agentleFS
yuryalencaryuryalencar/ai-skills/skills/review/SKILL.md

review

Skill0 starsChanged 15 days agoMITView on GitHub

Review one section of a scientific paper against the course-derived model for that section and report what is missing, weak or inconsistent, without rewriting it unasked. Sections are abstract, introduction, results-discussion, conclusions, title, cover-letter and response-to-reviewers. Name the section as the argument. Use when asked to review, critique, check, audit, proofread or give feedback on an abstract, introduction, results and discussion, conclusions, title, cover letter, or response to reviewers.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images 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.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文,过滤相关性,auto-ingest 高优先级论文,检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门:Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If it does not exist, stop and say so, and point at /write <section>.

    line 59
  2. Distinctive:

    Read the chosen reference in full and follow it.

    line 64
  3. Very specific:

    Re-score the section if an evaluation exists: If paper-out/evaluation.md exists, follow "Re-scoring one section" in the evaluate skill's …

    line 73

“Common” is measured: kept by at least 6 in 10 of the 156 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

/review

One entry point for critiquing every section of a paper. The researcher says what to review; this skill loads the checks for that section and runs them. Each section is judged against its own model, so the checks live in references/.

Usage

/review abstract
/review introduction src/introduction.tex
/review response-to-reviewers
/review                                   # infers the section, else asks

Sections

SectionReference
Abstractabstract
Introductionintroduction
Results and discussionresults-discussion
Conclusionsconclusions
Titletitle
Cover lettercover-letter
Response to reviewersresponse-to-reviewers

Methods is not offered, because the course gives no model to judge it against. Say so if asked.

Before anything else

  1. Check for paper-out/STATE.md and read it, with decisions.md and the relevant interviews/*.md, so you do not re-ask what is already settled and can check the section against earlier decisions.
  2. Load the style rules. Invoke paper-writing-style and read its references/human-voice.md. The project's own CLAUDE.md outranks them. If it is not installed, say so, and fall back to the condensed rules at the bottom of the /write skill's references/<section>.md if that skill is installed.
  3. Lock the language. Language of the user's first message, whole run. Rewrites are English.

Pick the section

  1. From the argument. Match it loosely: results and discussion are one section; conclusion, rebuttal, reviewer response, cover, letter all map to a row above.
  2. From a file path, if given: the file's name or contents say which section it is.
  3. From context, if there is no argument: the open file, or the section paper-out/STATE.md says was last written. Say what you inferred and let the researcher correct it.
  4. Otherwise ask. Offer the most likely sections (at most four, plus "other"), or list all seven in chat. Never guess a section and start reviewing.

Needs a draft

A review needs text to review. Find the section in src/ and main.tex, following the \input list. If it does not exist, stop and say so, and point at /write <section>. Do not review an outline or invent a draft to criticise.

Run it

Read the chosen reference in full and follow it. Do not mix checks from two sections.

After it finishes

  • Update paper-out/ before you finish, as references/session-state.md in paper-writing-style sets out, creating it if absent: this section's row in STATE.md (reviewed on this date, how many findings), a decisions.md entry for what was accepted or declined and why, open-questions.md for what was left, and the section's score in evaluation.md if it was re-scored. Name the files you wrote. A run is not finished until this is done.
  • Re-score the section if an evaluation exists. If paper-out/evaluation.md exists, follow "Re-scoring one section" in the evaluate skill's references/rubric.md: score the section again against the stored paper-out/venue-criteria.md, replace that section's block, recompute the overall score, and show the change (Introduction 6.0 to 7.0, overall 6.4 to 6.7). The user does not paste the venue text again. If there is no evaluation.md, do nothing and do not create one. If venue-criteria.md is missing or unreadable, or the evaluate skill is not installed, skip the re-score and say why.
  • Offer to apply the fixes with /write <section>, which picks up the suggestions in its Update mode.

Hard rules

  • Never rewrite the researcher's text unasked. Report, then offer rewrites for the weak parts only.
  • Never invent a result, number or citation key in a suggested rewrite. Flag it with \todo{} or % TODO:.
  • Never review a section that does not exist.
  • Never create evaluation.md or venue-criteria.md, and never score from criteria you did not read from the file. Only /evaluate starts an evaluation.
  • Never finish a run without updating paper-out/. Say which files you changed.
  • Never emit an em dash (---).

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.