research

Plugin research from marketplace research-kit in lividgreen/research-kit. Commands read from the repo's manifest — yesterday.

Skills (12)

• attribution

  An attribution check — every sentence crediting the project with proving, settling, bypassing, re-deriving or being first at a named external result, held to that result's primary source on four axes (the resource measured, the quantifiers, the scope and the author's own caveats), each verdict recor

• audit

  A consistency audit across the project's documents — the mechanical checks first, then what no script sees, every import read at its exporting statement, a regime condition stated with the same constants, a status labelled alike, definitional drift and every negative-coverage sentence held to the ar

• 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 command-line answer, rendered. Use when the owner wants to browse the records or the cards, when asked to start

• 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. Especially when a "quick obvious fix" is tempting or previous fixes didn't stick. When the person says '

• design

  Design pass for any new mechanism, tool, check, document section, or formal target — run BEFORE implementing. Use whenever the user proposes building or changing something ("let's add X", "can we do Y", "should we…", "what about…"), picks up a recorded open question or decision, or asks for a featur

• flow

  The typed flow of research work — ideas, tasks, questions, findings whose evidence a machine resolves, the goals the owner forms and the directions they set, one Markdown record each, linked by references and four links with a rule, moved through the `flow` CLI, with a validator, a generated index w

• freeze

  Freeze a session so a cold one can continue it — save what the work needs that the conversation alone holds, check the records with `flow state --check`, sweep what the session made stale, run the gates and commit, then report item by item. Use as `/research:freeze`, and before a session ends that c

• 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 what it says at a place, written and searched through the `library` CLI. Use when registering a work,

• method

  Method rules for a project that writes documents and makes claims — how to answer a review, what to call things, what a document holds and when a result enters one, what counts as evidence, what to check before pricing a piece of work, how to change a target honestly when a wall is hit, how to work

• 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. Use as `/research:research-init`, or when asked to set up research-kit, the flow or the library in a project, or to bring a project's exis

• scrutinize

  Argument-level scrutiny of one proof, section or statement — the claims with their asserted status, the inference gaps told apart as a missing result or a missing method, the load-bearing steps and the most appealing claim read hardest, the conditions made visible, and a class claim kept apart from

• whatsnext

  What we do next, for the whole project — review the cards the agent's hand holds, read the inbox and propose what to make of each item, rank the next list under the focus the person gives, refill the agent's hand by rank to its limit, propose additions to the person's hand, and write the log entry.

Similar plugins