Research Agora

Write, improve, or diagnose abstracts for ML conference papers. Use when asked to "write abstract", "improve abstract", "draft abstract", "summarize p...more

Write, improve, or diagnose abstracts for ML conference papers. Use when asked to "write abstract", "improve abstract", "draft abstract", "summarize paper", "abstract for submission", "audit my abstract", "diagnose abstract", "check my abstract", or "abstract feedback". Structures context, problem, approach, results, and impact.less

Write or improve discussion and limitations sections for ML conference papers. Use when asked to "write discussion", "add limitations", "discuss resul...more

Write or improve discussion and limitations sections for ML conference papers. Use when asked to "write discussion", "add limitations", "discuss results", "write conclusion", or "identify weaknesses". Generates balanced analysis of contributions, implications, and honest limitations.less

Write experimental details sections for ML papers with GitHub repository integration. Use when asked to "write experiments section", "document experim...more

Write experimental details sections for ML papers with GitHub repository integration. Use when asked to "write experiments section", "document experimental setup", "describe methodology", "write reproducibility details", or "experimental details". Extracts information from code to ensure accuracy.less

Write or improve introduction sections for ML conference papers. Use when asked to "write introduction", "improve intro", "draft intro", "motivate the...more

Write or improve introduction sections for ML conference papers. Use when asked to "write introduction", "improve intro", "draft intro", "motivate the paper", or "write opening". Structures motivation, problem statement, contributions, and paper outline.less

Summarize research papers for rapid triage and comprehension. Use when asked to "summarize this paper", "paper summary", "what does this paper do", "t...more

Summarize research papers for rapid triage and comprehension. Use when asked to "summarize this paper", "paper summary", "what does this paper do", "triage papers", or "TLDR this paper". Takes an arXiv ID or paper text and produces structured summaries at configurable depth.less

Fact-check references in ML paper drafts. Use when asked to "verify citations", "check references", "fact-check bibliography", "validate citations", o...more

Fact-check references in ML paper drafts. Use when asked to "verify citations", "check references", "fact-check bibliography", "validate citations", or "audit references". Verifies papers exist on arXiv, checks author names, years, and titles against actual publications.less

Generate critical reviews of ML paper drafts simulating a skeptical reviewer. Use when asked to "review my paper", "find weaknesses", "critique this d...more

Generate critical reviews of ML paper drafts simulating a skeptical reviewer. Use when asked to "review my paper", "find weaknesses", "critique this draft", "what would reviewers say", or "assess my submission". Provides harsh but constructive feedback to strengthen the paper before submission.less

Verify experimental claims in ML papers against source code repositories. Use when asked to "verify experiments", "check claims against code", "fact-c...more

Verify experimental claims in ML papers against source code repositories. Use when asked to "verify experiments", "check claims against code", "fact-check results", "audit experiments", or "validate paper against repo". Cross-references paper statements with actual implementation.less

Deep verify ALL paper claims with systematic evidence hierarchy. NOW SUPPORTS PARALLEL MODE via parallel-audit orchestrator for 2-3x speedup. Activate...more

Deep verify ALL paper claims with systematic evidence hierarchy. NOW SUPPORTS PARALLEL MODE via parallel-audit orchestrator for 2-3x speedup. Activates when asked to "audit claims", "verify claims", "check paper claims", "claim verification", "evidence check", "verify evidence", or "quick evidence scan". Includes Quick Mode for rapid brainstorming checks.less

Use this agent to simulate a first-time reader walking through your text. Activates when asked to "simulate reader", "where will readers get confused"...more

Use this agent to simulate a first-time reader walking through your text. Activates when asked to "simulate reader", "where will readers get confused", "reader experience", "comprehension check", or "reader perspective". Flags assumed knowledge, jargon cliffs, logical jumps, and points where readers will zone out.less

Use this agent to verify statistical rigor in ML papers - p-values, confidence intervals, significance tests, effect sizes. Activates when asked to "v...more

Use this agent to verify statistical rigor in ML papers - p-values, confidence intervals, significance tests, effect sizes. Activates when asked to "validate statistics", "check statistical rigor", "verify p-values", "statistical validation", or "check significance".less

Comprehensive pre-submission paper audit combining reviewer simulation, claim verification, clarity analysis, notation checking, and statistical valid...more

Comprehensive pre-submission paper audit combining reviewer simulation, claim verification, clarity analysis, notation checking, and statistical validation. Use when asked to "audit before submission", "pre-submission check", "is my paper ready", "self-review", or "submission readiness". Runs 5 diagnostic passes in parallel and produces a unified readiness report.less

Analyze convergence rates, complexity bounds, and approximation guarantees. The theoretical analogue of statistical-validator. Compares to known optim...more

Analyze convergence rates, complexity bounds, and approximation guarantees. The theoretical analogue of statistical-validator. Compares to known optimal rates and checks dimensional consistency. Trigger: "analyze bounds", "check convergence rate", "verify complexity", "bounds analysis".less

Stress-test theorems by systematically exploring what happens when assumptions are dropped or weakened. Generates low-dimensional test cases and bound...more

Stress-test theorems by systematically exploring what happens when assumptions are dropped or weakened. Generates low-dimensional test cases and boundary conditions. Trigger: "find counterexample", "stress test theorem", "test assumptions", "break this theorem", "assumption necessity".less

Translate informal mathematical intuitions into formal theorem statements with explicit quantifiers, conditions, and conclusions. Offers multiple form...more

Translate informal mathematical intuitions into formal theorem statements with explicit quantifiers, conditions, and conclusions. Offers multiple formalizations at different strength levels. Trigger: "formalize intuition", "make this precise", "formal version", "state theorem formally", "formalize this claim".less

Build a symbol table and check notation consistency throughout a paper. Detects overloaded symbols, undefined notation, and convention violations. Hyb...more

Build a symbol table and check notation consistency throughout a paper. Detects overloaded symbols, undefined notation, and convention violations. Hybrid: script-based regex extraction + LLM semantic analysis. Trigger: "check notation", "notation consistency", "symbol table", "find notation issues", "verify notation".less

Decompose proofs into logical steps, check each step follows from prior ones, identify assumption usage, and flag gaps or unjustified leaps. The theor...more

Decompose proofs into logical steps, check each step follows from prior ones, identify assumption usage, and flag gaps or unjustified leaps. The theoretical analogue of claim-auditor. Trigger: "audit proof", "check proof", "verify proof", "proof verification", "find proof gaps".less

Given a theorem to prove or conjecture to investigate, suggests proof approaches drawn from a broad knowledge of techniques. Classifies result type, r...more

Given a theorem to prove or conjecture to investigate, suggests proof approaches drawn from a broad knowledge of techniques. Classifies result type, recommends strategies, suggests intermediate lemmas, and identifies key technical challenges. Trigger: "suggest proof strategy", "how to prove", "proof approach", "proof technique", "prove this theorem".less

Build a DAG of theorem/lemma/proposition dependencies across the paper. Computes criticality scores, maps assumption flow, and detects orphan lemmas o...more

Build a DAG of theorem/lemma/proposition dependencies across the paper. Computes criticality scores, maps assumption flow, and detects orphan lemmas or circular dependencies. Trigger: "map theorem dependencies", "theorem DAG", "dependency graph", "trace assumptions".less

Identify cross-domain connections between a theoretical result and results from other subfields. Find structural analogies, vocabulary translations, a...more

Identify cross-domain connections between a theoretical result and results from other subfields. Find structural analogies, vocabulary translations, and generalization paths. Trigger: "connect to other fields", "cross-domain connections", "related theory", "theory bridge", "find analogous results".less

Identify relevant benchmarks and generate experiment plans for ML papers. Use when asked to "find benchmarks", "what datasets should I use", "experime...more

Identify relevant benchmarks and generate experiment plans for ML papers. Use when asked to "find benchmarks", "what datasets should I use", "experiment plan", "baseline comparison", "standard evaluation", "what to compare against", or "evaluation protocol". Searches arXiv for benchmark papers and extracts evaluation protocols.less

Sync ML experiment results to paper drafts. Use when asked to "update results", "sync experiments", "pull latest metrics", "update tables from code", ...more

Sync ML experiment results to paper drafts. Use when asked to "update results", "sync experiments", "pull latest metrics", "update tables from code", "experiment to paper", "refresh results", or "sync paper with repo". Extracts metrics from code/logs and updates paper sections.less

Write related work sections and discover relevant literature for ML papers. Use when asked to "write related work", "find related work", "literature r...more

Write related work sections and discover relevant literature for ML papers. Use when asked to "write related work", "find related work", "literature review", "survey the field", "find papers on [topic]", "build bibliography", "survey prior work", "position the paper", or "what papers should I cite". Supports both guided mode (provide papers to include) and autonomous mode (multi-query arXiv searches with paper approval workflow).less

Use this agent to map blog posts or essays into book structure. Activates when asked to "audit my content", "blog to book", "cluster my posts", "conte...more

Use this agent to map blog posts or essays into book structure. Activates when asked to "audit my content", "blog to book", "cluster my posts", "content audit", or "find themes across posts". Performs thematic clustering, gap analysis, and generates book conversion strategies from dispersed content.less

Use this agent to challenge arguments, identify logical fallacies, and expose cognitive biases. Supports iterative refinement through constructive adv...more

Use this agent to challenge arguments, identify logical fallacies, and expose cognitive biases. Supports iterative refinement through constructive adversarial thinking. Invoke during brainstorming, hypothesis formation, or before committing to claims.less

Use this agent to synthesize different perspectives, methodologies, or research approaches into unified frameworks. Invoke for literature review synth...more

Use this agent to synthesize different perspectives, methodologies, or research approaches into unified frameworks. Invoke for literature review synthesis, reconciling conflicting findings, bridging research communities, or resolving disagreements.less

Critiques a prompt using the RIOT framework and teaches one transferable lesson. Use when asked to "review my prompt", "improve this prompt", "why isn...more

Critiques a prompt using the RIOT framework and teaches one transferable lesson. Use when asked to "review my prompt", "improve this prompt", "why isn't my prompt working", "score my prompt", "make this prompt better", "diagnose my prompt", "fix my prompt", or "what's wrong with this prompt". User pastes a prompt; skill scores each RIOT component, identifies the failure mode, and generates an improved version with minimal changes.less

Add @latex decorators to existing functions to link them with paper equations. Use when asked to "annotate functions", "link functions to equations", ...more

Add @latex decorators to existing functions to link them with paper equations. Use when asked to "annotate functions", "link functions to equations", "add equation decorators", or "connect code to LaTeX".less

Initialize latex-code-sync in a project. Use when asked to "set up equation verification", "link paper to code", "initialize latex-code-sync", or "set...more

Initialize latex-code-sync in a project. Use when asked to "set up equation verification", "link paper to code", "initialize latex-code-sync", or "set up paper-code synchronization". Creates equations module, configuration, and optionally CI workflow.less

Run verification between paper equations and code implementations. Use when asked to "verify equations", "check paper-code consistency", "run equation...more

Run verification between paper equations and code implementations. Use when asked to "verify equations", "check paper-code consistency", "run equation tests", or "validate implementations match paper".less

Enforce consistent LaTeX formatting for ML conference papers. Use when asked to "fix LaTeX", "make LaTeX consistent", "format paper", "check LaTeX sty...more

Enforce consistent LaTeX formatting for ML conference papers. Use when asked to "fix LaTeX", "make LaTeX consistent", "format paper", "check LaTeX style", or "standardize notation". Covers math notation, references, tables, and common ML conventions.less

Use this agent to evaluate papers, presentations, posters, or communications for target audience alignment. Impersonates different reader personas (re...more

Use this agent to evaluate papers, presentations, posters, or communications for target audience alignment. Impersonates different reader personas (reviewers, industry engineers, students, experts) to identify jargon, unclear explanations, and narrative gaps.less

Use this agent to parse LaTeX .log files, diagnose compilation errors, and provide targeted fixes. Activates when asked to "debug latex", "fix latex e...more

Use this agent to parse LaTeX .log files, diagnose compilation errors, and provide targeted fixes. Activates when asked to "debug latex", "fix latex errors", "parse log file", "latex compilation error", or "why won't my paper compile".less

Use this agent to find semantic overlap and redundancy across documents. Activates when asked to "find redundancies", "am I repeating myself", "duplic...more

Use this agent to find semantic overlap and redundancy across documents. Activates when asked to "find redundancies", "am I repeating myself", "duplicate content", "overlap detection", or "merge candidates". Clusters similar content and suggests merge strategies.less

Use this agent to detect voice inconsistency across chapters, blog posts, or documents. Activates when asked to "check voice consistency", "tone drift...more

Use this agent to detect voice inconsistency across chapters, blog posts, or documents. Activates when asked to "check voice consistency", "tone drift", "does this sound like me", "voice fingerprint", or "style consistency check". Quantifies rhythm, formality, person, and metaphor density to flag unintentional drift.less

Visualize the logical skeleton of a paper's argument as a claim-evidence DAG. Use when asked to "map my argument", "does my logic hold", "argument str...more

Visualize the logical skeleton of a paper's argument as a claim-evidence DAG. Use when asked to "map my argument", "does my logic hold", "argument structure", "find logical gaps", or "why doesn't my paper flow". Flags missing links, orphan claims, circular reasoning, and unsupported assertions.less

Context-aware editorial intelligence that adapts to what you're writing. Use when asked to "edit this", "review my writing", "editorial feedback", "de...more

Context-aware editorial intelligence that adapts to what you're writing. Use when asked to "edit this", "review my writing", "editorial feedback", "developmental edit", "line edit", "improve clarity", "simplify writing", "check readability", "reduce jargon", or "make paper clearer". Detects format (paper/blog/book/grant), section type, and draft phase, then routes to the appropriate editorial lens — developmental, line, or copy editing.less

Translate writing between registers — paper to blog, blog to book chapter, academic to conversational. Use when asked to "convert this for blog", "mak...more

Translate writing between registers — paper to blog, blog to book chapter, academic to conversational. Use when asked to "convert this for blog", "make this more conversational", "translate register", "paper to blog", "blog to book", or "adapt for audience". Performs structural transformation, not just tone adjustment.less

Diagnose root causes of bad writing at the paragraph level. Use when asked to "diagnose this paragraph", "why does this suck", "what's wrong with this...more

Diagnose root causes of bad writing at the paragraph level. Use when asked to "diagnose this paragraph", "why does this suck", "what's wrong with this", "writing diagnosis", or "debug my writing". Identifies patterns like cognitive overload, buried ledes, idea soup, and monotonous rhythm — then teaches the fix.less

Quantitative writing quality verification for scientific papers. Use when asked to "score my writing", "grade this paper", "writing quality check", "v...more

Quantitative writing quality verification for scientific papers. Use when asked to "score my writing", "grade this paper", "writing quality check", "verify writing quality", "how good is my writing", "rate my prose", "writing metrics", "readability analysis", "check my paper's clarity", "writing score", or "assess writing quality". Produces a structured report with A-F grade, dimension scores, and prioritized fix suggestions.less

Create academic conference posters from research papers. Use when asked to "create poster", "make poster", "turn paper into poster", "poster for confe...more

Create academic conference posters from research papers. Use when asked to "create poster", "make poster", "turn paper into poster", "poster for conference".less

Create presentation slides from research papers for talks and seminars. Use when asked to "create slides", "make presentation", "turn paper into slide...more

Create presentation slides from research papers for talks and seminars. Use when asked to "create slides", "make presentation", "turn paper into slides", "prepare talk".less

Create animated GIFs to communicate ML research visually for Twitter/X, GitHub READMEs, and project websites. Use when asked to "create science gif", ...more

Create animated GIFs to communicate ML research visually for Twitter/X, GitHub READMEs, and project websites. Use when asked to "create science gif", "animate results", "make animated figure", "gif for twitter", "animate method", "visualize algorithm".less

Use this agent to generate publication-quality figures with narrative focus. Activates when asked to "create figure", "figure storytelling", "visualiz...more

Use this agent to generate publication-quality figures with narrative focus. Activates when asked to "create figure", "figure storytelling", "visualize results", "make publication figure", "data visualization", "create plots", "make figures publication ready", "format for conference", "style matplotlib", "improve figure quality", "publication figure", "matplotlib figure", "conference figure", or "plot results".less

Prepare OpenReview submission metadata from a paper draft. Use when asked to "prepare OpenReview submission", "format abstract for OpenReview", "gener...more

Prepare OpenReview submission metadata from a paper draft. Use when asked to "prepare OpenReview submission", "format abstract for OpenReview", "generate keywords", "write TL;DR", "create lay summary", "submission form", or "camera-ready metadata". Produces copy-pasteable abstract, keywords, TL;DR, and lay summary.less

Triage and prioritize revision work after receiving peer reviews. Decodes reviewer subtext and plans strategic responses. Use when asked to "triage re...more

Triage and prioritize revision work after receiving peer reviews. Decodes reviewer subtext and plans strategic responses. Use when asked to "triage reviews", "plan my revision", "revision strategy", "prioritize reviewer comments", "what should I fix first", "decode reviewer feedback", or "what do reviewers really mean". Step 1 of a 2-step pipeline (review-triage → reviewer-response-generator).less

Use this agent to prepare ML code/data/models for public release with comprehensive checklists. Activates when asked to "package artifacts", "prepare ...more

Use this agent to prepare ML code/data/models for public release with comprehensive checklists. Activates when asked to "package artifacts", "prepare release", "reproducibility checklist", "code release", or "prepare camera ready".less

Unified rebuttal writing agent with Quick Mode (template-driven) and Deep Mode (evidence-backed with code/data proof). Activates when asked to "write ...more

Unified rebuttal writing agent with Quick Mode (template-driven) and Deep Mode (evidence-backed with code/data proof). Activates when asked to "write rebuttal", "respond to reviewers", "reviewer response", "address reviewer comments", "draft rebuttal", or "rebuttal draft". Step 2 of the rebuttal pipeline (review-triage → reviewer-response-generator). Deep Mode searches GitHub for baselines and arXiv for supporting citations.less

Interactive decision tree for finding the right Research Agora skill. Use when asked to "which skill should I use", "what skill do I need", "find me a...more

Interactive decision tree for finding the right Research Agora skill. Use when asked to "which skill should I use", "what skill do I need", "find me a skill for", "I want to do X what skill helps", "help me pick a skill", "what can the Agora do for", "I need help with X", "recommend a skill", or "what skills exist for". Maps a natural-language task description to the most relevant skills with confidence scores and example invocations.less

Scans the current directory and recommends the single fastest Research Agora "wow moment". Use when asked for "quick start", "what should I run first"...more

Scans the current directory and recommends the single fastest Research Agora "wow moment". Use when asked for "quick start", "what should I run first", "fastest result", "show me something useful", "I want to try this", "give me a demo", "what can I do right now", "get me started fast", "what's the best first thing to try", or "impress me". Auto-detects project contents and returns THE single best skill to run right now, with the exact command using the user's actual filenames.less

Personalized Research Agora setup via scripts/onboard.py

Changelog skill for returning users. Summarizes what changed in the Research Agora since a given date or reference point. Use when asked "what's new",...more

Changelog skill for returning users. Summarizes what changed in the Research Agora since a given date or reference point. Use when asked "what's new", "what changed since I last used this", "what's been added", "catch me up", "what skills are new", "what changed last month", "any updates", "what did I miss", "has anything changed since [date]", "what's different", "changelog", "view changelog", or "bring me up to speed". Reads CHANGELOG.md and git log to produce a researcher-friendly summary with "try these new skills" recommendations.less

Health check for the user's Research Agora configuration. Reads CLAUDE.md files, checks installed plugins, MCP servers, hooks, and privacy settings. U...more

Health check for the user's Research Agora configuration. Reads CLAUDE.md files, checks installed plugins, MCP servers, hooks, and privacy settings. Use when asked to "audit my setup", "check my configuration", "am I set up correctly", "health check my Agora", "what am I missing", "how mature is my setup", "review my CLAUDE.md", "is my configuration good", or "help me level up my config". Produces a scored health report with specific, actionable recommendations.less

Analyze and refactor Python codebases to remove dead code, eliminate duplication, and simplify complexity. Use when asked to "simplify code", "remove ...more

Analyze and refactor Python codebases to remove dead code, eliminate duplication, and simplify complexity. Use when asked to "simplify code", "remove dead code", "find duplicates", "refactor", "clean up codebase", or "reduce complexity".less

Commit changes made during the current conversation. Use when asked to "commit", "save changes", "create a commit", or "commit my changes". Generates ...more

Commit changes made during the current conversation. Use when asked to "commit", "save changes", "create a commit", or "commit my changes". Generates conventional commit messages with co-authorship attribution.less

Generate HTCondor submission files and wrapper scripts for ML research jobs. Use when asked to "create condor job", "submit to cluster", "write .sub f...more

Generate HTCondor submission files and wrapper scripts for ML research jobs. Use when asked to "create condor job", "submit to cluster", "write .sub file", "htcondor setup", "cluster job", or "batch submission". Supports GPU/CPU jobs, parameter sweeps, multi-seed experiments, and ablation studies.less

Create GitHub pull requests from changes made during a chat session. Use when asked to "create a PR", "open a pull request", "submit changes", "push a...more

Create GitHub pull requests from changes made during a chat session. Use when asked to "create a PR", "open a pull request", "submit changes", "push and create PR", or at the end of a coding session when changes should be submitted for review. Handles branch creation, conventional commits, and PR description generation.less

Set up Python CI/CD with GitHub Actions, pre-commit hooks, and code quality tools. Use when asked to "set up CI/CD", "add pre-commit hooks", "configur...more

Set up Python CI/CD with GitHub Actions, pre-commit hooks, and code quality tools. Use when asked to "set up CI/CD", "add pre-commit hooks", "configure GitHub Actions", "add linting", or "set up testing pipeline". Configures Black, isort, flake8, and pytest for Python 3.11.less

Create TikZ/PGF figures for ML papers including neural networks, flowcharts, diagrams, and graphs. Use when asked to "create TikZ figure", "draw neura...more

Create TikZ/PGF figures for ML papers including neural networks, flowcharts, diagrams, and graphs. Use when asked to "create TikZ figure", "draw neural network", "make diagram in LaTeX", "TikZ flowchart", or "create architecture diagram".less

Create and edit Word documents using python-docx

Create and edit PowerPoint presentations using python-pptx

Create and edit Excel spreadsheets using openpyxl