Find and read academic papers (S2 + arXiv). Disambiguate ambiguous queries, search by keyword + citation graph + recommendations + snippets, judge by author-graded rubric, and read with L1/L2/L3 strategy. Trigger phrases: find papers, search papers, related work, citation analysis, recent advances, read this paper, baseline with code. Do NOT use for: survey reports (research-survey), idea generation (research-ideation), Related Work sections (paper-writing).
Use this skill whenever the user submits a non-trivial mathematical claim that needs a rigorous proof or audit. Trigger on IMO/Putnam/USAMO/Olympiad-style problems, ML/AI theoretical statements, research conjectures, suspected-false claims, multi-step proofs the user already failed on, proof drafts with possible hidden assumptions, or any request containing 'prove rigorously', 'verify this', 'is this true', 'find the gap', 'audit my proof', 'find a counterexample', or 'use EvoMath' that targets a mathematical claim. Activate also when the problem requires more than three reasoning steps. Do NOT use for single-step calculations, definition lookups, textbook exercises with a known recipe, code analysis tasks, literature survey questions, pure symbolic manipulation, or non-mathematical applications of those trigger phrases (e.g., 'is it true that GPT-4 can solve math?', 'verify this LaTeX syntax'); hand those back instead.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after research-ideation), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing research-ideation cycles or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use research-ideation).
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and experiment-craft (5-step diagnostic on failure). Use when: user has a planned experiment, needs to reproduce baselines, organize experiment workflow, or systematically validate a method. Do NOT use for debugging a specific experiment failure (use experiment-craft) or designing which experiments to run (use paper-planning).
End-to-end research ideation pipeline: literature grounding → multi-track idea generation (3 personas: innovator/pragmatist/critic) → iterative refinement → ELO tournament ranking → update evo-memory (IDE) → user selects direction → expand into manuscript-quality proposal. Use when: user wants to find a research direction, brainstorm ideas, evaluate idea novelty, design a novel solution, rank/compare research ideas, or generate a research proposal. Do NOT use for finding/searching/reading papers (use paper-navigator), literature survey reports (use research-survey), or planning a paper (use paper-planning).
Generates structured literature survey reports from collected papers using a multi-stage pipeline: outline generation (query-type adaptive) → draft survey → section-by-section expansion → summary section refinement → final assembly. Produces survey-grade output with taxonomy-based method analysis, LaTeX formalizations, comparative tables, and dense citations. Use when: user wants a literature review, research survey, field overview, or systematic synthesis of multiple papers. Do NOT use for finding/searching papers (use paper-navigator), generating research ideas (use research-ideation), or writing a paper's Related Work section (use paper-writing).
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing. Full workflow: content planning conversation → slides_plan.json → batch image generation → review with feedback → targeted slide editing → PPTX packaging. Use when: user wants to create a presentation, make slides, generate a PPT/PPTX, prepare a talk deck, design visual slide content, or generate high-quality figures/illustrations for papers and documents. Do NOT use for: writing academic papers (use paper-writing) or planning academic conference talk narrative structure (use academic-slides).
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent delegates a code task with 'MODE: MORE_EFFORT', the user selects 'More Effort' code generation mode, or the task explicitly requests iterative refinement for higher code quality. Do NOT use for single-pass code generation (Lite mode), experiment pipeline orchestration (use experiment-pipeline), or diagnosing a specific experiment failure (use experiment-craft).