lfx-self-serve-code-review

Audits commits against repo conventions, review checklists, and upstream API contracts.

12|6|Updated Jul 14, 2025
One-click install
npx skills add https://github.com/linuxfoundation/lfx-self-serve --skill lfx-self-serve-code-review-linuxfoundation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: lfx-self-serve-code-review
Source: https://github.com/linuxfoundation/lfx-self-serve/tree/main/.claude/skills/lfx-self-serve-code-review
Command: npx skills add https://github.com/linuxfoundation/lfx-self-serve --skill lfx-self-serve-code-review-linuxfoundation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Post-commit code reviews often miss repo-specific conventions and upstream API contract mismatches because reviewers rely on general knowledge instead of documented rules. This Skill audits the latest commit (or full branch diff) in the lfx-self-serve repo against its documented rule surface, producing a sourced, severity-calibrated markdown review. ## Core Features & Use Cases - Convention audit with citations: Loads .claude/rules/, the four docs/reviews/ checklists, and architecture docs, then emits findings only when a rule source can be quoted. - Upstream API contract validation: Verifies backend proxy endpoints against Go microservice OpenAPI specs via gh api, and checks Snowflake SQL bind placeholders. - Full-branch mode: Pass the branch keyword to audit the entire branch diff against origin/main for pre-PR sweeps. - Use Case: After committing a new meetings endpoint in apps/lfx-one/src/server/, invoke the Skill to confirm the endpoint matches the lfx-v2-meeting-service OpenAPI contract and complies with the backend checklist before opening a PR. ## Quick Start Ask the AI to run the lfx-self-serve code review on the latest commit, optionally adding the keyword branch for a full-branch pre-PR audit.

Frequently Asked Questions about lfx-self-serve-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a code review on my latest commit in lfx-self-serve?▼

Invoke the Skill after committing; it runs git show on HEAD, loads the repo's rule files and review checklists, and audits each changed file. Findings are rendered as a markdown report with Critical and Important severity groups.

How do I audit an entire branch before opening a pull request?▼

Pass the keyword branch when invoking the Skill to switch to full-branch mode. It fetches origin and diffs origin/main...HEAD, auditing everything the branch adds compared to main.

Does the review validate backend endpoints against upstream APIs?▼

Yes, for changes under apps/lfx-one/src/server/ it fetches the relevant Go microservice's OpenAPI spec via gh api and checks paths, methods, request and response shapes. If the upstream contract cannot be fetched, the report flags it as requiring manual validation.

What happens if a required checklist file cannot be loaded?▼

The report is marked INCOMPLETE with the name of the file that could not be read. The Skill treats the docs/reviews checklists as the primary audit surface, so skipping one invalidates the audit rather than producing a partial report.

What kinds of findings are suppressed as false positives?▼

Missing ChangeDetectionStrategy.OnPush, missing standalone: true, and flags on provideZonelessChangeDetection are suppressed because the app uses Angular 20 with stable zoneless change detection. Any convention finding without a quotable rule source is also dropped.

What reviews are outside this Skill's scope?▼

PR-shape checks like branch naming, DCO and GPG signatures belong to the pr-readiness command, generic senior code review belongs to lfx-general-code-review, and pattern matching against past PR comments belongs to lfx-self-serve-learnings-review.