techygarg/lattice-review-refiner
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classification, report format, scope rules, insight capture, and health logging. Produces a formal review-standards.md document that the review molecule will use as its process configuration. Use when the user says 'customize review', 'configure review', 'review preferences', 'review settings', 'change review process', or 'set up review'.
This is a copy. The original lives at techygarg/review-refiner.
npx skills add https://github.com/techygarg/lattice --skill review-refiner
.lattice/standards/review-standards.md (or custom path from .lattice/config.yaml → paths.review_standards)mode: overlay): A slim document containing only sections that differ from the defaults. The review molecule reads its embedded defaults first, then applies this document's sections on top. This is the expected common case.mode: override): A comprehensive standalone document that fully replaces the molecule's embedded defaults. For teams with fundamentally different review processes.paths.review_standards in .lattice/config.yaml./assets/template.md for the full document structure, default content, and interview guidance commentsThis refiner configures the review *process* -- how the review molecule orchestrates atom output. It does NOT configure what atoms check for.
| Belongs here (process orchestration) | Belongs in atom refiners (quality standards) |
|---------------------------------------|----------------------------------------------|
| Which atoms load and when | What checks an atom runs |
| Severity level definitions | What constitutes a violation |
| Report format and grouping | Checklist items and anti-patterns |
| Delta scope rules | Layer definitions, naming rules |
| Insight capture preferences | Domain modeling rules |
| Health log format | Security check thresholds |
| Custom review dimensions | Atom-specific validation logic |
If a user asks about changing what an atom checks for, redirect them to the appropriate atom refiner (architecture-refiner, clean-code-refiner, ddd-refiner).
Before starting the interview, check whether a custom document already exists:
.lattice/config.yaml — does paths.review_standards point to a file?Look for signals that inform the conversation:
.lattice/reviews/review-log.md — what atoms have been loading? What severity patterns exist? Are there recurring findings?.lattice/learnings/operational-learnings.md — what patterns have been captured? Is the file growing dense in any category?.lattice/config.yaml for paths.architecture, paths.clean_code, paths.ddd_principles) This tells you which atoms the team cares about.Share relevant findings with the user at the start: "I looked at your review history and noticed [patterns]. I'll use that as context for our conversation."
If the project is new with no review history, proceed with defaults as the starting point.
The first decision in the conversation. Present the three options:
"How would you like to configure your review process?
The defaults cover a solid review workflow. Option 1 is recommended unless your review process needs to be fundamentally different."
Map the choice:
mode: overlaymode: overrideThis should be fast. Many sections will be "keep as-is."
This is thorough. Every section gets attention and appears in the output.
secure-coding from conditional to always-loaded.Read ./assets/template.md and follow the <!-- INTERVIEW GUIDANCE: --> comments for each section. Those comments contain the specific questions to ask, probing questions, and what is customizable vs fixed.
Decisions in early sections affect later sections. When a user changes an early section, flag the dependent sections:
| Decision in | Affects | How |
|-------------|---------|-----|
| §1 Atom Loading | §2, §3, §5, §6 | Per-atom severity overrides reference atom names; report sections map to loaded atoms; insight categories follow atoms; log atom names must match |
| §2 Severity | §3, §5, §6, §7 | Report ordering follows severity levels; capture criteria reference severity; log counts use severity names; custom dimensions need severity assignment |
| §4 Scope Rules | §1, §7 | Expanded scope may trigger more conditional atoms; custom dimensions follow scope rules |
| §7 Custom Dimensions | §2, §3 | Custom dimensions contribute findings needing severity classification and report placement |
When a dependency is triggered, inform the user: "Since you changed [X], we should also review [Y] — it's affected by that decision."
For each of the 7 default sections:
For each of the 7 default sections:
mode: overlaymode: overrideStrip all <!-- INTERVIEW GUIDANCE: --> comments from the output. The final document is a clean specification.
Determine output path:
.lattice/config.yaml exists and has paths.review_standards, use that path..lattice/standards/review-standards.md.Write the document:
.lattice/standards/ directory (and .lattice/ parent) if it does not exist.Update config:
.lattice/config.yaml does not exist, create it with: paths:
review_standards: .lattice/standards/review-standards.md
.lattice/config.yaml exists but has no paths.review_standards, add the key. Preserve all existing content..lattice/config.yaml exists and already has the key, no config change needed.Confirm to user:
"Your review standards document has been written to [PATH] in [overlay|override] mode. The review molecule will now use it [on top of the defaults | instead of the defaults] when running reviews."
Before writing the final document, verify:
<!-- INTERVIEW GUIDANCE: --> comments remainmode: overlay<!-- INTERVIEW GUIDANCE: --> comments remainmode: override.lattice/config.yaml) is correctly updatedTake techygarg/lattice-review-refiner from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.