rizanw/steno-spec / packages/skills/skills/steno-review
steno-review
Verifiedsteno-review — zero-history review
Why: a reviewer that shares your conversation agrees with you. Reviewers must see only the packet. A review settles and removes. It never grows the spec on its own, and it ends: one full round, at most one verify round.
Steps
steno review --stage <requirements|design|tasks|drift>→ writesreviews/<date>-<stage>-packet.mdand prints the round (fullorverify), the size and any warning. Note the path; tell the user every warning. If it says nothing changed, go to step 7.- EGM, only on request. If
.steno/config.yamlsetsreviewer: egmor the user asked for EGM in this request, and EGM is installed: invokeegm-reviewon that packet file (fordrift,egm-drift-report), telling it which stage the file is; for requirements or tasks, add that it is not a design document, so no architecture, alternatives or risks sections are expected. Save its findings asreviews/<date>-<stage>.md. Go to step 5. - Otherwise (the default) check whether this session can start sub-agents that do not inherit the conversation. If it cannot, stop and tell the user a fresh-context review is not possible here; do not review in your own context.
- Start one sub-agent per persona in
reviewers/that applies to the stage (each file says which); in a verify round leave outscope. If a sub-agent type namedsteno-reviewer-<persona>is registered (Claude Code aftersteno init), use it and give it only the packet path. Otherwise start a plain sub-agent and give it only: the persona file, the packet path, read-only access. Merge duplicates and writereviews/<date>-<stage>.md(append# Round Nafter the first) in three groups:## Decide,## Fix,## Notes for the next stage, each line- [sev] <id>: <finding> → <change or options>. - Decide first. Ask the user each
decidefinding, scope cuts before additions, one question at a time with the options and your pick. Never apply adecideon your own, and never turn one into new text before the user says yes. Write each answer and each rejected finding as one line inreviews/<stage>-decisions.md(- <id>: <decision>, <reason>); the next packet shows it to reviewers so they do not reopen it. A cut goes to## Non-goalswith its trigger. A split is not a cut: before deleting anything, runsteno new <slug> --title "<Title>"for the part that leaves, move its requirements, glossary terms and open questions into that spec'srequirements.md(renumbered from R1;steno lintthere), and only then replace them here with one## Non-goalsline naming the new spec. Tell the user the new spec exists and is still at requirements. - Then fix. Drop every
fixon an item that was cut. Apply the rest: afixrewrites or deletes existing text and adds no criterion, section or task. Leavenotefindings in the findings file; do not edit them into the document. Runsteno lint, then list each appliedfixto the user in one line. - Gate. The review has passed when no high
fixis open and everydecidehas an answer. Say so, give the size before and after, and offersteno approve <stage>. Offer one verify round (step 1 again) only if step 6 changed the document and a high finding was among the fixes. After the verify round, or when the CLI warns about the round limit, do not start another: list what is still open and let the user approve, edit or ask forsteno review --full. - Open questions. If the document still lists entries under
## Open questions, list them numbered and ask the user to pick: Interview (offer first; one question at a time with your recommended answer and its trade-off; after each answer edit the document, delete the question (and the heading with the last one), confirm in one line; "skip" and "stop" are allowed; finish withsteno lint), Edit myself (when the user says done, runsteno lintand re-list what is open), or Skip (steno approve <stage>; the questions are settled in the next stage). Skip this step fordrift.
Personas (reviewers/)
scope · completeness · clarity · code-fit · implementability · ears
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |