full-review
Skill1 starsChanged 3 months agoMITView on GitHub
Holistic review of the entire document rather than a single section. Use when the user asks whether the whole thing is ready, wants cross-chapter coherence checked, or asks about overall argument flow, terminology drift, or guideline compliance across the document. Triggers on "review the whole thesis", "review the whole report", "check everything", "holistic review", "does it hold together", "are the chapters connected".
10 other projects use a version of this.
Adopted by
Most recently taken up by
- Randomblock1/skillstheir own version, first seen Nov 16, 2026
- fmind/dottheir own version, first seen Nov 15, 2026
- fmind/dotfilestheir own version, first seen Nov 15, 2026
- arcasilesgroup/ai-engineeringtheir own version, first seen Nov 8, 2026
- Smaui94/ClaudeSkillCollectiontheir own version, first seen Nov 8, 2026
- blamechris/chroxytheir own version, first seen Nov 8, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- arcasilesgroup/ai-engineering★ 65same name
- fmind/dot★ 13same name
- fmind/dotfiles★ 13same name
- u7-u7/dev-skills★ 9same name
- blamechris/chroxy★ 8same name
- garthcodes/claude-skills★ 2same name
- cabbagecachekid/neon-jetpack★ 0same name
- cabbagecachekid/red-pen★ 0same name
- Randomblock1/skills★ 0same name
- Smaui94/ClaudeSkillCollection★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- factsSkill
- figureSkill
- ingestSkill
- onboardSkill
- plan-sectionSkill
- researchSkill
- reviewSkill
- save-materialSkill
- statusSkill
- teachSkill
- verify-sourcesSkill
- writeSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Every file in sections/, in order, plus docs/facts.md, docs/requirements.md, .claude/rules/, and docs/feedback/.
- Distinctive: line 59
Do not edit any files. This skill is read-only.
“Common” is measured: kept by at least 6 in 10 of the 7 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.
Files
/full-review — Review the document as one thing
A document can have six strong sections and still fail: theory introduced and never used, a conclusion that answers a different question than the introduction asked, the same number given three ways, a promise in Chapter 1 that nothing delivers. Those failures are invisible from inside any single section, which is why this review exists.
1. Read everything
Every file in sections/, in order, plus docs/facts.md, docs/requirements.md, .claude/rules/, and docs/feedback/. For a long document, dispatch parallel subagents to read groups of sections and report back, then do the cross-cutting analysis yourself — the connections are the point and they cannot be delegated piecemeal.
2. Assess
A. The red thread. Trace the central argument from the research question to the conclusion. For each question or learning goal: where it is posed, where it is addressed, where it is answered. Mark any that is posed and never answered, or answered without having been posed.
B. Chapter coherence. Does each chapter set up the next? Does the roadmap in the introduction match what the document actually does? Is there a section that serves no part of the argument?
C. Theory into practice. Is every concept introduced before it is used? Is the theory in the literature review actually applied later, or introduced and abandoned? Are there claims in the analysis or discussion with no theoretical or empirical footing?
D. Facts. Grep every number, percentage, date, and sample size across all sections and check each against docs/facts.md. Report every disagreement with both locations. This check catches more real errors than any other in this list.
E. Terminology. List the recurring concepts and every variant used for each. Any concept named more than one way is a finding. Check acronyms are defined once, on first use, and used consistently afterwards.
F. Citations. Extract every in-text citation and cross-check against the reference list, in both directions: cited but not listed, listed but never cited. Flag sections that are conspicuously thin on sources given what they claim.
G. Requirements. Against docs/requirements.md: total length versus the limit, per-section budgets, citation style, every mandated structural element, abstract length, figure and table numbering, appendix policy, front-page requirements.
H. Assessment criteria. Go through the institution's criteria one at a time and grade the document against each, with the evidence for the grade.
3. Report
# Full Review — <date>
## Overall
<Three to five sentences. Would this pass, and what is the single biggest risk?>
## Length
| Section | Chars | Budget | Status |
|---------|------:|-------:|--------|
| ... | | | |
| **Total** | | | |
## A. Red thread
- RQ1: posed §1.3 → addressed §4.2 → answered §6.1 [COMPLETE / INCOMPLETE]
## B–H
<One block per dimension, each finding tagged CRITICAL / WARNING / OK with exact locations.>
## Priority actions
<Ordered by impact on the grade, not by section order. Say what to do, not just what is wrong.>Distinguish throughout between what is missing and what is wrong — they need different work. Where a section is still a stub, note it and spend the effort on sections with real content.
Do not edit any files. This skill is read-only.
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
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.

