Papers
566 skills in Research > Papers
exploration-continue
Resume exploration from where previous Claude session left off by reading the exploration journal (docs/exploration/). Use at start of session when user says "continue", "resume", or "pick up where we left off".
context-saver
Automatically save exploration findings, discoveries, and current state to the exploration journal (docs/exploration/). Use when making important discoveries or completing a phase of work. Ensures future Claude sessions can continue where this session left off.
atris
Atris workflow enforcement for repos using atris/ (MAP, TODO, journal, features, plan-do-review, anti-slop). Use when the user asks to follow the Atris system or mentions atris, MAP.md, TODO.md, journal/logs, features, plan/do/review, or anti-slop policies.
research-synthesis
Synthesize research findings for OAK planning using the oak.plan-research workflow. Use when consolidating findings from codebase exploration, comparing approaches, or creating research/*.md documents.
lobster-bioinformatics
Run bioinformatics analyses using Lobster AI - single-cell RNA-seq, bulk RNA-seq, literature mining, dataset discovery, quality control, and visualization. Use when analyzing genomics data, searching for papers/datasets, or working with H5AD, CSV, GEO/SRA accessions, or biological data. Requires lobster-ai package installed.
lean4-theorem-proving
Use when developing Lean 4 proofs, facing type class synthesis errors, managing sorries/axioms, or searching mathlib - provides build-first workflow, instance management patterns (haveI/letI), and domain-specific tactics
reasoning
MANDATORY structured reasoning framework for complex analysis. Provides dependency analysis, risk assessment, hypothesis formation, and action inhibition patterns.
debugging
MANDATORY for ANY bug, test failure, or unexpected behavior - four-phase systematic framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions. CONSULT THIS SKILL if you find yourself having to fix bugs, test failures, or unexpected behavior.
deep-research
This skill should be used when users request comprehensive, in-depth research on a topic that requires detailed analysis similar to an academic journal or whitepaper. The skill conducts multi-phase research using web search and content analysis, employing high parallelism with multiple subagents, and produces a detailed markdown report with citations.
starwards-debugging
Systematic debugging for Starwards - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with Colyseus state inspection, Tweakpane debugging, multiplayer sync issues, and monorepo-specific troubleshooting
Logs Analysis
Analyze system and application log data from sosreport archives, extracting error patterns, kernel panics, OOM events, service failures, and application crashes from journald logs and traditional log files within the sosreport directory structure to identify root causes of system failures and issues
whitepapers
Use when producing research-heavy whitepapers or technical guides that require structured argumentation and data.
insight-synthesis
Use to convert raw customer feedback into compelling narratives, themes, and recommendations.
media-database
Use when researching, segmenting, and maintaining journalist/analyst contact lists.
update-publications
Updates the Monarch Initiative publications page with latest data from Google Scholar. Use this when the user asks to update publications, refresh citation metrics, or add new papers to the publications page.
Exploratory Data Analysis
Discover patterns, distributions, and relationships in data through visualization, summary statistics, and hypothesis generation for exploratory data analysis, data profiling, and initial insights
Statistical Hypothesis Testing
Conduct statistical tests including t-tests, chi-square, ANOVA, and p-value analysis for statistical significance, hypothesis validation, and A/B testing
financial-close
Month-end and year-end close workflow covering journal entries, reconciliations, close procedures, and audit preparation. Delivers accurate, timely close with full audit trail.
property-based-testing
Design property-based tests that verify code properties hold for all inputs using automatic test case generation. Use for property-based, QuickCheck, hypothesis testing, generative testing, and invariant verification.
systematic-debugging
Four-phase debugging framework - root cause investigation, pattern analysis, hypothesis testing, implementation. Ensures understanding before attempting fixes.