# research-kit > A kit for doing research with a coding agent — a project's ideas, questions, tasks, findings and cited works kept as checked Markdown in its own repository. This site is the project's documentation at v0.1.0, published 2026-10-26. Source and releases: https://github.com/lividgreen/research-kit. The project is one of the projects at https://www.livid.work/projects/research-kit/. ## Overview - [research-kit](https://research-kit.livid.work/) — A kit for doing research with a coding agent — a project's ideas, questions, tasks, findings and cited works kept as checked Markdown in its own repository. - markdown: https://research-kit.livid.work/index.md ## Documentation - [Documentation](https://research-kit.livid.work/docs/) — Documentation of research-kit: Why research-kit, How to use, Getting started, Scope, Install, What goes online, and what runs, Glossary, The bindings files, The checks, Development. - markdown: https://research-kit.livid.work/docs.md - [Why research-kit](https://research-kit.livid.work/docs/why/) — The failures in one research project each piece of the kit replaced - markdown: https://research-kit.livid.work/docs/why.md - [How to use](https://research-kit.livid.work/docs/how-to-use/) — A research thread as you say it to the agent, and the commands underneath - markdown: https://research-kit.livid.work/docs/how-to-use.md - [Getting started](https://research-kit.livid.work/docs/getting-started/) — The records as written, a failed check, a card, the dashboard - markdown: https://research-kit.livid.work/docs/getting-started.md - [Scope](https://research-kit.livid.work/docs/scope/) — What the kit assumes, what the agent does without asking, what it is not - markdown: https://research-kit.livid.work/docs/scope.md - [Install](https://research-kit.livid.work/docs/install/) — The routes, the supported agents, the optional tools, updating - markdown: https://research-kit.livid.work/docs/install.md - [What goes online, and what runs](https://research-kit.livid.work/docs/network/) — The online commands, the hosts they call, the environment variables they read - markdown: https://research-kit.livid.work/docs/network.md - [Glossary](https://research-kit.livid.work/docs/glossary/) — Every word the skills use, one line each - markdown: https://research-kit.livid.work/docs/glossary.md - [The bindings files](https://research-kit.livid.work/docs/bindings/) — Flow.toml, library.toml and formal.toml as init writes them, every binding explained - markdown: https://research-kit.livid.work/docs/bindings.md - [The checks](https://research-kit.livid.work/docs/checks/) — Every code flow check and library check can report, what the formal checks verify, the exit codes - markdown: https://research-kit.livid.work/docs/checks.md - [Development](https://research-kit.livid.work/docs/development/) — The layout, the tests, how a release is cut; the CHANGELOG beside the README - markdown: https://research-kit.livid.work/docs/development.md ## Changelog - [Changelog](https://research-kit.livid.work/changelog/) — Each release is a tag; the version is read from the tag and the version fields docs/development.md names, and each release’s section is headed by its tag and date; a change not yet released goes… - markdown: https://research-kit.livid.work/changelog.md ## Plugins - [formal](https://research-kit.livid.work/plugins/formal/) — The prover side of research-kit: the harness of a prover session for a project that pairs its documents with a machine-checked library. It is built for Lean 4, the only prover it has run with: the… - markdown: https://research-kit.livid.work/plugins/formal.md - [research](https://research-kit.livid.work/plugins/research/) — The record side of research-kit: what a research project keeps in its own repository so that a coding agent works from it instead of from memory. Ideas, questions, tasks and findings are Markdown… - markdown: https://research-kit.livid.work/plugins/research.md ## Skills - [Setting the prover side up](https://research-kit.livid.work/plugins/formal/skills/formal-init/) — Sets a project up for the formal plugin — formal.toml over its Lean workspace, the manifest generator in the workspace, the prover session's standing instructions, the flow's declaration evidence… - markdown: https://research-kit.livid.work/plugins/formal/skills/formal-init.md - [Handing work to the prover](https://research-kit.livid.work/plugins/formal/skills/handoff/) — Compose a prover-session handoff prompt for the formal target(s) named — statement-first from the document's text, with the declarations quoted, a refute-first line, the bundle's shape and the… - markdown: https://research-kit.livid.work/plugins/formal/skills/handoff.md - [Landing a handback](https://research-kit.livid.work/plugins/formal/skills/land/) — Land a prover session's handback — verify the report at the tree (the manifest diff with formal handback, a cold read-back of every landed statement from a packet formal readback builds, the binders… - markdown: https://research-kit.livid.work/plugins/formal/skills/land.md - [The dashboard](https://research-kit.livid.work/plugins/research/skills/dashboard/) — One read-only browser dashboard over the flow's records, the reference library's cards and any other component installed beside it and bound in the project — every page the component's own… - markdown: https://research-kit.livid.work/plugins/research/skills/dashboard.md - [Debug to the root cause; claim with evidence](https://research-kit.livid.work/plugins/research/skills/debug/) — Root-cause debugging discipline — use when encountering any bug, failing test or check, unexpected behavior, or build failure, BEFORE proposing fixes; and again before claiming anything is fixed. - markdown: https://research-kit.livid.work/plugins/research/skills/debug.md - [Design before implementation](https://research-kit.livid.work/plugins/research/skills/design/) — Design pass for any new mechanism, tool, check, document section, or formal target — run BEFORE implementing. - markdown: https://research-kit.livid.work/plugins/research/skills/design.md - [The flow](https://research-kit.livid.work/plugins/research/skills/flow/) — The typed flow of research work — ideas, tasks, questions with kill criteria and findings whose evidence a machine resolves, one Markdown record each, transitions through the flow CLI, a validator, a… - markdown: https://research-kit.livid.work/plugins/research/skills/flow.md - [The reference library](https://research-kit.livid.work/plugins/research/skills/library/) — The reference library — one card per referred work (a paper, a book, a preprint, a software library or tool, a dataset, a report handed in, a page) holding its fields, how it was read, our notes and… - markdown: https://research-kit.livid.work/plugins/research/skills/library.md - [Research method](https://research-kit.livid.work/plugins/research/skills/method/) — Method rules for a project that writes documents and makes claims — how to review, what counts as evidence, what to check before pricing a piece of work, how to change a target honestly when a wall… - markdown: https://research-kit.livid.work/plugins/research/skills/method.md - [Setting a project up](https://research-kit.livid.work/plugins/research/skills/research-init/) — Sets a project up for the research plugin — the flow, the reference library, the instructions paragraphs and the pre-commit hooks — and checks an existing setup. - markdown: https://research-kit.livid.work/plugins/research/skills/research-init.md