Menu
Skills in this repository
SkillsMP has collected 109 skills from flonat/claude-research. Open a skill to review its source and details.
flonat/claude-researchShowing 40 of 109 collected skills.
Convert an accepted anonymous-submission LaTeX paper (AAAI/AIES/ACM-style) to camera-ready and implement the accepted reviews. Use when a paper is accepted with no rebuttal and you need to de-anonymize, add copyright, turn on section numbering, implement each…
Use when you need OpenAI Codex (gpt-5.5) as an adversarial mathematical co-processor — verify, write, and explore modes for hard proofs, counterexample search, and independent verification. Treat every output as a lead, not a verdict.
Use when you need to scaffold, run, or publish computational research experiments.
Use when you need to replicate a quantitative analysis in a second language (R↔Python↔Stata↔Julia) to verify correctness. Level 1 of the verification hierarchy.
Use when you need an end-to-end analysis pipeline: EDA, estimation, or publication output.
Review user-facing documentation for accuracy, consistency, and completeness across private, public, nested repos, and the user manual. Use when docs feel stale, after major changes, or before sharing. (Replaces `/repo-doc-audit`)
Use when you need power analysis, pre-analysis plans, QSF parsing, or survey design.
"Use when you need to see what changed between two versions of a LaTeX document — two files, two project directories, or two git revisions. Produces a human-readable change summary plus a machine-readable, severity-graded list of semantic changes."
Use when /latex reports a clean build but the document still needs a deeper visual-quality review. Runs the Phase 4 source-pathology lint AND renders selected PDF pages to images for vision-model inspection, catching rendered-output issues that grep cannot —…
Use when you need to create a research poster in LaTeX (beamerposter, tikzposter, or baposter).
Write clear, detailed mathematical proofs for academic papers. Use when the user asks to prove a result, derive an equation, justify a claim analytically, or expand a proof sketch into a full proof. Also trigger on "prove", "show analytically", "derive",…
Guide for creating MCP servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use when you need to extract and compare data collection methods across empirical papers.
Use when you need to numerically stress-test / falsify a SELF-AUTHORED mathematical claim — monotonicity, threshold, comparative-static, inequality, closed-form, or limit — by Monte-Carlo/sweep over its parameter space. Finds a counterexample (definitive…
Use when you need to automate browser interactions, test web pages and work with Playwright tests.
Use when you need a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), and hardcoded secrets. Triggers: 'audit before commit', 'check before push', 'pre-commit scan', 'safety check'.
Use when you need to improve the readability and exposition of mathematical proofs already verified as correct, without changing their mathematical content — polish or edit a proof, lemma, or appendix; after a proof has been written and verified; or on "make…
Use when you need Python environment management with uv (install, create venv, manage deps).
Use when you need to audit which findings in a literature have been replicated or failed.
Systematic reviewer response workflow: parse comments, classify by severity, develop response strategy, write structured rebuttal. Use when asked to 'write rebuttal', 'respond to reviewers', 'draft review response', or 'handle R&R'.
Use when you need to create, modify, or measure performance of skills.
Use when you need to symbolically verify a SELF-AUTHORED algebra step, derivative, limit, comparative-static sign, or closed-form identity using a CAS (sympy) — proving or refuting it, not just stress-testing. R2 of the verification spectrum: unlike…
Use when you need to synthesise parallel review reports into a prioritised revision plan.
Use when you need to generate structurally realistic synthetic datasets for pilot testing or power analysis.
Use when you need to autonomously iterate on a code project until tests pass — root-cause failures, apply minimal fixes, retry. Generic over Python/R/Julia/HPC pipelines. Triggers: 'iterate until tests pass', 'autonomous test loop', 'fix until green',…
Use when labels overlap arrows in a TikZ figure, text sits on boxes, or arrows cross each other. Audits and fixes residual TikZ visual collisions in any .tex file using mathematical gap calculations and Bézier depth formulas — no eyeballing. Downstream repair…
Fork an existing conference/journal paper into a second-venue submission variant: verify both CFPs' concurrent-submission policies, create a separate Overleaf project, convert the document class (LIPIcs/LNCS/acmart → target format), refit to the new page…
Use when you need to VERIFY a self-authored mathematical result end-to-end — route each claim to the right rung of the verification spectrum (R0 adversarial review, R1 numerical falsification, R2 symbolic/CAS, R3 Lean proof) and aggregate into one…
Use when you need to identify the weakest arguments across a literature.
Use when you need to interact with or test a local web application using Playwright.
Use when you need to challenge research assumptions or stress-test arguments.
Use when you need to prune duplicates and merge overlapping entries in MEMORY.md files.
Use when you need all quality checks run before submission, producing a single dated report.
Use when you receive referee comments for a paper (R&R, revise-and-resubmit) and need a DAG-validated revision master plan — atomic task extraction, dependency mapping, computational critical-path analysis, execution blocks, venue strategy. Merges…
Use when you need to design or audit an identification strategy for an observational study.
Use when you need to convert a Markdown draft into a buildable LaTeX project.
Use when you need to explore a research question from multiple independent perspectives.
Use when you need to create an academic Beamer presentation with original theme and multi-agent review.
"Use when you need to analyze writing samples to create a portable voice profile."
"Use when you need to edit content to match a specific voice profile."