agentleFS
Sign inStart free
mxslrmxslr/mlcraft/skills/literature-review/SKILL.md

literature-review

Skill8 starsChanged 4 months agoMITView on GitHub

Use when starting an ML task or choosing a method, to research papers/benchmarks and find the best approach and the REALISTIC accuracy ceiling. Finds SOTA, critically appraises reported numbers, and flags claims inflated by data leakage or ROI-cropping. Triggers on 'what's the best model/method for', 'state of the art', 'research papers', 'benchmark', 'how accurate can this get'.

84 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use pdf-explore, paper-narrative and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JimLiuSkill

    pdf-explore

    Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance of something across the whole document (datasets, benchmarks, citations, figures, table rows, accession numbers — including appendices). Skip it only for a single lookup of 1–4 pages quoted in your very next response — `read_file(pages=[...])` attaches pages as images that are dropped from context after one turn, so multi-section answers end up re-reading the same ranges repeatedly. Parses the PDF once in the Python kernel: `pdf_pages` (pages as persistent text), `pdf_outline` (TOC), `pdf_scan` (rank pages by relevance), `pdf_map`/`pdf_extract` (per-page summary / structured fields via parallel haiku calls). For PDF creation/manipulation, use reportlab/pypdf directly.

    Also in 9 projects that use this

  • JimLiuSkill

    paper-narrative

    Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. `derive_paper_brief(abstract, captions)` extracts pitch/vision/per-figure-claims; a handling-editor reviewer on the full deck returns hook_verdict (would Fig 1 make me send this for review?), arc (hook→mechanism→evidence→application), figure_moves (panels in the wrong figure), missing_panels (concrete analyses to RUN), kill_list, and boldest_defensible_fig1. Hands per-figure claims to `figure-composer`. Load when writing or revising a paper.

    Also in 5 projects that use this

  • Norman-burySkill

    brainstorming-research

    Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

    Also in 4 projects that use this

  • lingzhi227Skill

    latex-formatting

    Handle LaTeX formatting, templates, and styling for academic papers. Set up conference templates (ICML, ICLR, NeurIPS, AAAI, ACL), fix formatting issues, manage packages, and ensure venue-specific compliance. Use when the user needs to set up a paper template, fix LaTeX formatting, or prepare for submission.

    Also in 4 projects that use this

  • lingzhi227Skill

    novelty-assessment

    Assess research idea novelty through systematic literature search. Multi-round search-evaluate loops with harsh critic persona. Binary novel/not-novel decision with justification. Use before committing to a research direction.

    Also in 4 projects that use this

  • +6 more from JimLiu
  • +1 more from lingzhi227

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 65 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never pick a method from memory or hype.

    line 8
  2. Distinctive:

    Read the top 2-5 sources. For each, record: method, dataset + split, headline metric, how the split was done.

    line 12
  3. Distinctive:

    Comparable?: Only the official benchmark split can be compared across papers.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 65 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Literature Review (research-first, skeptical)

Never pick a method from memory or hype. Ground it in evidence.

Do this

  1. Delegate breadth to the paper-researcher agent when available; otherwise run diverse WebSearch yourself (by task, by dataset + "state of the art", by method family, by "patient-level" / "leakage").
  2. Read the top 2-5 sources. For each, record: method, dataset + split, headline metric, how the split was done.

Appraise every number adversarially

A high number is a hypothesis to disprove, not a target:

  • Whole-input vs ROI/patch? ROI-crop (lesion already cropped) is a different, easier problem than whole-image. Numbers are not comparable.
  • Split integrity? A random per-sample split with multiple samples per subject causes leakage and inflated scores. Demand group/patient/temporal or the official split.
  • Test size & metric? A tiny test set or thresholded accuracy is unstable. Prefer AUC / mAP / F1 with confidence intervals.
  • Comparable? Only the official benchmark split can be compared across papers.

Output an evidence brief

  • SOTA table with columns: method, dataset/split, metric, credibility note.
  • Realistic ceiling: best rigorous, leakage-free, comparable number - the honest target.
  • Ranked techniques worth combining, each with evidence + caveat.
  • Traps to avoid.
  • Sources as markdown links.

Red flags = distrust, don't chase

99%+ on a hard whole-image medical/vision benchmark almost always means ROI-only or leakage. Say so plainly. The professional move is knowing which numbers are fake.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free