メニュー
Use when producing a publishable or shareable literature review - chained workflow from scope to written review with verification
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | structured-literature-review |
| description | Use when producing a publishable or shareable literature review - chained workflow from scope to written review with verification |
| kind | workflow |
| audience | anyone |
| ai-tools | any |
| complexity | chained |
| time | 1-3 days |
| version | 1.0.0 |
| source | bundled |
| composes | ["literature-scan","verifying-before-citing"] |
Produces a publishable or shareable literature review by running a structured pipeline: scope → search → screen → extract → synthesize → write → verify. Each stage has an explicit handoff artifact and a quality gate.
A written review (1-20 pages depending on scope) with: scope, methods, themes, evidence map, gaps, and a verified bibliography.
This is a chained workflow with 6 stages and explicit handoffs.
Gate: scope fits on one page; inclusion criteria are specific enough that two people would categorize the same source the same way.
Run literature-scan to identify the canonical sources. Then expand:
Save: source list with metadata (title, author, year, venue, where you found it).
Gate: at least 30 candidates; search queries are recorded.
Apply inclusion/exclusion criteria from Stage 1 to each candidate. Record reason for each exclusion.
Gate: included list is non-empty and the exclusion reasons are concrete.
For each included source, extract: research question, method, sample, key findings, limitations, your one-line summary, and the theme(s) it speaks to.
Gate: every included source has every column filled. Empty cells = re-read the source.
Cluster sources into 3-7 themes. For each theme: what is the consensus, what is contested, what's the strongest evidence on each side, what gaps remain.
Gate: every theme is supported by multiple sources; consensus and contestation are both named.
Standard structure (adjust for venue):
Run verifying-before-citing on every cited claim. Open the primary source for each. Fix or hedge or cut.
Gate: every citation has been verified or explicitly hedged.
Input: Research question — "What does the evidence say about the effectiveness of remote work on team productivity, 2020-2025?"
Output: a 12-page review covering 28 sources organized into 4 themes (individual productivity, team coordination cost, manager experience, equity effects), with consensus and contestation in each, and a verified bibliography.
Use when the meta-builder routes to kind=discipline. Generates a discipline spell with the rule, excuses table, warning signs, and hard gates.
Use when the user wants to capture a repeatable task as a reusable spell, or asks "how do I build a workflow / skill / framework for X"
Use when the meta-builder routes to kind=subagent. Generates a spell that dispatches one or more subagents to do work in parallel or in isolation.
Use when the meta-builder routes to kind=workflow. Generates a workflow spell with explicit stages, checkpoints, and loop-back conditions.
Use when composing multiple spells into a chain that runs end-to-end (e.g. brainstorm -> plan -> execute -> verify).
Use when browsing what spells are available - bundled seeds, your personal library, or both. Filter by kind, audience, or update status.
