exec-code-review
Skill1 starsChanged 28 days agoMITView on GitHub
Execution skill loaded to perform a final diff review proportional to the change.
In this repository29 other files it gives its agents.
- exec-accessibilitySkill
- exec-architectureSkill
- exec-debuggingSkill
- exec-documentationSkill
- exec-performanceSkill
- exec-refactoringSkill
- exec-repo-patternsSkill
- exec-securitySkill
- exec-testingSkill
- exec-ui-uxSkill
- exec-verificationSkill
- tech-dockerSkill
- tech-flutterSkill
- tech-goSkill
- tech-graphqlSkill
- tech-kotlinSkill
- tech-nextjsSkill
- tech-nodeSkill
- tech-postgresSkill
- tech-pythonSkill
- tech-reactSkill
- tech-rustSkill
- tech-swiftSkill
- tech-tailwindSkill
- tech-typescriptSkill
- tech-vueSkill
- linear-spanks-gitSkill
- linear-spanksSkill
- linear-workflowSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 19
After a fix, inspect the changed areas and rerun affected checks.
≈ “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
Code Review Strategy
Review the final task diff once against the user's goal, acceptance criteria, repository requirements, and concrete correctness, security, and regression risks. Use the workflow's existing review decision; this skill does not require another reviewer or planning phase.
Classify each finding:
- Blocking: an evidenced defect, unmet acceptance criterion, or violated repository requirement. Cite the affected code/evidence and the requirement or failure. Fix it within the existing plan when its scope and assumptions still hold.
- Suggestion: optional naming, style, cleanup, or design alternatives that satisfy the existing requirements. Report useful suggestions briefly; they do not block completion or authorize edits.
After a fix, inspect the changed areas and rerun affected checks. Preserve unaffected review coverage; do not restart a whole-task review or hunt for additional polish. New evidenced defects still block. Replan only for material changes to the task's scope, acceptance, interfaces, dependencies, or policy.
Finish with the changes, meaningful verification, and any material remaining limitations. Do not produce a separate critique transcript or launch another review when current evidence is sufficient.
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.