update-review-rules
Skill246 starsChanged 5 months agoMITView on GitHub
Add a new issue type to one of Sculptor's review-rule docs. Use when you've encountered a class of bugs, anti-patterns, or flaky test patterns that should be caught in future reviews.
In this repository23 other files it gives its agents.
- openhost-agent/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- address-commentsSkill
- auto-qa-changesSkill
- auto-qa-iphoneSkill
- batch-claude-runnerSkill
- code-review-checklistSkill
- cut-releaseSkill
- debug-integration-testSkill
- frontend-design-tokensSkill
- manually-qa-branchSkill
- measure-react-rendersSkill
- openhost-frontend-previewSkill
- openhost-sculptorSkill
- post-pr-to-slackSkill
- profile-sculptor-backendSkill
- promote-releaseSkill
- run-integration-testSkill
- storybook-screenshotSkill
- update-help-docsSkill
- update-specsSkill
- write-integration-testSkill
- write-release-notesSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 3 are distinctive, and 10 are 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.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Add a new issue type to one of Sculptor's review-rule docs to prevent a class of issues from recurring.
- Distinctive: line 30
Read all the review docs listed above to understand the existing rules, their format, and their naming conventions.
- Very specific: line 32
If the rule is about Playwright tests, integration test patterns, or test isolation/structure → integration_tests.md.
- Very specific: line 33
If the rule is about visual/design quality: design-system usage, tokens, component reuse, UI copy → design.md.
- Very specific: line 34
If the rule is about where files live, when files/directories are warranted, or how things are named → file_structure.md.
- Very specific: line 35
If the rule references Sculptor-specific frontend hooks, atoms, file paths, or our data-flow conventions (e.g.
- Very specific: line 36
If the rule is purely about React's framework primitives and would apply in any React codebase → react.md.
- Very specific: line 37
When in doubt for frontend rules, prefer sculptor.md over react.md.
- Very specific: line 77
Use no_ prefix for patterns that should not exist (e.g., no_effect_chains, no_sleep_then_assert)
- Very specific: line 78
Use use_ prefix for prescriptive positive patterns (e.g., use_derived_atoms, use_expect_not_assert)
- Very specific: line 79
Use a descriptive noun/adjective for structural issues (e.g., monolithic_component, unstable_list_keys)
- Distinctive: line 83
Only include code examples when absolutely necessary.
- Distinctive: line 85
Place the new rule near related rules in the chosen file.
≈ “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
Add a Review Rule
Add a new issue type to one of Sculptor's review-rule docs to prevent a class of issues from recurring.
The review-rule docs:
docs/development/review/react.md— generic React rules that would apply in any React codebase: effects, state, refs, render purity, performance, props, lists.docs/development/review/sculptor.md— Sculptor-specific frontend conventions: backend data hooks (WS-pushed atoms, HTTP-pulled TanStack queries), Jotai atom usage, component-level invariants tied to our codebase.docs/development/review/design.md— design quality judgments a linter can't make: Radix-first component usage, correct token selection, reuse of shared components, consistent UI copy.docs/development/review/file_structure.md— file placement, feature layout, and naming: code located with its feature, kind-directory anatomy, helper/subfeature thresholds, component naming and domain vocabulary.docs/development/review/integration_tests.md— Sculptor integration test rules: Playwright assertion patterns, test isolation, POM usage, flaky-pattern avoidance.
Input
The user provides a description of the problem — this could be:
- A bug they just fixed and want to prevent in the future
- A code pattern they noticed during review that should be flagged
- A flaky test or test pattern that should be caught earlier
- A link to a file/line or diff that demonstrates the issue
Steps
- Read all the review docs listed above to understand the existing rules, their format, and their naming conventions.
- Decide which file the new rule belongs in:
- If the rule is about Playwright tests, integration test patterns, or test isolation/structure →
integration_tests.md. - If the rule is about visual/design quality: design-system usage, tokens, component reuse, UI copy →
design.md. - If the rule is about where files live, when files/directories are warranted, or how things are named →
file_structure.md. - If the rule references Sculptor-specific frontend hooks, atoms, file paths, or our data-flow conventions (e.g.
useUnifiedStream,BackendQueryResult,workspaceAtomFamily) →sculptor.md. - If the rule is purely about React's framework primitives and would apply in any React codebase →
react.md. - When in doubt for frontend rules, prefer
sculptor.mdoverreact.md; revisit if the rule turns out to be more generic than expected.
- If the rule is about Playwright tests, integration test patterns, or test isolation/structure →
- Determine whether an existing rule already covers the issue (check all the docs). If it does, tell the user which rule covers it and ask if they'd like to refine that rule instead. Do not add a duplicate.
Draft a new rule following the exact format of existing rules in the chosen file.
For
react.mdandsculptor.md(flat list,## rule_nameheadings):--- ## `snake_case_rule_name` **Question:** A yes/no question that a reviewer can ask about the code. One or two paragraphs explaining why this is a problem and what the correct approach is. **What to look for:** - Concrete pattern or code smell to search for - Another pattern **Fix:** (optional) Brief description of how to fix it. **Exceptions:** (optional) Cases where this pattern is acceptable.For
integration_tests.md(sectioned,### rule_nameinside an existing## Section):--- ### `snake_case_rule_name` **Question:** ... [rest is the same as above, but the heading is `###` and the rule lives under one of the existing `## Section` groupings — pick the section that matches the rule's topic, e.g. "Playwright Assertions", "Test Isolation", "Test Structure"]- Choose a clear
snake_casename that describes the problem (not the fix). Follow the naming conventions:- Use
no_prefix for patterns that should not exist (e.g.,no_effect_chains,no_sleep_then_assert) - Use
use_prefix for prescriptive positive patterns (e.g.,use_derived_atoms,use_expect_not_assert) - Use a descriptive noun/adjective for structural issues (e.g.,
monolithic_component,unstable_list_keys)
- Use
- Write the rule to be generic — it should describe a class of issues, not a single instance. Strip out details specific to the user's particular bug (component names, variable names, business logic, Linear ticket IDs). For
sculptor.mdandintegration_tests.mdrules, naming our codebase concepts is fine (and expected); forreact.mdrules, the content should apply in any React codebase. The "What to look for" section should describe concrete, recognizable patterns a reviewer can spot in code. - Only include code examples when absolutely necessary. Lean on the description, explanation, and "What to look for" patterns to convey the rule. The rule should be self-contained without code. Test rules sometimes benefit more from a "Bad/Good" pair because Playwright APIs are pattern-heavy.
- Place the new rule near related rules in the chosen file. Use your judgement — group it with rules about similar topics (effects, state, atoms, refs, performance, Playwright assertions, test isolation, etc.).
- Show the user the new rule (and which file you're adding it to) and ask for confirmation before writing it to the file.
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.

