run-review-cycle
Skill1 starsChanged 50 days agoMITView on GitHub
Run a full self-correction review cycle over the artifact set.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- add-adrSkill
- add-implementation-decisionSkill
- add-requirementSkill
- adr-managementSkill
- artifact-managementSkill
- enterprise-standardsSkill
- implementation-managementSkill
- implementation-statusSkill
- resume-implementationSkill
- run-implementation-reviewSkill
- start-architectureSkill
- start-ideationSkill
- start-implementationSkill
- writing-styleSkill
- adr-managementSkill
- artifact-managementSkill
- enterprise-standardsSkill
- implementation-managementSkill
- writing-styleSkill
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
- Distinctive: line 12
If it needs a decision, ask the user with AskUserQuestion and send the answer back to it.
- Distinctive: line 13
If its final message hands work to another agent, delegate that work to the named subagent.
- Distinctive: line 18
Run a complete review.
- Very specific: line 20
If I named an application above, review docs/artifacts/<app-name>/ and run python -m artifact_tools validate docs/artifacts/<app-name> …
- Distinctive: line 23
Add your qualitative checks: coverage, traceability, contradictions, testability, scope creep, and blueprint fit.
- Very specific: line 27
Do not edit any files. If the verdict is NEEDS-CHANGES, list precise fixes so artifact-manager can resolve them.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
How to run this in Claude Code
Delegate this request to the critic-reviewer subagent with the Agent tool. Pass it the
request below, the user's arguments and the application's docs/artifacts/<app> path.
If it needs a decision, ask the user with AskUserQuestion and send the answer back to it.
If its final message hands work to another agent, delegate that work to the named
subagent. Report the outcome to the user.
This request
Run a complete review.
- If I named an application above, review
docs/artifacts/<app-name>/and runpython -m artifact_tools validate docs/artifacts/<app-name> --strict. If I did not, review every application withpython -m artifact_tools validate docs/artifacts --strict. - Add your qualitative checks: coverage, traceability, contradictions, testability, scope creep, and blueprint fit.
- Return your standard report (VALIDATION / BLOCKING / ADVISORY / VERDICT).
Do not edit any files. If the verdict is NEEDS-CHANGES, list precise fixes so
artifact-manager can resolve them.
Arguments from the user: $ARGUMENTS
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.

