sdd-review
Skill36 starsChanged 6 months agoMITView on GitHub
Cognitive SDD skill for reviewing an implementation against requirements.md, design.md, and tasks.md, producing review.md with coverage, findings, verification evidence, and merge readiness. Use when the conversation calls for review after implementation or before completion, even without an explicit command. Do not use to implement fixes directly.
We split this skill into the rules it gives an agent
27 rules. 0 are common, 12 are distinctive, and 15 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
15
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 19
Read ../_shared/references/templates.md when writing the review artifact.
- Very specific: line 20
Use package-level templates/review.md as the user-facing template when available.
- Very specific: line 21
Use the SDD Handoff Template and package-level templates/handoff.md when refreshing .ai/sdd/handoff/sdd-brief.md after review.
- Very specific: line 28
If .status is missing or invalid, stop and ask the user to repair it.
- Very specific: line 29
Prefer reviewing after implementation:done.
- Very specific: line 30
If status is implementation:in-progress, state that the review is partial and do not set .status to review:done.
- Very specific: line 31
If status is earlier than implementation:in-progress, block unless the user explicitly asks for a non-final artifact review.
- Very specific: line 32
Read requirements.md, design.md, tasks.md, and decisions.md if present.
- Very specific: line 35
Use files listed in tasks.md as the starting scope.
- Distinctive: line 37
If scope is unclear, ask the user which files or feature area to review.
- Distinctive: line 40
Check each functional requirement and acceptance criterion.
- Distinctive: line 41
Check that design decisions and edge cases were implemented or intentionally updated.
- Distinctive: line 42
Check task completion claims against actual code.
- Distinctive: line 48
Do not flag style issues already covered by formatters unless they indicate a larger problem.
- Distinctive: line 52
Run project verification commands when available.
- Distinctive: line 54
If commands cannot run, document why and perform manual verification where possible.
- Very specific: line 57
Use the Review Template from ../_shared/references/templates.md.
- Very specific: line 61
Do not advance .status for partial or non-final artifact reviews.
- Very specific: line 62
Update .ai/sdd/INDEX.md with the current status when practical.
- Very specific: line 65
If .status becomes review:done, update .ai/sdd/handoff/sdd-brief.md with review verdict, verification evidence summary, known follow-ups, …
- Very specific: line 67
Do not mark ready for release when verdict is Needs fixes or verification failed.
- Distinctive: line 83
Do not fix issues in this skill unless the user explicitly asks to switch to implementation.
- Distinctive: line 84
Do not mark review done if verification was skipped without explanation.
- Very specific: line 85
Do not infer implementation completion from files or task checkboxes alone.
- Distinctive: line 86
Do not approve code that diverges from requirements, design, or traceability mappings unless the spec has been explicitly updated.
- Distinctive: line 87
Do not create noisy review reports.
- Distinctive: line 88
Do not use the handoff to hide review failures.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SDD Review
Validate implementation against the approved SDD artifacts.
Purpose
Review checks whether the delivered code matches the product requirements, technical design, task plan, and project quality bar. It creates a concise but actionable review.md artifact.
Workflow
- Load the SDD reference.
- Read
../_shared/references/sdd-practical.md. - Apply the Language Policy: respond and write artifacts in the user's initial chat language while keeping skill instructions and templates in EN-US.
- Read
../_shared/references/templates.mdwhen writing the review artifact. - Use package-level
templates/review.mdas the user-facing template when available. - Use the SDD Handoff Template and package-level
templates/handoff.mdwhen refreshing.ai/sdd/handoff/sdd-brief.mdafter review. - Load relevant
.ai/steering/*.mdfiles when present, especially conventions, principles, and verification rules.
- Read
- Locate the feature and validate the gate.
- Use
.ai/sdd/specs/NNN-feature-name/. - Read
.status. - Validate
.statusagainst the official status values fromsdd-practical.md. - If
.statusis missing or invalid, stop and ask the user to repair it; do not infer implementation completion from files or task checkboxes alone. - Prefer reviewing after
implementation:done. - If status is
implementation:in-progress, state that the review is partial and do not set.statustoreview:done. - If status is earlier than
implementation:in-progress, block unless the user explicitly asks for a non-final artifact review. - Read
requirements.md,design.md,tasks.md, anddecisions.mdif present.
- Use
- Identify review scope.
- Use files listed in
tasks.mdas the starting scope. - Inspect current repository changes when available.
- If scope is unclear, ask the user which files or feature area to review.
- Use files listed in
- Review against the spec.
- Check each functional requirement and acceptance criterion.
- Check that design decisions and edge cases were implemented or intentionally updated.
- Check task completion claims against actual code.
- Flag missing, partial, or divergent behavior.
- Review code quality.
- Evaluate correctness, security, accessibility, performance, error/loading/empty states, maintainability, and tests.
- Focus on high-signal findings.
- Do not flag style issues already covered by formatters unless they indicate a larger problem.
- Deduplicate repeated issues into one finding with affected files listed.
- Verify.
- Run project verification commands when available.
- At minimum, run or identify lint/test/build equivalents for the stack.
- If commands cannot run, document why and perform manual verification where possible.
- Write review.
- Use the Review Template from
../_shared/references/templates.md. - Save as
.ai/sdd/specs/NNN-feature-name/review.md. - Include coverage tables for requirements, tasks, and design decisions, plus quality check, verification result, issues found, and verdict.
- Set
.statustoreview:doneonly when starting fromimplementation:done, the review is complete, and the verdict is not blocked by missing information. - Do not advance
.statusfor partial or non-final artifact reviews. - Update
.ai/sdd/INDEX.mdwith the current status when practical; if not updated, tell the user the index may be stale.
- Use the Review Template from
- Refresh the SDD handoff when review is complete.
- If
.statusbecomesreview:done, update.ai/sdd/handoff/sdd-brief.mdwith review verdict, verification evidence summary, known follow-ups, blockers, and readiness for QA/release. - Preserve exact source paths to the reviewed spec artifacts.
- Do not mark ready for release when verdict is
Needs fixesor verification failed.
- If
Verdict Rules
Approved: requirements pass, design is followed, verification passes, no blocking issues.Approved with follow-ups: core requirements pass, only low/medium non-blocking issues remain.Needs fixes: any Must Have requirement fails, verification fails, or high/critical issue exists.
Output
.ai/sdd/specs/NNN-feature-name/review.md- Updated
.statuswhen complete - Refreshed
.ai/sdd/handoff/sdd-brief.mdwhen.statusbecomesreview:done
Critical Rules
- Do not fix issues in this skill unless the user explicitly asks to switch to implementation.
- Do not mark review done if verification was skipped without explanation.
- Do not infer implementation completion from files or task checkboxes alone; require valid
.status. - Do not approve code that diverges from requirements, design, or traceability mappings unless the spec has been explicitly updated.
- Do not create noisy review reports; prioritize actionable findings.
- Do not use the handoff to hide review failures; blockers and failed verification must be explicit.
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- dataelement/bisheng★ 12ksame name
- khangpqvn/SDDADD★ 12same name
- waldo1001/waldo.BCObservatory★ 10same name
- chucky2305/sdd-antipattern-plugin★ 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.
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.

