A multi-perspective review process for academic papers, which are research articles submitted to scholarly journals. It simulates an editor, several subject reviewers, a methods reviewer, and a critic to produce an editorial decision and revision plan.
An academic writing workflow covering planning, drafting, revising, reviewing, citations, abstracts, formatting, and disclosure statements. It supports several paper types, citation styles, and outputs such as LaTeX, DOCX, PDF, and Markdown.
An academic research workflow coordinator that guides work from choosing a research question through writing, review, revisions, and a final submission package.
A team of 13 AI agents for academic research, from turning a topic into a research question and finding sources to checking evidence, combining results, and writing APA 7 reports. It supports literature reviews, fact-checking, paper reviews, systematic reviews, and meta-analysis; bioRxiv is not mentioned in the supplied description.
A collection of skills for academic research, from finding and checking sources to writing papers and simulating peer review. It is adapted from a Claude Code workflow and includes support for research reports, citations, LaTeX, and DOCX output when local tools are available.
An HTML slide-deck maker for creating presentations from scratch, converting PowerPoint files into web pages, or improving existing HTML slides. It produces a single dependency-free file in a fixed 16:9 layout.
Run comprehensive health checks on the Obsidian knowledge base including broken wikilinks, orphan pages, stale status, concept page completeness, and status consistency. Trigger phrases: lint knowledge base, knowledge base health check, kb check, run lint, 知识库检查, 健康检查.
Mole (https://github.com/tw93/mole) is a macOS terminal maintenance tool that replaces CleanMyMac, AppCleaner, DaisyDisk, and iStat Menus with a single binary. This skill should be used when the user asks about Mac cleanup, disk space analysis, app uninstallation, system optimization, system monitoring, or project…
A coordination skill for splitting independent development or data tasks among several software agents and combining their results. Tasks are independent when they do not share files or depend on one another’s output.
A workflow for closing a development branch after all work and tests are complete. A branch is a separate line of changes in a version-control system such as Git.
A step-by-step guide for handling code-review feedback: classify each issue, confirm unclear requests, fix items one at a time, and ask for another review.
A development workflow that gives each planned coding task to a fresh helper agent, then checks the result against the requirements and code-quality rules.
A step-by-step debugging guide that starts by finding the root cause before suggesting a fix. It covers reproducing the problem, examining recent changes, tracing data, testing hypotheses, and checking for regressions.
A software-development method called test-driven development, or TDD, where you write a test first, confirm that it fails, then write the smallest implementation that makes it pass.
An engineering workflow that guides an agent from idea clarification through design, planning, test-driven development, review, verification, and branch cleanup. Test-driven development, or TDD, means writing a failing test before the production code that makes it pass.
A final checklist for verifying software work before declaring it complete, including tests, requirements, code quality, files, documentation, and Git status.
A repair process for fixing common formatting mistakes in the inputs an AI sends to software tools, after schema validation reports a problem. A schema is the set of rules describing valid input data.
A repair guide for invalid tool-call inputs from language models. It checks the input against a schema, fixes certain recoverable formatting mistakes, and retries validation.