code-review
Skill1 starsChanged 7 months agoMITView on GitHub
Perform a comprehensive code review of an LWC component, Apex class, or both against project standards
194 other projects use a version of this.
Adopted by
Most recently taken up by
- doggy8088/spec-kittheir own version, first seen Nov 9, 2026
- strelov1/freehiretheir own version, first seen Nov 9, 2026
- storybookjs/storybooktheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- supabase/supabasetheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use close-spec, design-with-images and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
PydanticSkilladd-new-model
Add support for a newly-released language or image generation model in pydantic-ai (e.g. openai:gpt-5.6, anthropic:claude-sonnet-5, openai:gpt-image-2). Use when a provider ships a new model id and you need to wire literals, profile flags, adapters, and tests to recognize it. Handles SDK-lag, gateway list conventions, capability probing, and direct image-model geometry.
Also in 9 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
Microsoft AzureSkillazsdk-common-apiview-feedback-resolution
Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_customized_code_update, azure-sdk-mcp:azsdk_typespec_delegate_apiview_feedback, azure-sdk-mcp:azsdk_run_typespec_validation, azure-sdk-mcp:azsdk_package_generate_code.
Also in 6 projects that use this
Microsoft AzureSkillazsdk-common-generate-sdk-locally
Generate and finalize Azure SDKs locally from TypeSpec, including build, checks, tests, changelog, metadata, and version updates by default. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "run CI checks", "validate package", "run checks", "update changelog", "fix SDK build errors", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.
Also in 6 projects that use this
- +4 more from dzhng
- +2 more from Azure
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 194
- mattpocock/skills★ 309ksame name
- TheAlgorithms/Python★ 226ksame name
- microsoft/vscode★ 195ksame name
- github/spec-kit★ 149ksame name
- ggml-org/llama.cpp★ 134ksame name
- supabase/supabase★ 115ksame name
- storybookjs/storybook★ 91ksame name
- shareAI-lab/analysis_claude_code★ 80ksame name
- shareAI-lab/learn-claude-code★ 80ksame name
- vectorize-io/hindsight★ 60ksame name
184 more not listed
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.
In this repository53 other files it gives its agents.
- templates/CLAUDE.mdCLAUDE.md
- adrSkill
- agent-deploySkill
- agent-discoverSkill
- agent-eval-trendSkill
- agent-exchange-listSkill
- agent-specSkill
- agent-testSkill
- agent-vs-flow-vs-apexSkill
- before-vs-after-triggerSkill
- complexitySkill
- coverage-trendSkill
- dead-codeSkill
- dependency-graphSkill
- deploySkill
- destructive-changesSkill
- diff-deploySkill
- erdSkill
- field-impactSkill
- flaky-test-finderSkill
- flow-auditSkill
- flow-vs-apexSkill
- fls-auditSkill
- gateway-configSkill
- generate-docsSkill
- limit-usageSkill
- lwc-vs-reactSkill
- mcp-tool-vs-restSkill
- notifySkill
- onboardSkill
- org-diffSkill
- org-exploreSkill
- package-versionSkill
- pattern-packSkill
- perf-reviewSkill
- permset-auditSkill
- pr-prepareSkill
- queueable-vs-batchSkill
- quick-deploySkill
- react-initSkill
- release-notesSkill
- scratch-orgSkill
- security-scanSkill
- sequence-diagramSkill
- sf-initSkill
- sharing-reviewSkill
- slack-agentSkill
- soql-analyzerSkill
- test-coverageSkill
- test-dataSkill
- test-planSkill
- trust-evalSkill
- trust-layer-auditSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 184 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Always start by reading .claude/sf-project.json for paths, naming convention, and quality targets.
- Distinctive: line 39
If reviewing "both" or if the LWC imports Apex controllers, read those controllers too
- Distinctive: line 55
If reviewing "both", use the LWC name
- Very specific: line 57
Create the code-reviews/ directory if it doesn't exist
- Distinctive: line 158
Run git diff --name-only main...HEAD to find changed source files
- Very specific: line 167
When the input is all:
- Very specific: line 170
After all individual reviews, produce a summary at code-reviews/SUMMARY.md:
- Distinctive: line 184
Do NOT produce individual review files — the audit is a summary-only pass
- Distinctive: line 191
Do NOT edit any source code files — this is a read-only review of the codebase
- Distinctive: line 193
If documentation is missing or outdated, flag it but don't create it
“Common” is measured: kept by at least 6 in 10 of the 184 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
You are performing a code review for this Salesforce project. Assess code quality, identify issues, and highlight strengths — but make no edits.
Read Project Config First
Always start by reading .claude/sf-project.json for paths, naming convention, and quality targets. References below to {paths.lwcSource}, {naming.lwc.prefix}, etc. resolve from that file.
Input
The user provided: $ARGUMENTS
This could be:
- An LWC component name (matches the project's
naming.lwc.prefix) - An Apex class name
- A file path
- The word
bothfollowed by an LWC name (e.g.,both myComponent) to review the LWC and all its Apex dependencies - The word
all— review every in-scope LWC component (see Batch Modes) - The word
audit— produce a single compliance matrix instead of per-component reviews (see Batch Modes) - The word
pr— review only files changed sincemainHEAD (see PR mode)
CI flags (per ${CLAUDE_PLUGIN_ROOT}/docs/ci-output-contract.md):
--ci— machine-readable output, exit codes per contract--format json|sarif— output format (defaultjsonin CI mode)--out <path>— write to file instead of stdout--fail-on error|warning|note— minimum severity that triggers exit 1 (defaulterror)
Steps
- Identify the target. Determine if the input is an LWC, Apex class, or both. If a component name is given without a path, search in
{paths.lwcSource}and{paths.apexSource}. - Read all source files.
- For LWC: Read the
.js,.html,.css, and.js-meta.xmlfiles - For Apex: Read the
.clsfile - If reviewing "both" or if the LWC imports Apex controllers, read those controllers too
- For LWC: Read the
- Read the project standards. These are critical — review against them:
docs/patterns/salesforce-patterns.md— generic platform patternsdocs/patterns/project-patterns.md— project-specific patterns and shared componentsdocs/lwc-standards.md— CSS, JS, and accessibility rules (for LWC reviews)docs/apex-standards.md— Governor limits, SOQL, DML, security rules (for Apex reviews)docs/quality-checklist.md— Unified quality checklistdocs/project-context.md— Object model and channel context
- Read existing documentation for the component if it exists in
{paths.lwcDocs}or{paths.apexDocs}to check whether the docs are still accurate. - Produce the review report using the format below.
- Save the review report to the
code-reviews/directory in the project root.- File name:
{ComponentName}.md - If reviewing "both", use the LWC name
- Overwrite if the file already exists
- Create the
code-reviews/directory if it doesn't exist
- File name:
Review Report Format
## Code Review: {ComponentName}
### Summary
(1-2 sentences: what this component does and overall assessment)
### Strengths
- (Things done well — be specific, reference line numbers or patterns followed)
### Issues
#### Critical (must fix — security, data loss, broken functionality)
- (or "None")
#### High (should fix — governor limits, performance, accessibility gaps)
- (or "None")
#### Medium (recommended — maintainability, pattern compliance, code clarity)
- (or "None")
#### Low (nice to have — naming, minor style, documentation drift)
- (or "None")
### Pattern Compliance
| Pattern | Source | Applies? | Followed? | Notes |
|---------|--------|----------|-----------|-------|
| Paginated Datatable | SF-1 | Yes/No | ✅/❌/Partial | (details) |
| Record Detail View | SF-2 | Yes/No | ✅/❌/Partial | (details) |
| LMS Subscription Lifecycle | SF-3 | Yes/No | ✅/❌/Partial | (details) |
| XML Meta Config | SF-4 | Yes/No | ✅/❌/Partial | (details) |
| Paginated Apex Controller | SF-5 | Yes/No | ✅/❌/Partial | (details) |
| AuraEnabled Methods | SF-6 | Yes/No | ✅/❌/Partial | (details) |
| Trigger Handler Framework | SF-7 | Yes/No | ✅/❌/Partial | (details) |
| Toast Notifications | SF-8 | Yes/No | ✅/❌/Partial | (details) |
| Wrapper / DTO Classes | SF-9 | Yes/No | ✅/❌/Partial | (details) |
| Confirmation Dialog | SF-10 | Yes/No | ✅/❌/Partial | (details) |
| Filter Whitelist | SF-11 | Yes/No | ✅/❌/Partial | (details) |
| Apex Inline Docs | SF-12 | Yes/No | ✅/❌/Partial | (details) |
| LWC Inline Docs | SF-13 | Yes/No | ✅/❌/Partial | (details) |
| LWC Jest Test Structure | SF-14 | Yes/No | ✅/❌/Partial | (details) |
| HTTP Callout via Named Credential | SF-15 | Yes/No | ✅/❌/Partial | (details) |
| Apex REST Service | SF-16 | Yes/No | ✅/❌/Partial | (details) |
| Custom Metadata Type Lookup | SF-17 | Yes/No | ✅/❌/Partial | (details) |
| LWC Internationalization | SF-18 | Yes/No | ✅/❌/Partial | (details) |
| Virtualized List for Large Datasets | SF-19 | Yes/No | ✅/❌/Partial | (details) |
| Lazy-Loaded Sub-component | SF-20 | Yes/No | ✅/❌/Partial | (details) |
| (Any project-specific patterns from project-patterns.md that apply) | PRJ-N | Yes/No | ✅/❌/Partial | (details) |
| (Any pack-installed patterns that apply: AGT-* / RX-* / PE-* / CDC-* / etc.) | (prefix)-N | Yes/No | ✅/❌/Partial | (details) |
### Documentation Status
- (Is the doc file up to date with the current code? Flag any drift.)
### Suggestions
- (Optional improvements that aren't strictly issues — performance optimizations, refactoring ideas, accessibility enhancements)Review Checklist
Assess all applicable items from docs/quality-checklist.md — the unified quality checklist.
For LWC reviews, check: JavaScript, CSS, HTML/Accessibility, and Meta XML sections. For Apex reviews, check: Security, Governor Limits, Error Handling, and Code Quality sections. For "both" reviews, check all sections.
CI Mode
In CI mode (--ci), produce findings in the internal shape (see docs/ci-output-contract.md) instead of the Markdown report:
[
{
"ruleId": "SF-5",
"severity": "warning",
"message": "Paginated controller missing the count companion method",
"file": "force-app/main/default/classes/OrderController.cls",
"line": 42,
"ruleHelpUri": "<patternsSalesforceDoc>#paginated-controller",
"tool": "code-review"
}
]For SARIF output, source ${CLAUDE_PLUGIN_ROOT}/hooks/lib/sarif.sh and pipe through sarif_emit "argo/code-review" "<plugin-version>".
Exit codes (per contract):
- 0 — no findings at or above
--fail-onthreshold - 1 — findings at or above the threshold
- 2 — invocation error
Rule ID prefixes used by code-review:
SF-N/PRJ-N— pattern-compliance findings (matches the pattern doc IDs)LWC-*— LWC-specific issues (e.g.,LWC-WIRE-IN-LOOP)APEX-*— Apex-specific issues not covered by /security-scan or /fls-audit
PR Mode
Invoked as /argo:code-review pr:
- Run
git diff --name-only main...HEADto find changed source files - For each changed file, dispatch into the per-file review path
- Aggregate findings; emit a single report (Markdown or CI JSON)
- Useful in CI as the gate on PR merges
Batch Modes
all — Review all in-scope components
When the input is all:
- List all directories in
{paths.lwcSource}matching{naming.lwc.prefix}*(or all directories ifnaming.lwc.prefixis empty), excluding any matching patterns innaming.lwc.excludePrefixes - For each component, run a full review and save to
code-reviews/{componentName}.md - After all individual reviews, produce a summary at
code-reviews/SUMMARY.md:- Table: component name, critical issues count, high issues count, overall assessment
- Top 5 most common issues across all components
- Components with the best/worst pattern compliance
audit — Standards compliance matrix
When the input is audit:
- List all in-scope LWC components and their Apex dependencies
- For each, do a lightweight pass against
docs/quality-checklist.mdand both pattern docs - Produce a single compliance report at
code-reviews/AUDIT.md:- Compliance matrix: rows = components, columns = patterns (SF-1 through SF-20, plus any PRJ-* and pack-installed prefixes — AGT-* / RX-* / PE-* / CDC-* / etc. — that apply), cells = Pass/Fail/N/A
- Summary of most common violations
- Recommended priority fixes (grouped by category)
- Do NOT produce individual review files — the audit is a summary-only pass
Rules
- Be specific: reference file names and line numbers
- Be balanced: always include strengths, not just problems
- Be actionable: every issue should have a clear fix
- Do NOT edit any source code files — this is a read-only review of the codebase
- The only files you should write are review reports in
code-reviews/ - If documentation is missing or outdated, flag it but don't create it
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

