Literature Review
Survey the existing literature on a topic and synthesize it into a structured review: a planner sets the scope, inclusion criteria, and the themes to organize around, then a researcher gathers and characterizes each source (method, finding, quality), then a copywriter synthesizes them thematically rather than source-by-source, surfacing consensus, disagreement, and gaps. The ordering matters because a review written without inclusion criteria becomes an arbitrary pile, and one written source-by-source reads like a list of summaries instead of a synthesis; locking themes and a source matrix first forces the comparative analysis that makes a real lit review. Use this for academic-style literature surveys, state-of-the-art reviews, 'what does the research say' questions, and synthesizing a body of papers or articles.
Steps
Entry step: scope. Each step names the specialist role it wants; the full working prompt is expandable.
- Scope the reviewplannerentry
topic boundaries, inclusion criteria, organizing themes
Show working prompt
1. State the review topic and its boundaries in one sentence (what is in and out of scope). 2. Define inclusion criteria: source types accepted (peer-reviewed, official reports, etc.), recency window, and a minimum source count (aim 6+). 3. Decide 3-5 organizing themes or dimensions the review will be structured around (NOT source-by-source) plus a source-characterization matrix schema (columns like source, year, method, key finding, quality/limitation). 4. Write an acceptance-criteria checklist (e.g. 'review is organized by theme not by source', 'each source appears in the matrix with all columns filled', 'consensus vs disagreement is explicitly called out', 'a gaps/future-work section exists', 'minimum source count met'). 5. Record decisions. Call write_task_note with the themes, matrix schema, and checklist, and write the same to notes/scope.md.
- Gather & characterize sourcesresearcher
build the source matrix: method, finding, quality per source
Show working prompt
1. Find sources meeting the inclusion criteria, prioritizing seminal and recent work. 2. For each source, add a row to the matrix in notes/sources.md with every scoped column filled: citation key [n], title/author/year, method or evidence type, key finding (with the figure or claim), and a one-line quality note or limitation. 3. As you go, tag which organizing theme(s) each source speaks to so the writer can group them. 4. Note where sources agree and where they conflict on the same question. 5. Flag anything you could not verify as UNVERIFIED. Good looks like a matrix where the comparative structure of the field is already visible. Do not write the prose review yet.
- Synthesize the reviewcopywriter
write a thematic synthesis with consensus, conflict, gaps
Show working prompt
1. Write review.md organized by the locked themes (one section per theme), NOT one section per source. 2. In each theme, synthesize across sources: state what is established, cite the supporting sources [n], then explicitly note where sources disagree and why. 3. Open with an introduction framing the topic and scope, and close with a 'Gaps & future directions' section. 4. Add a numbered References list built from notes/sources.md so every [n] resolves. 5. Keep it comparative and analytical, not a chain of one-paragraph summaries. 6. On a loop-back, fix only the named gaps. 7. Call write_task_note with the review path and which criteria now pass.
- Evaluatereviewer
Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.
Show working prompt
Open review.md and check EACH criterion PASS/FAIL: (1) the review is organized by theme, not source-by-source; (2) every source in notes/sources.md is cited and every matrix column was actually used to inform the prose; (3) consensus AND disagreement are explicitly surfaced for at least the main themes; (4) a gaps/future-work section exists; (5) the minimum source count is met and inclusion criteria respected; (6) every inline [n] resolves to the References list. A pile of per-source summaries with no synthesis FAILS even if every source is present. Then route — this is the whole point of the loop: - **Every criterion PASSES →** call `advance_task_step({ ref, stepId: "evaluate", next: "finish" })`. - **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: "evaluate", next: "synthesize" })` to loop back. The builder fixes exactly those gaps. Never route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in. - Finishdeveloper
All acceptance criteria met. Stamp a short summary and report DONE.
Show working prompt
Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.
Triggers
Phrases that suggest this craftbook to a crew.
- literature review
- what does the research say
- survey the literature
- state of the art review
- summarize the papers on
Source
View this craftbook on GitHub · MIT license