Desk Research

Plugin desk-research from marketplace agent-ready-repo in eugenelim/agent-ready-repo. Commands read from the repo's manifest — today.

Skills (12)

• build-outline

  Decompose a research question into the sub-questions a thorough answer must address. Builds the outline that `/source-map` then populates and `/desk-research` then synthesises against. Grounded in STORM's outline stage (multi-perspective topic decomposition) and PICO (Population, Intervention, Compa

• compare-hypotheses

  Compare competing hypotheses on a decision-shaped question using an ACH-style evidence matrix (hypotheses × evidence-for/against). Dispatches per-hypothesis parallel retrieval on Claude Code (one `evidence-retriever` subagent per hypothesis). In decision-pipeline invocations expects upstream `<topic

• decision-archaeology

  Reconstruct the rationale for a past decision by walking time-ordered artifacts (commits, PRs, design docs, chat logs, internal memos). Self-contained — does not invoke `/source-map` or other research-pack skills, because the source surface is time-ordered and internal, and authority is established

• desk-research-project-check

  Passive stop-signal for a research project — reads the synthesis matrix and memos by eye and reports whether the corpus has stopped changing the structure (theoretical saturation), plus a recommendation. Triggers on project-lifecycle phrasing — \"is this project saturated\", \"should I keep gatherin

• desk-research-project-digest

  Build the digest middle layer of a research project — the constructed-column synthesis matrix and analytic memos the pack previously lacked. Triggers on project-lifecycle phrasing — \"digest the sources\", \"build the synthesis matrix\", \"cluster what I've gathered\" — inside an existing project fo

• desk-research-project-start

  Start a stateful, multi-week research project — the lifecycle axis, orthogonal to the depth axis the `/research` skill carries. Triggers on explicit project-lifecycle phrasing — \"start a research project\", \"set up a research project on X\", \"begin a sustained investigation\", \"open a research d

• desk-research-project-status

  Orient to the current desk-research project at a glance — reads overview.md and surfaces phase, working hypothesis, stop-signal verdict, and what to do next. Triggers on 'where are we on the X research', 'status of the Y investigation', 'resume the Z project', 'what phase is the research in', 'where

• desk-research-project-synthesize

  Synthesize a research project into its typed verdict and a self-contained governance brief. Triggers on project-lifecycle phrasing — \"synthesize the project\", \"write up the findings\", \"produce the brief\" — inside an existing project folder. Reads synthesis-matrix.md + memos.md and writes BOTH

• desk-research

  Evidence-grounded research with selectable depth and discipline. Use for any look-up, find-out, fact-check, or comprehensive investigation, including prior art and best practice surveys. Carries a mode parameter (quick / standard / applied / deep) with `quick` as default — casual phrasings (`look up

• devils-advocate

  Adversarially review a research artifact (`<topic-slug>-survey.md`) or a user-supplied claim. Searches for counter-evidence, names the strongest objections, and routes each to a verdict — either a confidence-rating downgrade or a do-not-resolve verdict for an irreducible tension where both sides are

• identify-perspectives

  Enumerate the named camps on a contested topic before research begins. Builds the perspective scaffold that `/source-map` and `/compare-hypotheses` consume downstream in the decision pipeline. Fairly represents every significant view in proportion to its prominence, and surfaces every viable explana

• source-map

  Curate the authoritative sources for a topic before research begins. Surveys adjacent material to discover voices rather than asking the LLM directly who's authoritative — STORM's finding is that ungrounded LLM question generation produces shallow, surface-level questions, so this skill grounds disc

Subagents (2)

• evidence-retriever

  Read-only retrieval subagent. Given a scoped query, fetches web and local material, then returns a synthesised summary with citations. Used by `/desk-research` standard and deep modes and by `/compare-hypotheses` for per-hypothesis parallel retrieval. Preserves main-session context by collapsing raw

• source-extractor

  Read-only extraction subagent. Given a list of candidate URLs or local paths, fetches each, extracts the substantive content, and returns a per-source synthesis with citations. Used by `/source-map` to populate `<topic-slug>-sources.md` after candidates are discovered; used by `/decision-archaeology

Hooks (1)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/.claude-plugin/scripts/install-marker.py" --install-route claude-plugins

Similar plugins