Mmcp.market

lit-review skill

by pedrohcgs·pedrohcgs/claude-code-my-workflow·1.6k stars·MIT

Structured literature search + synthesis with citation extraction, thematic clustering, and gap identification. Use when user says "find papers on X", "do a lit review", "what's the literature on...", "summarize what we know about...", "where's the gap in this field", "review recent work on Y". Produces a written review with BibTeX-ready citations. Uses WebSearch/WebFetch for recent work.

A100/100content scan

Is the lit-review skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the lit-review skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/pedrohcgs/claude-code-my-workflow.git /tmp/claude-code-my-workflow
mkdir -p ~/.claude/skills
cp -r /tmp/claude-code-my-workflow/.claude/skills/lit-review ~/.claude/skills/lit-review
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Literature Review

Conduct a structured literature search and synthesis on the given topic.

Input: $ARGUMENTS — a topic, paper title, research question, or phenomenon to investigate.

Steps

  1. Parse the topic from $ARGUMENTS. If a specific paper is named, use it as the anchor.
  1. Search for related work using available tools:
  • Check mastersupportingdocs/supporting_papers/ for uploaded papers
  • Use WebSearch to find recent publications (if available)
  • Use WebFetch to access working paper repositories (if available)
  • Read any existing .bib file for papers already in the project
  1. Organize findings into these categories:
  • Theoretical contributions — models, frameworks, mechanisms
  • Empirical findings — key results, effect sizes, data sources
  • Methodological innovations — new estimators, identification strategies, inference methods
  • Open debates — unresolved disagreements in the literature
  1. Identify gaps and opportunities:

the apparent count and the independent count — studies that share an experiment, dataset, sample or research team count once.

  • What questions remain unanswered?
  • What data or methods could address them?
  • Where do findings conflict?
  • How independent is the support? For any finding you call consistent or replicated, give

replications and report them, or say none were found and give the search terms used.

  • What went the other way? For each headline finding, search for null results and failed
  1. Extract citations in BibTeX format for all papers discussed.
  1. Save the report to qualityreports/litreview[sanitizedtopic].md

Output Format

# Literature Review: [Topic]

**Date:** [YYYY-MM-DD]
**Query:** [Original query from user]

## Summary

[2-3 paragraph overview of the state of the literature]

## Key Papers

### [Author (Year)] — [Short Title]
- **Main contribution:** [1-2 sentences]
- **Method:** [Identification strategy / data]
- **Key finding:** [Result with effect size if available]
- **Relevance:** [Why it matters for our research]

[Repeat for 5-15 papers, ordered by relevance]

## Thematic Organization

### Theoretical Contributions
[Grouped discussion]

### Empirical Findings
[Grouped discussion with comparison across studies]

### Methodological Innovations
[Methods relevant to the topic]

## Gaps and Opportunities

1. [Gap 1 — what's missing and why it matters]
2. [Gap 2]
3. [Gap 3]

## Suggested Next Steps

- [Concrete actions: papers to read, data to obtain, methods to consider]

## BibTeX Entries

@article{...}

Post-Flight Verification (mandatory, CoVe)

Before returning the draft literature review to the user, run the Post-Flight Verification protocol from .claude/rules/post-flight-verification.md. Literature reviews are very high hallucination risk because WebSearch can return plausible-sounding fabricated citations. CoVe catches this architecturally.

Steps

  1. Extract claims from the draft. Each cited paper, each paraphrased finding ("Smith 2019 shows X"), each negative-literature assertion ("no prior work studies Y") is a claim.
  2. Generate verification questions per claim. Specific ones: "Does Smith (2019, JEL) Section 3 actually report the finding that X implies Y? Is the venue correct?"
  3. Spawn claim-verifier via the Agent tool with subagenttype=claim-verifier, in a fresh context — a named Agent call, not a conversation fork, which would inherit the draft. Pass: the claims table, the verification questions, the source-material pointers (paper URLs, DOIs, mastersupportingdocs/ paths). Do NOT pass the draft text itself** — the fresh-context independence is what makes CoVe work.
  4. Reconcile: if the verifier reports PASS, attach a green Post-Flight block to the output. If PARTIAL, mark the unverifiable claims with uncertainty flags in the BibTeX block. If FAIL, remove or rewrite the contradicted citations using the verifier's evidence before returning.

Skip conditions

  • --no-verify flag — user opts out for speed.
  • User hands you ≤3 papers they already have read and confirmed; CoVe is overhead for content they've personally verified.

Output contract

Append a Post-Flight block to the report (collapsed by default). See rule doc for the format.

Important

  • Be honest about uncertainty. If you cannot verify a citation, say so.
  • Prioritize recent work (last 5-10 years) unless seminal papers are older.
  • Note working papers vs published papers — working papers may change.
  • Do NOT fabricate citations. If you're unsure about a paper's details, flag it for the user to verify. Post-Flight Verification catches most fabrications automatically; this rule is the backup.

More skills from pedrohcgs/claude-code-my-workflow

  • Aadjudicate-reviewTurn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.
  • Aaudit-reproducibilityEnforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
  • Ablast-radiusBefore and after changing anything shared — a function's return value, a signature, a schema, a label set, a config default, a constant, a file format — find every consumer and actually run them. Catches the change that looks purely additive but silently breaks a contract in a file you never opened. Use when editing shared code, adding a field/column/return element, renaming, changing units or defaults, or touching a pipeline that produces reported numbers.
  • Acapture-environmentSnapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning Dockerfile, and produces a paste-ready "Computational requirements" block. Use when user says "capture the environment", "snapshot my dependencies", "pin the versions", "make a renv.lock / requirements.txt", "make this byte-reproducible", or before releasing a replication package to openICPSR / the AEA Data Editor.
  • AchallengeStress-test a finding against the choices you did not make. Enumerates the discrete forks a competent analyst could have taken (measure definition, sample filter, control set, clustering level, weighting, functional form), runs the specification grid, and reports the distribution rather than a point estimate — then attacks the identifying assumption with named, computable sensitivity statistics. Use when the user says "is this robust", "challenge this result", "specification curve", "multiverse", "how sensitive is this", "what if I'd used a different measure", "stress-test my estimate", or before a result becomes a headline claim. NOT a reviewer of prose or code — it challenges the CLAIM.
  • AcheckpointSave a structured state snapshot before stopping or handing off. Captures the active plan, recent decisions, file pointers (with line numbers), open questions, and the next 1–3 actions into a checkpoint file under `quality_reports/checkpoints/`. Optionally proposes `[LEARN]` entries to add to MEMORY.md. Use when user says "checkpoint", "save state", "snapshot before I stop", "where am I", "wrap up the session for handoff", or before a long break / model switch / collaborator handoff. Companion to (NOT replacement for) the narrative session-log workflow.
  • Acoauthor-briefGenerate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says "coauthor brief", "handoff brief", "bring my coauthor up to speed", "what changed since last week", "onboard a collaborator", "write a handoff for [name]", or before sending a co-author the repo. NOT a commit or a checkpoint — it is the cross-machine, cross-person summary `meta-governance.md` only partially covers.
  • AcommitCommit the current work — runs the quality, consistency and passport gates, branches off main if needed, stages specific files, and writes a commit whose subject states what is now true. Pushes and opens a pull request only with --pr or when the user asks; never merges — a merge happens only when the user explicitly says to merge. Use ONLY on explicit commit intent — user says "commit", "let's commit this", "open a PR", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Never force-pushes or skips hooks.
  • Acompile-latexCompile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a `.tex` file isn't producing a PDF. Operates on `Slides/*.tex`.
  • Acompress-sessionDistill the current conversation into a structured note (decisions made, open questions, file pointers with line numbers, next 1–3 actions) and save to `quality_reports/session_logs/` before auto-compression. Differs from `/checkpoint` (explicit stop-point snapshot) and from auto-compaction (which truncates rather than distills). Use when context is approaching auto-compact threshold, when a long pipeline has accumulated many decisions, or when the user says "compress", "distil this session", "before we hit auto-compact", "structured handoff before context resets".
  • Acontext-statusShow current context status and session health. Use to check how much context has been used, whether auto-compact is approaching, and what state will be preserved.
  • Acreate-lectureCreate a new Beamer lecture `.tex` from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds the full deck — NOT for compiling existing `.tex` (use `/compile-latex`).

All agent skills → · MCP servers