agentleFS
denismrvoljakdenismrvoljak/claude-scholar/.claude/skills/review/SKILL.md

review

Skill1 starsChanged 3 months agoMITView on GitHub

Review one section for academic quality against the project's rules and the institution's criteria. Use when the user wants feedback on, a critique of, or an assessment of a section. Triggers on "review my", "how does this look", "check the quality of", "is this section ready", "give me feedback on".

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, daily-arxiv 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

  • 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

  • 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

    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

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

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not edit any files. This skill is read-only.

    line 65

“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 — Review a section

You are an examiner reading one section closely. Be specific: a finding without a location and a fix is not a finding.

1. Read

  • The target section.
  • docs/facts.md — first among the standards. Any number, date, or term in the section that disagrees with this file is a CRITICAL finding.
  • docs/requirements.md — formal requirements and the assessment criteria the work is graded against.
  • .claude/rules/writing.md and .claude/rules/structure.md.
  • docs/feedback/ — prior feedback. A regressed fix is CRITICAL.
  • The adjacent sections, for continuity and duplication.

2. Evaluate

Argument. Does the section have one point, stated early and carried through? Does each paragraph advance it? Is there a paragraph that could be deleted with no loss?

Evidence. Is every substantive claim supported by a citation or by the author's own analysis? Point to the unsupported ones by line. Does the evidence actually support the strength of the claim as written, or has a suggestive finding been reported as a settled one?

Method and reasoning. Are assumptions stated? Are the limits of the evidence acknowledged where they matter? Is anything asserted that the method used could not establish?

Criteria alignment. Go through the assessment criteria in docs/requirements.md one by one and say how this section performs against each.

Structure. Does it follow the structure structure.md requires for this section, including any element the institution mandates?

Citations. Correct style, no stray footnotes, every cited work in the reference list.

Language. Register, paragraph length, defined acronyms, consistent terminology, and the conventions set in writing.md.

Rule sweep. Run the pre-flight grep block from the bottom of .claude/rules/writing.md against the file. Report every hit with its line number. A hit is at least a WARNING; a hit on a term the supervisor personally objected to is CRITICAL. For each, check whether the sentence would be stronger with a concrete substitute — a number, a threshold, a named mechanism.

Also check: headings that name a category rather than its contents, counted-list openers with no list, forward references that never pay off, and explanations repeated from an earlier section.

Budget. wc -m the file against the budget in structure.md.

3. Report

## Review: <section>

Characters: X / Y budget

### CRITICAL — must fix
- [C1] <finding> — <file:line> — <fix>

### WARNING — weakens the work
- [W1] ...

### SUGGESTION
- [S1] ...

### What is working
- <specifically what, so it does not get edited away>

Say why each critical finding matters, tied to the assessment criteria where it applies. Do not pad the list: three real problems reported precisely are more useful than twenty stylistic notes.

Do not edit any files. This skill is read-only.

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.