review-scope
Skill73 starsChanged 6 days agoApache-2.0View on GitHub
Review a change against issue, RFC, branch, and user-request scope. Use when a broad review needs a dedicated scope/completeness pass or when the user asks whether the implementation actually matches the intended surface.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-learningSkill
- bump-rfcSkill
- closeoutSkill
- create-github-issueSkill
- create-planSkill
- create-pr-descriptionSkill
- fixSkill
- flag-compiler-bugSkill
- fleet-auditSkill
- hello-worldSkill
- loopSkill
- orchestrate-parallel-workSkill
- ralph-loopSkill
- review-and-fixSkill
- review-architectureSkill
- review-code-smellsSkill
- review-docs-claimsSkill
- review-incan-source-qualitySkill
- review-orchestrateSkill
- review-rfcSkill
- review-rust-proseSkill
- reviewSkill
- review-test-styleSkill
- start-workSkill
- testSkill
- write-commit-messageSkill
- write-rfcSkill
- yeet-prSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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
- Distinctive: line 28
Write a slice report at:
- Very specific: line 32
Do not write to the canonical .agents/state/review-report.md.
- Distinctive: line 48
Do not suppress a finding just because it may be non-blocking for the immediate fix loop.
- Distinctive: line 77
If there are no findings, say so explicitly.
≈ “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
Review Scope — Incan Compiler
Purpose
/review-scope is a cross-file report-only reviewer for intended scope and delivered behavior.
Own:
- missing in-scope work
- out-of-scope additions
- issue/RFC/branch intent satisfaction
- docs/examples/scaffolds promising behavior the code does not deliver
Do not own:
- local prose quality unless it creates scope drift
- detailed architecture placement
- test style details
- final branch-clean judgment
Output artifact
Write a slice report at:
.agents/state/review-report.scope.md
Do not write to the canonical .agents/state/review-report.md.
Workflow
- Derive intended scope from:
- current user request
- issue/branch metadata
- governing RFC/design docs
- user-facing docs/examples on the branch
- Review the whole presented worktree as a single review surface, not only the orchestrator's guess at the "main task files".
- Flag:
- missing promised behavior
- scope creep
- examples/docs/scaffolds that imply unsupported flows
- adjacent branch churn or future-work noise when it materially affects reviewability or branch quality
- Attach findings to concrete files when possible, even if the reasoning was cross-file.
- Do not suppress a finding just because it may be non-blocking for the immediate fix loop. Relevance is decided later.
Slice report shape
# Review Slice Report
- role: scope
- worker: <agent-id or stable label>
- status: in_progress | clean | blocked
## Scope
- issue / RFC:
- reviewed surfaces:
- ...
## Findings
- [ ] blocker | behavior | docs-generated fiction | workspaces/docs-site/docs/language/reference/project_lifecycle.md:181
Says plain `incan build` remains a valid direct command, but the CLI still requires `<FILE>` outside `--lib`.
## Reviewed Clean Surfaces
- <optional, only for risky or disputed clean calls>
## Notes
- <optional broader scope observation>
Use `Notes` for context, but keep actual concerns in `## Findings` rather than hiding them in prose.If there are no findings, say so explicitly.
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.

