← All creators

yogsoth-ai

Organization

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.

130 indexed · 84 Featured · 393 stars · avg score 88
Prolific

Categories

Indexed Skills (130)

Data & Documents Featured

paper-fetch

Retrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly with no search at all, while other references use alphaxiv, Semantic Scholar routing, then bioRxiv/medRxiv. Use this as the mandatory first step whenever any other paper-reading SOP in this package needs the actual text of a paper — it is the sole entry point of the pipeline and every downstream SOP reads the files it lands, so do not bypass it even when the caller already has the file. If it returns not_found, halt immediately; do not fabricate content or guess at the paper's likely contents.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

abductive-hypothesis-generation

Strategy: Inference to the best explanation in the face of anomalies

378 Updated 6 days ago
yogsoth-ai
Web & Frontend Featured

ablation-design

Design ablation studies to isolate component contributions in ML systems

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adversarial-debate-truthseeking

Strategy: Dialectic engine retuned for truth-seeking, not survival. A defender steelmans a claim into its MOST falsifiable form, a critic attacks to refute it, a judge classifies the exchange into BROKEN/CORROBORATED/UNFALSIFIABLE — the judge does NOT pick a winner or score persuasiveness. Methods: Irving debate (repurposed), Toulmin argumentation, Mayo severe testing.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adversarial-escalation

Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adversarial-persona

Strategy: Role-play attacks from hostile personas — competing lab researcher, hostile reviewer, funding skeptic, domain outsider — each with distinct attack motivations and blind spots.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adversarial-roleplay

Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation.

378 Updated 6 days ago
yogsoth-ai
Testing & QA Featured

adversarial-stress-testing

Campaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ahrq-picme-assessment

SOP: Use the AHRQ PiCMe framework to systematically assess a research gap across 6 dimensions

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alternative-analysis

Strategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing — generate competing explanations and scenarios to challenge the dominant narrative.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

anomaly-driven-abduction

Tactic: Inductive/abductive path — describe anomalous phenomena, generate candidate explanations, rank by plausibility

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

acu-nugget-recall

Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

argumentative-zoning

Tactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning. Use when fixed rhetorical labels and cross-paper alignment matter.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

atomic-unit-recall-aggregate

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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

claim-writing

Blind-rewrite a citing sentence (citance) from another paper into a single atomic, independently-verifiable claim (SciFact's annotation protocol) — never looking at the cited paper's content while rewriting. Use this when you have a specific citing sentence and want it decomposed into checkable atomic claims, as the first step before rationale-selection and claim-label-prediction.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

domain-level-judgment

Fold raw signalling-question answers into domain-level judgments for RoB2, ROBINS-I, or QUADAS-2, per each tool's own lookup rules — the first of two aggregation levels these tools define. QUADAS-2 is dual-axis (risk-of-bias AND applicability-concern per domain, D1-D3) and terminates here with no further rollup; RoB2/ROBINS-I continue on to worst-case-lookup for an overall verdict. Use this after signalling-question-answering has produced the raw answers.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

dual-column-self-check

Run one of the ML/CS reproducibility checklists (ML Reproducibility Checklist, REFORMS, NeurIPS Paper Checklist, Model Cards, Datasheets for Datasets) against a paper as a reader-side audit, producing a category (Yes/No/NA) plus free-text reason per item. Use this whenever the user wants a reproducibility/completeness self-check run on an ML or CS paper — invoke this directly, it has no study-design gate in this package since these checklists are engineering self-audits, not clinical-study tools.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

engineering-config-grading

(Proposal, unverified) Grade reproducibility-relevant engineering configuration items (hyperparameter search range, compute budget, seed handling, dataset splits) on a complete/partial/none scale, requiring the grader to first define what "complete" means per item before judging against it. Use this after study-design-tool-gate has dispatched an ML/CS engineering paper here; this is a graded QUALITY judgment, distinct from dual-column-self-check's binary Yes/No/NA self-audit checklists.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

first-pass-skim

Keshav's first pass over one paper — a 5-10 minute skim of title, abstract, headings, figures, and conclusion only, producing skim notes and a read-deeper judgment. Use this as the first step whenever a paper is being read via the Keshav three-pass method; always precedes second-pass-grasp and never reads section bodies itself.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

keshav-three-pass

Tactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.

392 Updated 1 weeks ago
yogsoth-ai
Data & Documents Featured

multi-stage-cascade-extraction

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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

qalmri-worksheet

Tactic: Fill a six-slot QALMRI worksheet for one paper: Question, Alternatives, Logic, Method, Results, and Inference. Use for a structured reading worksheet rather than a graded evaluation.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

question-framing

Fill a slot-based question-framing schema (PICO, PECO, or SPIDER) from a paper's stated research question. Use this whenever the user wants a paper's research question structured into one of these standard clinical/qualitative-research question frames; this frames what question is being asked, it does not read or evaluate the paper's content otherwise.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

rationale-selection

Select the minimal set of 1-3 verbatim sentences from a candidate paper/abstract sufficient to entail or refute an atomic claim (SciFact's rationale-selection step). Use this after claim-writing has produced an atomic claim, as the evidence-gathering step before claim-label-prediction; an empty rationale set is a valid outcome, not an error.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

reforms-grading

Tactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.

392 Updated 1 weeks ago
yogsoth-ai
Data & Documents Featured

reporting-standard-checklist

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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

reproducibility-third-party-verification

(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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

research-question-appraisal

Judge a paper's stated research question against the FINER criteria (Feasible, Interesting, Novel, Ethical, Relevant) — five independent judgments with justification, evaluating the question itself, not the paper's results. Use this whenever the user wants to know whether a paper is asking a good research question, distinct from whether it answered that question well.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

rhetorical-structure-quality

(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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

second-pass-grasp

Keshav's second pass — a careful full read (ignoring proof/derivation detail) producing prose-level understanding sufficient to explain the paper's main contribution and evidence to a colleague. Use this after first-pass-skim, as the main content-grasping pass of the Keshav three-pass method; do not force its output into a structured data schema.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

signalling-question-answering

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.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

star-awarding

Award NOS's (Newcastle-Ottawa Scale) stars item-by-item across Selection (up to 4), Comparability (up to 2), and Outcome/Exposure (up to 3) — a binary award-or-not action per item, distinct from a 5-value signalling judgment. Use this after study-design-tool-gate has dispatched to NOS, as the first step before sum-threshold-scoring.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

study-design-tool-gate

Classify a paper's study design (RCT, cohort, case-control, diagnostic-accuracy, systematic-review, animal-study, prediction-model, etc., or not_applicable) and dispatch to the correct downstream bias-risk/quality/reporting tool and specific variant (CASP has 8 variants, JBI ~6, RoB2 has parallel/cluster/crossover versions). Use this as the mandatory first step before running ANY of CASP, JBI, AMSTAR-2, NOS, RoB2, ROBINS-I, QUADAS-2, CONSORT, STROBE, ARRIVE, SPIRIT, TRIPOD, or engineering-config-grading — these tools are all study-design-conditional and picking the wrong variant produces meaningless results. It is entirely correct and common for this gate to determine that none of these medically-descended tools applies (e.g. most CS/ML papers) — that is a valid, complete answer, not a failure.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

sum-threshold-scoring

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 terminal step.

392 Updated 1 weeks ago
yogsoth-ai
Data & Documents Featured

template-slot-filling

Fill a paper's reported values into an already-given comparison-template attribute schema (e.g. Task/Dataset/Metric/Value) — the executable half of ORKG's comparison-template method. Use this when a template's attribute schema is already fixed and you need one paper's row filled in; this does NOT build new templates (that half is a human-curator task, out of scope).

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

third-pass-deep-read

Keshav's third pass — the heaviest of the three, a full sentence-by-sentence re-read including proofs/derivations, attempting a virtual re-implementation of the paper to surface implicit assumptions and concrete improvement points. Use this after second-pass-grasp, as the terminal step of the Keshav three-pass method, whenever genuine mastery of a paper (not just a summary) is needed. This is not a skippable recap — treat "nothing new to add" as suspicious, not a default outcome.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

unit-classification

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 has split the text, whenever a sentence- or clause-level rhetorical/functional classification is needed; do not use this for methods requiring document-level coreference reasoning (see multi-stage-cascade-extraction instead).

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

unit-segmentation

Split a paper's text into sentence- or clause-level units (with character offsets) for downstream classification, at a caller-specified granularity and scope (full text, abstract-only, or intro-only). Use this as the mandatory first step whenever any sentence/clause-level classification method (Argumentative Zoning, CoreSC, PubMed-RCT, CSAbstruct, Swales move analysis, CODA-19) needs its input pre-segmented — always precedes unit-classification.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

worst-case-lookup

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 quality-appraisal-checklist (for AMSTAR-2) has produced per-domain/item judgments — this SOP has two structurally distinct upstream callers and must identify which value domain it received before applying the matching lookup rule. QUADAS-2 never reaches this SOP; it terminates one step earlier at domain-level-judgment.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

ablation-component-mapping

Map system architecture to ablatable units for ablation studies

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ablation-execution

Remove components one by one from a system, record the response/impact of each removal.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

abp-vulnerability-classification

Classify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.

378 Updated 6 days ago
yogsoth-ai
Data & Documents Featured

abstraction-extraction

Extract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

abstraction-laddering

Move between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

abstraction-to-design

Abstract biological principle to design principle. Bridge from biology to engineering.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

action-priority-matrix

Compute Risk Priority Number (RPN = S x O x D), classify failure modes into H/M/L action priority per AIAG-VDA tables.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

activity-listing

Enumerate all implementation activities from an experiment design

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

advocate-construction

Construct the strongest possible case for a rejected candidate or counter-position.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

aggregation-method

Aggregate multiple ranking ballots into a consensus ranking using a specified social choice method.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ahp-weighting

SOP: Use the AHP (Analytic Hierarchy Process) to determine scoring-dimension weights, outputting a weight vector

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ahrq-reason-classification

Classify gap root causes using AHRQ 4-reason framework (insufficient info, biased info, inconsistent info, not yet integrated).

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alternative-futures

Generate 2-4 divergent scenarios from the same evidence base, each representing a plausible alternative to the artifact's conclusions.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alternative-model-generation

Generate alternative model formulations by relaxing, replacing, or generalizing specific assumptions.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alternative-scoring

Score each candidate alternative against all criteria to produce a score matrix.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alternatives-generation

Generate alternatives for every known approach — ensure no approach goes unchallenged.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

analogy-chain

Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

analogy-quality-assessment

Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

and-or-decompose

KAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

anomaly-characterization

SOP: Describe and classify anomalous phenomena that existing theory cannot explain

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

answering-sequence-design

SOP: Design the optimal answering order for sub-questions

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

appreciative-discovery

Search for positive deviants and extract transferable principles using Appreciative Inquiry.

378 Updated 6 days ago
yogsoth-ai
Code & Development Featured

ara-compile

SOP: Turn the feeding plan into the compiler's $ARGUMENTS and run the external ARA compiler once inline to produce ../ara/

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ablation-brainstorm

Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

actor-profiling

Understand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adaptive-pair-selection

Iteratively select maximally informative pairs, execute comparisons, update ratings, and check convergence until ranking stabilizes.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

adversarial-debate-protocol

Structured debate protocol that constructs an advocate, deploys critic attacks, and renders a judge verdict through iterative rounds.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

analogical-transfer

Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

anti-benchmark

Challenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

appropriateness-bounding

Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

atomic-unit-matching

Judge, per atomic content unit, whether a target text (summary, abstract, or other candidate text) contains it — binary present/absent (ACU) or ternary support/partial_support/not_support (Nugget), per caller's value domain. Use this after atomic-unit-writing has produced the reference units, as the matching step before recall aggregation.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

atomic-unit-writing

Extract (ACU-style) or freshly author (Nugget-style) a list of atomic content units from a paper, optionally tagged vital/okay for importance. Use this as the first step whenever building a reference set of atomic facts for later recall-checking a summary or abstract against the paper — always precedes atomic-unit-matching.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

claim-label-prediction

Judge a three-way SUPPORTS/REFUTES/NOINFO label for an atomic claim, based only on its selected rationale sentences (SciFact's final classification step). Use this after rationale-selection has produced the evidence sentences — this is the terminal step of the SciFact chain, producing the complete (claim, abstract, label, rationale) tuple.

392 Updated 1 weeks ago
yogsoth-ai
Testing & QA Featured

qalmri

Produce a six-slot QALMRI worksheet (Question, Alternatives, Logic, Method, Results, Inference) as free-text notes on one paper — a structured note-taking format, not a scored evaluation. Use this whenever the user wants a QALMRI-style reading worksheet for a specific paper.

392 Updated 1 weeks ago
yogsoth-ai
Code & Development Featured

qasper-evidence-qa

Answer a specific question about a paper, grounding the answer in exact quoted evidence spans from the text (QASPER-style question-driven QA with span-level evidence, no schema categorization). Use this whenever the user asks a specific factual question about a paper and wants the answer traceable to exact text spans.

392 Updated 1 weeks ago
yogsoth-ai
AI & Automation Featured

abstraction-ladder

Perform bisociation at multiple abstraction levels

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

alias-resolution

SOP for detecting and resolving concept aliases — merge duplicate pages, redirect edges.

378 Updated 6 days ago
yogsoth-ai
Data & Documents Featured

analogy-extraction

Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

appreciative-reframing

Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.

378 Updated 6 days ago
yogsoth-ai
Code & Development Featured

injection-fidelity

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.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

ladder-quality-order

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 standards.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

optimization-loop

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 scripted; only the backprop attribution is a judgment call.

378 Updated 6 days ago
yogsoth-ai
AI & Automation Featured

repo-dependency-graph

Reconstruct a DARE skill repo's true use-dependency relations and render them as a self-contained, offline, Obsidian-style interactive HTML graph (pyvis / vis-network). Use this whenever the user wants to graph / map / visualize the skill dependencies of a repo or package, "画依赖图 / graph 化这个 repo / 把 skill 连边画出来 / 用 pyvis 出个图 / skill 关系图", or to audit how campaign→strategy→ tactic→sop skills connect. Trigger even if the user just says "给这个 package 做个图" without naming pyvis or HTML. Goes straight to HTML — never write an intermediate mermaid markdown first.

378 Updated 6 days ago
yogsoth-ai
Code & Development Featured

formated-results

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.

378 Updated 6 days ago
yogsoth-ai
Code & Development Featured

formated-specs

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.

378 Updated 6 days ago
yogsoth-ai
Data & Documents Solid

paper-fetch

Retrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly with no search at all, while other references use alphaxiv, Semantic Scholar routing, then bioRxiv/medRxiv. Use this as the mandatory first step whenever any other paper-reading SOP in this package needs the actual text of a paper — it is the sole entry point of the pipeline and every downstream SOP reads the files it lands, so do not bypass it even when the caller already has the file. If it returns not_found, halt immediately; do not fabricate content or guess at the paper's likely contents.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

acu-nugget-recall

Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

argumentative-zoning

Tactic: Label every sentence of one paper with its rhetorical role using Argumentative Zoning. Use when fixed rhetorical labels and cross-paper alignment matter.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

atomic-unit-recall-aggregate

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.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

claim-writing

Blind-rewrite a citing sentence (citance) from another paper into a single atomic, independently-verifiable claim (SciFact's annotation protocol) — never looking at the cited paper's content while rewriting. Use this when you have a specific citing sentence and want it decomposed into checkable atomic claims, as the first step before rationale-selection and claim-label-prediction.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

domain-level-judgment

Fold raw signalling-question answers into domain-level judgments for RoB2, ROBINS-I, or QUADAS-2, per each tool's own lookup rules — the first of two aggregation levels these tools define. QUADAS-2 is dual-axis (risk-of-bias AND applicability-concern per domain, D1-D3) and terminates here with no further rollup; RoB2/ROBINS-I continue on to worst-case-lookup for an overall verdict. Use this after signalling-question-answering has produced the raw answers.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

dual-column-self-check

Run one of the ML/CS reproducibility checklists (ML Reproducibility Checklist, REFORMS, NeurIPS Paper Checklist, Model Cards, Datasheets for Datasets) against a paper as a reader-side audit, producing a category (Yes/No/NA) plus free-text reason per item. Use this whenever the user wants a reproducibility/completeness self-check run on an ML or CS paper — invoke this directly, it has no study-design gate in this package since these checklists are engineering self-audits, not clinical-study tools.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

engineering-config-grading

(Proposal, unverified) Grade reproducibility-relevant engineering configuration items (hyperparameter search range, compute budget, seed handling, dataset splits) on a complete/partial/none scale, requiring the grader to first define what "complete" means per item before judging against it. Use this after study-design-tool-gate has dispatched an ML/CS engineering paper here; this is a graded QUALITY judgment, distinct from dual-column-self-check's binary Yes/No/NA self-audit checklists.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

first-pass-skim

Five-minute skim pass over a single academic paper (title, abstract, headings, figures, conclusion only) to classify the paper's type and draft candidate public-audience angles before any deep reading happens. Use this as the entry point whenever the user gives you one specific paper to summarize, explain, or turn into a WeChat/blog article, and you haven't classified the paper yet. Always run this before second-pass-grasp.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

keshav-three-pass

Tactic: Read one paper by Keshav's three-pass method — a shallow skim, a contribution-grasping full read, then a deep virtual re-implementation. Use when the goal is understanding a paper rather than extracting a fixed schema.

1 Updated 1 weeks ago
yogsoth-ai
Data & Documents Listed

multi-stage-cascade-extraction

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.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

qalmri-worksheet

Tactic: Fill a six-slot QALMRI worksheet for one paper: Question, Alternatives, Logic, Method, Results, and Inference. Use for a structured reading worksheet rather than a graded evaluation.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

question-framing

Fill a slot-based question-framing schema (PICO, PECO, or SPIDER) from a paper's stated research question. Use this whenever the user wants a paper's research question structured into one of these standard clinical/qualitative-research question frames; this frames what question is being asked, it does not read or evaluate the paper's content otherwise.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

rationale-selection

Select the minimal set of 1-3 verbatim sentences from a candidate paper/abstract sufficient to entail or refute an atomic claim (SciFact's rationale-selection step). Use this after claim-writing has produced an atomic claim, as the evidence-gathering step before claim-label-prediction; an empty rationale set is a valid outcome, not an error.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

reforms-grading

Tactic: Grade an ML/CS paper's reproducibility configuration reporting as complete, partial, or none after checking that clinical appraisal tools do not apply. Use when the question is whether the work can be rerun.

1 Updated 1 weeks ago
yogsoth-ai
AI & Automation Listed

reporting-standard-checklist

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.

1 Updated 1 weeks ago
yogsoth-ai

Showing top 100 of 130 skills by quality score. Browse the full catalog at /browse.

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.