critic-review
Skill1 starsChanged 14 days agoMITView on GitHub
Review the project docs and experiments for gaps between what is documented, what was implemented, and the state of the art. Use when the user wants a critical assessment of the whole project, wants to check for missing experiments, bad assumptions, or weak evidence.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- TianMingKanae/engineering-multi-ai-skillstheir own version, first seen Oct 20, 2026
- junhjang/claude-harnesstheir own version, first seen May 12, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- TianMingKanae/engineering-multi-ai-skills★ 6same name
- junhjang/claude-harness★ 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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- developing-data-science-notebooksSkill
- expectation-driven-scienceSkill
- experiment-graphSkill
- experiment-pipelineSkill
- exp-reviewSkill
- hypothesysSkill
- let-it-ripSkill
- literature-researchSkill
- mad-science-setupSkill
- notify-gchat-human-waitSkill
- to-articleSkill
- to-docSkill
- what-i-doSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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
- Very specific: line 15
Every important doc lives under docs/....
- Distinctive: line 16
Look for the implemented notebooks in the folders.
- Distinctive: line 34
Write a report from the full analysis performed.
- Distinctive: line 36
If necessary, propose new experiments to fill the gaps and strengthen the project.
- Very specific: line 37
Before finishing, ask the user whether they want a more thorough review using the /literature-research skill.
- Distinctive: line 40
If it was done, run the full review again to check everything.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Critic Review
The main goal of this skill is to evaluate the entire project to understand what is good, what could be better, and which gaps remain. With that, if necessary, propose new experiments to make the project more scientifically robust.
Critic Review Flow
- Read the main docs of the project
- Every important doc lives under
docs/.... - Look for the implemented notebooks in the folders. If a notebook does not exist, the experiment was not run.
- Every important doc lives under
- Analyze the docs and the results, if any.
- Against the project's main goal and the analysis above, check:
- Is the proposed experiment enough to validate the hypothesis?
- Is there enough evidence to validate the hypothesis? How strong is it?
- Are there any wrong assumptions drawn from the results?
- Evaluate the project against the scientific process
- What is good?
- What could be better?
- What are the gaps?
- How strong is each piece of evidence relative to the hypothesis and its premises?
- How strong is the project as a whole?
- Give the final assessment based on the review flow
- Write a report from the full analysis performed.
- Save it in
docs/critic-review/<today-date>_<critic_review_name>.md
- Save it in
- If necessary, propose new experiments to fill the gaps and strengthen the project.
- Before finishing, ask the user whether they want a more thorough review using
the
/literature-researchskill. Give your recommendation on this point based on the final assessment.- If it was done, run the full review again to check everything.
- Write a report from the full analysis performed.
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.