paper (not just appealing at the skim stage). Use this as the first step of drafting, after quality-assurance has passed, whenever you have candidate_angles from first-pass-skim and a verified bundle.
    512 repo stars
  11. ▌
    Failure Routing · yogsoth-ai bundle
    Fixed lookup table mapping a detected verification failure type (precision_fail, recall_fail, drift_fail, none) to the specific upstream pipeline step to route back to. Use this immediately after pre-write-precision-check, pre-write-recall-check, or post-write-drift-check report a result, to decide whether and where to loop back rather than proceeding.
    512 repo stars
  12. ▌
    Quality Assurance · yogsoth-ai
    Verification strategy that independently re-checks a paper bundle's precision (no unsupported claims) and recall (nothing important omitted) against the original source, before any article drafting begins, then re-checks the finished draft for drift. Use this after deep-read produces a bundle and before audience-first-writing drafts an article — this is the mandatory middle strategy of the paper-reading pipeline.
    512 repo stars
  13. ▌
    Third Pass Verify · yogsoth-ai bundle
    Targeted re-read of only the bundle fields flagged as uncertain by second-pass-grasp, using precise PDF queries rather than a full re-read. Use this immediately after second-pass-grasp whenever its uncertain_fields output is non-empty; skip straight to extract-structured-bundle when it's empty.
    512 repo stars
  14. ▌
    Progressive Passes · yogsoth-ai
    Full 3-pass progressive deep-reading of a paper — skim, grasp, targeted verify — producing a structured bundle ready for fact-checking and article drafting. This is the default reading tactic for the paper-reading package; use it whenever no angle is already decided and you're starting from a bare paper reference.
    512 repo stars
  15. ▌
    Seven Sweeps Revision · yogsoth-ai bundle
    Revise a drafted WeChat article through 3 focused editing passes (Clarity, Prove It, Specificity), each checking one dimension before the next runs. Use this after section-drafting-with-style produces the initial article_draft, before the post-write drift check. Named after the copy-editing "Seven Sweeps" framework this is adapted from — v1 implements 3 of the 7 sweeps; the rest are deferred until real usage shows they're needed.
    512 repo stars
  16. ▌
    Audience First Writing · yogsoth-ai
    Writing strategy that turns a verified paper bundle into a finished public-audience article — selecting an angle, applying a pre-set style constraint during drafting (never a post-hoc rewrite), and checking the result for drift against the bundle. Use this after quality-assurance has passed on the bundle — this is the final strategy of the paper-reading pipeline, producing the WeChat article itself.
    512 repo stars
  17. ▌
    Dual Gate Verification · yogsoth-ai
    Strict verification path — runs an exhaustive precision check and an exhaustive recall check against the bundle before drafting, then a drift check after drafting, routing any failure back to the appropriate upstream step. This is the default (and, in v1, only) quality-assurance tactic; use it for every run unless a future spot-check or human-in-loop tactic is explicitly requested.
    512 repo stars
  18. ▌
    Post Write Drift Check · yogsoth-ai bundle
    Back-summarize the finished article draft and diff it against the already-verified bundle to catch drift (new errors or omissions introduced during drafting/styling) — even when the bundle itself already passed precision and recall checks. Use this immediately after any drafting sop (section-drafting-with-style, or any future content-faithful/hybrid drafting sop) produces an article_draft, before considering the article final. Shared by both quality-assurance and audience-first-writing.
    512 repo stars
  19. ▌
    Pre Write Recall Check · yogsoth-ai bundle
    Independently extract a paper's most important atomic facts directly from the raw source (before looking at the bundle at all), then check whether the bundle covers each one — catching content the bundle omitted. Use this before any article drafting begins, alongside pre-write-precision-check, immediately after extract-structured-bundle produces the bundle. This is a distinct check from precision-check — it catches omissions, not wrong claims — and must never be merged into it.
    512 repo stars
  20. ▌
    Extract Structured Bundle · yogsoth-ai bundle
    Finalize a paper's verified reading output into the exact bundle schema (problem/method/key_result/limitation, each with a source_anchor) that all downstream fact-checking and article-drafting sops consume. Use this as the last step of the deep-read strategy, after third-pass-verify, whenever you need to hand off a finished bundle to quality-assurance or audience-first-writing.
    512 repo stars
  21. ▌
    Pre Write Precision Check · yogsoth-ai bundle
    Independently fact-check every claim in a paper's bundle against the raw source text (Factored Verification method), flagging any claim the source doesn't actually support at a correctness score below 0.8. Use this before any article drafting begins, immediately after extract-structured-bundle produces the bundle — never skip this even if the bundle looks obviously correct, since research shows even top models hallucinate subtly when summarizing papers.
    512 repo stars
  22. ▌
    Section Drafting With Style · yogsoth-ai bundle
    Draft the full WeChat article from the verified bundle, chosen angle, and hook, applying a pre-set style guide and paragraph/figure-placement structural rules from the start — never as a post-hoc rewrite pass. Use this after hook-crafting has produced the opening hook, as the main drafting step of the marketing-led tactic.
    512 repo stars
  23. ▌
    Gap Prioritization · yogsoth-ai
    Strategy for ranking unexplored combinations by novelty, feasibility, and potential impact.
    512 repo stars
  24. ▌
    Variable Identification · yogsoth-ai
    Identify key variables in the causal system
    512 repo stars
  25. ▌
    Gap Identification · yogsoth-ai bundle
    Identify what the literature has NOT addressed — missing methods, untested combinations, unexplored applications, contradictions without resolution. Used by all strategies.
    512 repo stars
  26. ▌
    Claim Decomposition · yogsoth-ai
    Independent/dependent claim parsing, element extraction, and feature mapping to technical domains
    512 repo stars
  27. ▌
    Deep Insight · yogsoth-ai
    Deep Insight Engine with 5 campaigns (gap-analysis, insight, boundary-analysis, sensitivity-analysis, problem-reformulation). Use this skill whenever a user needs to deeply analyze research gaps, understand root causes, probe method boundaries, assess assumption sensitivity, or reformulate research problems. Pre-condition: north-star-crystallization complete + knowledge-acquisition campaign has produced initial findings.
    512 repo stars
  28. ▌
    Jtbd Mapping · yogsoth-ai bundle
    Map stakeholder Jobs-to-be-Done — functional, emotional, and social jobs for each affected party. Identifies unserved jobs as opportunity signals.
    512 repo stars
  29. ▌
    Gap Synthesis · yogsoth-ai bundle
    Compile all gap analysis intermediate products into a coherent final report with executive summary, detailed findings, and research agenda.
    512 repo stars
  30. ▌
    Re Derivation · yogsoth-ai bundle
    Re-derive conclusions under a negated assumption, tracking where the derivation diverges from the original.
    512 repo stars
  31. ▌
    Clr Validation · yogsoth-ai bundle
    Apply Goldratt's 8 Categories of Legitimate Reservation to validate causal claims. Tests clarity, existence, sufficiency, and logical integrity.
    512 repo stars
  32. ▌
    Gap Validation · yogsoth-ai
    Validate gap authenticity via cross-database verification, temporal sensitivity testing, and false-gap filtering. Ensures gaps are genuine absences, not search artifacts.
    512 repo stars
  33. ▌
    Lateral Escape · yogsoth-ai
    de Bono lateral escape sequence — identify dominant idea, generate provocations (escape/reversal/exaggeration/distortion), follow consequences to extract new framings. Breaks paradigm lock-in.
    512 repo stars
  34. ▌
    Tension Mining · yogsoth-ai
    Identify opposing forces that keep gaps open. Uses evaporating cloud to expose hidden assumptions behind conflicts and polarity mapping for unresolvable tensions.
    512 repo stars
  35. ▌
    Catwoe Analysis · yogsoth-ai bundle
    Apply Checkland's CATWOE analysis from a specific stakeholder perspective to reveal how the problem looks from that viewpoint.
    512 repo stars
  36. ▌
    Csh 12 Question · yogsoth-ai bundle
    Apply Ulrich's Critical Systems Heuristics 12 questions across 4 dimensions (motivation, control, expertise, legitimacy) comparing is vs ought.
    512 repo stars
  37. ▌
    Hmw Formulation · yogsoth-ai bundle
    Generate "How Might We" questions at different scope levels (narrow, medium, broad). Ensures each is actionable without being prescriptive.
    512 repo stars
  38. ▌
    Assumption Audit · yogsoth-ai
    Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.
    512 repo stars
  39. ▌
    Cross Validation · yogsoth-ai
    Multi-source cross-validation of gap authenticity — cross-database search, temporal sensitivity testing, false-gap filtering, stakeholder confirmation.
    512 repo stars
  40. ▌
    Egm Construction · yogsoth-ai bundle
    Build structured Evidence Gap Maps — define axes (intervention × outcome or method × domain), place gaps in cells, annotate with evidence density and quality.
    512 repo stars
  41. ▌
    Evidence Grading · yogsoth-ai bundle
    Assess evidence quality using GRADE/SOE framework. Rates certainty level and identifies downgrade reasons.
    512 repo stars
  42. ▌
    Evidence Mapping · yogsoth-ai
    Systematic evidence map construction — search, classify, locate gaps, visualize. Combines concept-matrix-construction, gap-keyword-extraction, evidence-grading, and egm-construction SOPs.
    512 repo stars
  43. ▌
    Morris Screening · yogsoth-ai bundle
    Morris method screening — compute elementary effects to quickly identify important vs unimportant parameters.
    512 repo stars
  44. ▌
    Polarity Mapping · yogsoth-ai bundle
    Map unresolvable tensions as Johnson polarities — 4 quadrants (positive/negative of each pole), early warnings, action steps for managing rather than solving.
    512 repo stars
  45. ▌
    Reframing Matrix · yogsoth-ai bundle
    Reframe the problem from 4 professional perspectives to reveal what each discipline would focus on.
    512 repo stars
  46. ▌
    Scaling Frontier · yogsoth-ai
    Analyze behavior across scales — detect regime changes, identify capacity limits, fit scaling laws within regimes.
    512 repo stars
  47. ▌
    Socratic Probing · yogsoth-ai bundle
    Apply 6 types of Socratic questions to test claims and assumptions. Exposes weaknesses and strengthens reasoning.
    512 repo stars
  48. ▌
    Boundary Critique · yogsoth-ai
    Apply CSH boundary critique — what is included/excluded, who benefits/is harmed, what expertise is privileged/marginalized. Identifies opportunities at the boundaries.
    512 repo stars
  49. ▌
    Evaporating Cloud · yogsoth-ai bundle
    Model conflicts as Goldratt's Evaporating Cloud — expose hidden assumptions behind opposing needs to dissolve the conflict.
    512 repo stars
  50. ▌
    Boundary Synthesis · yogsoth-ai bundle
    Compile all boundary analysis products into a coherent report — validity envelopes, robustness results, failure catalogs, scaling maps, safe operating conditions.
    512 repo stars
  51. ▌
    Boundary Unfolding · yogsoth-ai
    Systematically expose hidden system boundaries — CSH 12-question is/ought comparison, identify excluded stakeholders, reveal blind spots. Combines csh-12-question, jtbd-mapping, and salience-classification SOPs.
    512 repo stars
  52. ▌
    Evidence Synthesis · yogsoth-ai bundle
    Synthesize multi-source evidence into structured argumentation. Weaves findings from literature, web, and analysis into coherent evidence maps with explicit strength ratings.
    512 repo stars
  53. ▌
    Failure Clustering · yogsoth-ai bundle
    Group observed failures by mechanism (not symptom), identify common triggers per cluster, estimate frequency and severity.
    512 repo stars
  54. ▌
    Five Whys Drilling · yogsoth-ai bundle
    Iterative "Why?" questioning (5+ levels) to drill from surface phenomenon to actionable root cause. Each level verified against evidence.
    512 repo stars
  55. ▌
    Fragility Flagging · yogsoth-ai bundle
    Identify which specific assumption changes cause conclusion divergence. Rates fragility severity and plausibility of alternatives.
    512 repo stars
  56. ▌
    Gap Classification · yogsoth-ai
    Classify identified gaps using Miles 7-type taxonomy and AHRQ 4-reason framework. Determines gap type (theoretical, methodological, empirical, etc.) and root cause of gap existence.
    512 repo stars
  57. ▌
    Robustness Testing · yogsoth-ai
    Test conclusion robustness via multi-model convergence — enumerate assumptions, generate alternatives, compare results, flag fragile conclusions.
    512 repo stars
  58. ▌
    Wickedness Scoring · yogsoth-ai bundle
    Score a problem against Rittel's 10 criteria to determine if it is tame, complex, or wicked.
    512 repo stars
  59. ▌
    False Gap Filtering · yogsoth-ai bundle
    Detect false gaps — search failures, already-solved gaps, and inherently unanswerable questions masquerading as research gaps.
    512 repo stars
  60. ▌
    Negation Definition · yogsoth-ai bundle
    Define strongest plausible alternatives (negations) for each assumption to enable perturbation analysis.
    512 repo stars
  61. ▌
    Parameter Screening · yogsoth-ai
    Quick Morris method screening to identify which parameters have large effects and which can be safely ignored.
    512 repo stars
  62. ▌
    Root Cause Drilling · yogsoth-ai
    Drill from surface symptoms to root causes via 5 Whys, Ishikawa decomposition, and Current Reality Trees. Validates each causal link with literature evidence.
    512 repo stars
  63. ▌
    Sobol Decomposition · yogsoth-ai bundle
    Sobol variance decomposition — compute first-order and total-order sensitivity indices for precise variance attribution.
    512 repo stars
  64. ▌
    Stakeholder Mapping · yogsoth-ai
    Map all affected parties using CSH 12-question framework, identify jobs-to-be-done, classify by salience. Reveals whose perspective is systematically excluded.
    512 repo stars
  65. ▌
    Uncertainty Cascade · yogsoth-ai
    Uncertainty cascade propagation — assign input distributions, sample via Monte Carlo, propagate through model, analyze output distribution, identify critical paths. Maps how input uncertainty flows to output uncertainty.
    512 repo stars
  66. ▌
    Causal Tree Building · yogsoth-ai
    Build logical causal trees from symptoms to root causes — list UDEs, connect causal chains, validate logic, locate root causes. Combines ishikawa-decomposition, current-reality-tree, and clr-validation SOPs.
    512 repo stars
  67. ▌
    Current Reality Tree · yogsoth-ai bundle
    Build TOC Current Reality Trees — connect Undesirable Effects via sufficient-cause logic to identify 1-3 root causes.
    512 repo stars
  68. ▌
    Decision Sensitivity · yogsoth-ai
    Identify which uncertainties would actually change the research direction decision. Compute EVPI to prioritize uncertainty reduction.
    512 repo stars
  69. ▌
    Dominant Idea Escape · yogsoth-ai
    Identify dominant paradigms constraining the field and use de Bono lateral thinking provocations to escape them.
    512 repo stars
  70. ▌
    Edge Case Generation · yogsoth-ai bundle
    Systematically generate boundary inputs — boundary values, adversarial constructions, distribution shifts, rare combinations, scale extremes.
    512 repo stars
  71. ▌
    Monte Carlo Sampling · yogsoth-ai bundle
    Design and execute Monte Carlo sampling strategy for uncertainty propagation through a model.
    512 repo stars
  72. ▌
    Abstraction Laddering · yogsoth-ai bundle
    Move between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.
    512 repo stars
  73. ▌
    Consequence Following · yogsoth-ai bundle
    Follow a provocation's logical consequences step by step to extract viable insights and new research directions.
    512 repo stars
  74. ▌
    Dialectical Synthesis · yogsoth-ai
    Hegelian thesis-antithesis-synthesis cycle — propose position, generate opposition, structured debate, synthesize transcending insight. Combines evaporating-cloud and polarity-mapping SOPs.
    512 repo stars
  75. ▌
    Failure Mode Analysis · yogsoth-ai
    Systematically catalog failure modes — generate edge cases, observe failures, cluster by mechanism, identify triggers and frequency.
    512 repo stars
  76. ▌
    Interaction Detection · yogsoth-ai bundle
    Detect and characterize significant parameter interactions from Sobol decomposition results.
    512 repo stars
  77. ▌
    Sensitivity Synthesis · yogsoth-ai bundle
    Synthesize all sensitivity analysis results into a coherent report with prioritized recommendations.
    512 repo stars
  78. ▌
    Wickedness Assessment · yogsoth-ai
    Apply Rittel's 10 criteria to determine if the problem is tame, complex, or wicked, and adjust research strategy accordingly.
    512 repo stars
  79. ▌
    Appreciative Discovery · yogsoth-ai bundle
    Search for positive deviants and extract transferable principles using Appreciative Inquiry.
    512 repo stars
  80. ▌
    Appreciative Reframing · yogsoth-ai
    Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.
    512 repo stars
  81. ▌
    Assumption Criticality · yogsoth-ai
    Measure how much conclusions change when each assumption is negated. Ranks assumptions by their impact on the final result.
    512 repo stars
  82. ▌
    Assumption Stress Test · yogsoth-ai
    Systematic stress testing of assumptions — surface, classify by vulnerability, attack, assess fragility. Combines assumption-surfacing (shared), abp-vulnerability-classification, and clr-validation SOPs.
    512 repo stars
  83. ▌
    Convergence Assessment · yogsoth-ai bundle
    Compare results across multiple model variants — quantitative agreement metrics and qualitative conclusion stability.
    512 repo stars
  84. ▌
    Gap Keyword Extraction · yogsoth-ai bundle
    Extract gap-indicating sentences and phrases from papers/reviews. Identifies linguistic markers of research gaps (e.g., "remains unclear", "has not been explored", "limited understanding").
    512 repo stars
  85. ▌
    Gap Synthesis Strategy · yogsoth-ai
    Compile all gap analysis products into a coherent final report with evidence gap maps, research agenda, and concept matrices.
    512 repo stars
  86. ▌
    Ishikawa Decomposition · yogsoth-ai bundle
    Decompose problems into 6M categories (Methodology, Data, Theory, Measurement, Researchers, Environment) via fishbone diagram analysis.
    512 repo stars
  87. ▌
    Prioritization Scoring · yogsoth-ai
    Multi-dimensional gap scoring and ranking — define criteria, score, weight, rank, sensitivity-check. Combines multi-criteria-scoring, stakeholder-confirmation, and feasibility assessment.
    512 repo stars
  88. ▌
    Question Reformulation · yogsoth-ai
    Reframe research questions using abstraction laddering, HMW formulation, and Socratic probing. Find the most productive level and framing for investigation.
    512 repo stars
  89. ▌
    Variance Decomposition · yogsoth-ai
    Sobol variance decomposition — compute first-order and total-order sensitivity indices to quantify each parameter's contribution to output variance.
    512 repo stars
  90. ▌
    Controlled Perturbation · yogsoth-ai bundle
    Systematically vary parameters along defined axes, recording performance at each point to identify degradation thresholds.
    512 repo stars
  91. ▌
    Distribution Assignment · yogsoth-ai bundle
    Assign probability distributions to uncertain parameters based on available evidence and domain knowledge.
    512 repo stars
  92. ▌
    Multi Model Convergence · yogsoth-ai
    Wimsatt-style multi-method cross-validation — enumerate assumptions, generate alternative models, compare results, flag divergences.
    512 repo stars
  93. ▌
    Reformulation Synthesis · yogsoth-ai bundle
    Compile all problem reformulation analyses into a coherent report with a recommended new problem definition.
    512 repo stars
  94. ▌
    Salience Classification · yogsoth-ai bundle
    Classify stakeholders by Mitchell et al. framework (Power, Legitimacy, Urgency). Assigns salience category and identifies systematically excluded parties.
    512 repo stars
  95. ▌
    Systematic Perturbation · yogsoth-ai
    Multi-axis systematic perturbation — define variation axes, perturb along each, measure degradation, construct validity envelope.
    512 repo stars
  96. ▌
    Uncertainty Propagation · yogsoth-ai
    Propagate input uncertainties through the model via Monte Carlo sampling. Identifies which input uncertainties contribute most to output uncertainty.
    512 repo stars
  97. ▌
    Scaling Regime Detection · yogsoth-ai bundle
    Detect regime changes in scaling behavior — breakpoints where behavior qualitatively shifts, mechanisms behind transitions.
    512 repo stars
  98. ▌
    Stakeholder Confirmation · yogsoth-ai bundle
    Simulate stakeholder perspectives to validate gap priorities. Assesses gap value from researcher, practitioner, funder, and end-user viewpoints.
    512 repo stars
  99. ▌
    Deep Insight Paper Search · yogsoth-ai
    AI-powered paper summary and search. Import of literature-engine/literature-search skill. AI summary level — cite as "AI-extracted" not "paper states".
    512 repo stars
  100. ▌
    Deep Insight Web Research · yogsoth-ai
    Deep web research with full page fetching via Apify. Import of web-browsing/web-research skill. Must fetch full page — no conclusions from previews.
    512 repo stars