linuxfoundation

Run the local pre-PR review trio on the current repo — the general reviewer plus the repo's own code and learnings reviewers — on headless Pi when it is available, or Claude subagents otherwise, and return their ordinary Markdown reports. Use after a commit,…

The general code-review method for LFX local reviews — correctness, security, data privacy, error handling, simplicity, naming, DRY, testing, performance and style, over one explicit pinned range, normally the single commit at the branch's tip. Carries no…

LFX cross-repo topology and ownership router. Use when the task spans more than one LFX repo, asks "which repo owns X", "where does Y live", "what repos does this touch", "what consumes Z", or needs a peer-repo file path from inside a single repo. Loads…

Central explainer for adding object storage capability to an LFX V2 service. Covers the S3-compatible storage decision, hard requirements (no presigned uploads, private buckets only, 20 MB cap, per-service bucket ownership, metadata/payload separation), Go…

Provisioning requirements for LFX object storage backends in deployed environments (prod, staging, shared dev): private S3 buckets, CloudFront with Origin Access Control, shared wildcard certificate, and IRSA write access, all in `lfx-v2-opentofu`. Written…

Address PR review comments, fetches unresolved threads, makes code changes, commits with a summary, responds to each comment, resolves threads, posts a follow-up summary, dismisses stale "changes requested" reviews, and re-requests review. Use whenever…

Senior review method for lfx-skills pull requests. Use whenever the task is to review a pull request on this repo, whatever it changes.

How to judge an lfx-skills pull request: what makes a skill or reviewer agent sound (frontmatter, triggers, internal consistency, reference accuracy) and whether the change respects the central-vs-repo boundary of the LFX skills fanout architecture. Use on…

Review a pull request against LFX architecture standards. Requires the reviewer's HEAD to be the PR's branch (author scenarios are natural; external reviewers run `gh pr checkout <N>` first). Fetches main fresh, then launches…

Pre-PR shape check on local lfx-self-serve work. Audits PR-shape sanity (branch name, ticket reference — JIRA or GitHub Issue —, conventional-commit format, rebase status, DCO + GPG signing per commit, total diff size, and protected files touched) against the…

Mechanical pre-PR pipeline, license headers, format, lint, build, protected file check, commit verification, and PR change summary. Run after the post-commit reviewer trio has been drained and `/lfx-self-serve-pr-readiness` has passed. Pattern/convention…

Guided development workflow for building, fixing, updating, or refactoring code, components, services, backend endpoints, shared types, or full features. Use whenever someone wants to add a feature, fix a bug, modify existing code, create something new,…

Senior code-review method for lfx-self-serve (LFX One) pull requests. Use when the task is to review a PR for correctness, design, and security on this repo.

How to judge the implementation of an lfx-self-serve (LFX One) pull request: the general quality dimensions (correctness, error handling, tests, performance, readability, code truthfulness) and how to hold the diff to the repo's documented standards for the…

Security review for lfx-self-serve (LFX One) pull requests. Use when a PR touches the auth middleware or route classification, the OIDC session or token-exchange paths, a server controller or service, a proxy call to an upstream microservice, the public…

Use when building or modifying a Self Serve drawer component — slide-in detail panels with lazy data loading, chart integration, two-way `[(visible)]` bindings, and the standard responsive width class chain. Trigger phrases include "building a drawer", "open…

Repo-owned learnings review brain for local pre-PR review on lfx-v2-newsletter-service. Matches the reviewed change against the empirical pattern knowledge base in docs/reviews/knowledge-base/ — patterns extracted from real past PR review comments on this…

Launch the three local reviewers as Claude subagents when lfx-local-review selects the Claude fallback.

Repo-owned code-review brain for local pre-PR review on lfx-v2-newsletter-service. Audits the reviewed change against this repo's written rule surface — CLAUDE.md, the repo-local skills, and the service-owned contract docs — and returns an ordinary Markdown…

Senior code-review method for lfx-v2-newsletter-service pull requests. Use when the task is to review a PR for correctness, design, and security and post review comments on this repo. Posts inline severity-tagged comments plus a summary on the PR itself.

Cut a new GitHub release/tag for lfx-v2-newsletter-service from main, verify the tagged build published the image and Helm chart, then open a version-bump PR on lfx-v2-argocd pinning the target environments to the new version. Use when the user asks to "cut a…

How to drive an open lfx-v2-newsletter-service pull request through the agentic review flow: read the lfx-reviewer "Agentic review check" comment, fix or rebut every blocking finding, answer every review thread, push one batched round at a time, and loop…

The exact format for the two verdict comments the agentic review posts on a lfx-v2-newsletter-service pull request: the needs-human verdict (escalation) and the agentic-check verdict (conductor). Use whenever you post either verdict. Defines the human…

Conduct an lfx-v2-newsletter-service pull request to a clean state: reconcile the AI reviewers' threads against the latest commits and developer replies, work with the engineer on findings that go against the architecture, and report whether the change is…

Write API end-to-end tests. Use when adding or changing API endpoints, or when the user asks for API e2e, smoke, or contract tests.

Write focused Vitest unit tests. Use when adding or improving unit tests for business logic, data access, common services, or other server modules.

Scaffold a new sub-worker inside packages_worker (npm, deps.dev, osv, scorecard, etc.) following the single-service multi-entry-point structure. Use when: "add a new packages worker", "scaffold a sub-worker in packages_worker", "new worker for packages-db",…

Get packages_worker running locally — first time or resuming after a break. Spins up packages-db if not running, applies any pending migrations, and starts the worker. All steps are safe to re-run. Use when: "set up packages worker", "start packages worker",…

Record an architecture decision as an ADR in docs/adr/. Use when choosing between frameworks, libraries, databases, or architectural patterns; stating a decision with reasoning ("we decided X instead of Y because..."); or querying past decisions ("why did we…

Generate a commit message and commit staged changes using git commit -s -S.

Recover from missing DCO sign-off on commits. Handles the single-commit amend, older-commit recovery via interactive rebase or cherry-pick, and explains the Probot DCO check that blocks PRs without sign-off. Use when a PR fails the DCO check, when a commit…

Pre-PR validation — working tree status, format, lint, TypeScript check, and protected file check. Workspace-aware: detects which of backend/, frontend/, services/apps/*, services/libs/* were changed and runs only the relevant scripts. Use before submitting…

Use when adding a new HTTP endpoint to the lfx-v2-member-service (b2b_org, b2b_org settings, project membership, key contacts, admin actions, or related membership resources). Covers the Goa design update, regeneration, handler implementation, test…

Path-scoped Go and Goa conventions for the lfx-v2-member-service repo. Auto-attaches when editing Go implementation, Goa design files, NATS KV cache code or request/reply handlers, logging, pagination, errors, request context, generated-code boundaries,…

The exact format for the two verdict comments the agentic review posts on a lfx-v2-member-service pull request: the needs-human verdict (escalation) and the agentic-check verdict (conductor). Use whenever you post either verdict. Defines the human…

Senior code-review method for lfx-v2-member-service pull requests: reviewer scope and knowledge sources, how to place a change in this Salesforce-backed Go service and in the LFX V2 platform around it, and the signal discipline that keeps review quiet unless…

Detailed boundaries behind the needs-human decision for lfx-v2-member-service: authentication and the Heimdall RuleSet, the access grants this service emits, writes to production Salesforce data and the shared API budget, authoritative no-TTL state,…

Decide whether an lfx-v2-member-service pull request needs a human's sign-off before it can merge (the needs-human gate), regardless of code quality. Use when the task is the needs-human escalation on a PR. Posts a single machine-readable needs-human verdict…

Conduct an lfx-v2-member-service pull request to a clean state: reconcile the AI reviewers' threads against the latest commits and developer replies, work with the engineer on findings that go against the architecture, and report whether the change is clean.…

How to judge the implementation of an lfx-v2-member-service pull request: the grounding technique for reading a hunk in its real context, the general quality dimensions (correctness, error handling, logging, tests, concurrency, readability, code…

Repo-local development conventions for the lfx-v2-committee-service. Auto-attaches on Go implementation paths (cmd/, internal/, pkg/, gen/), Goa design files under cmd/committee-api/design/, repo docs, the service-local Helm chart, Makefile, go.mod, and…

Repo-owned `repo_learnings` review brain for lfx-v2-committee-service, loaded by the `lfx-local-review` host through the `local-learnings-review` discovery alias. Matches one pinned commit range — normally a commit against its first parent — against the…

Repo-owned `repo_code` review brain for lfx-v2-committee-service, loaded by the `lfx-local-review` host through the `local-code-review` discovery alias. Audits one pinned commit range — normally a commit against its first parent — against this repo's written…

Launch the three local reviewers as Claude subagents when lfx-local-review selects the Claude fallback.

How to judge the implementation of an lfx-v2-committee-service pull request: the general quality dimensions (correctness, error handling, tests, concurrency, readability, code truthfulness), how to hold the diff to the repo's documented standards for this Goa…

Senior code-review method for lfx-v2-committee-service pull requests. Use when the task is to review a PR for correctness, design, and security on this repo.

Pre-PR shape check for local lfx-v2-committee-service work. Audits branch name, JIRA reference, conventional commits, rebase status, DCO and GPG signing, total diff size, and repo-specific protected files against the target base branch. Does not audit Go…

Mechanical pre-PR validation for lfx-v2-committee-service. Checks working tree state, license headers, Go formatting, golangci-lint, API and CLI build, Go tests, repo-specific protected files, commit verification, and PR change summary. Run after…

Automated triage and fixing of Dependabot security vulnerabilities (IN-1189). Starts by asking which scope to tackle (critical, high, medium/low, or specific advisories) with checkboxes. Fetches open alerts, dedupes them, classifies each by origin (submodule…

Record an architecture decision as an ADR in docs/adr/. Use when choosing between frameworks, libraries, databases, or architectural patterns; stating a decision with reasoning ("we decided X instead of Y because..."); or querying past decisions ("why did we…

Generate a commit message and commit staged changes using git commit -s -S.

Pre-PR validation — license headers, format, lint, TypeScript check, build, and protected file check. Use before submitting any PR, to check if code is ready, validate changes, or verify a branch before review.

Review a pull request against Insights architecture standards — fetches PR diff, verifies previous comments are addressed, validates PR metadata (title, branch, JIRA, size), runs a code-standards check against every file in `.claude/rules/` and…

Run the docs site, blog, or Storybook locally. Use when contributing to documentation, previewing blog posts, or developing UI components in isolation. Not needed for regular frontend development.

Full development environment setup from scratch — prerequisites, dependencies, .env file, optional local PostgreSQL database (for auth/collections/chat work), and dev server. Use for first-time setup, broken environments, missing env vars, or when the app…

Repo-owned code-review brain for lfx-v2-campaign-service, the code role of the local pre-PR reviewer trio. Audits the host-pinned commit range against this repository's written rule surface — CLAUDE.md, README, Makefile, docs/, the OKF knowledge bundle, the…

Launch the three local reviewers as Claude subagents when lfx-local-review selects the Claude fallback.

Repo-owned empirical review brain for lfx-v2-campaign-service, the learnings role of the local pre-PR reviewer trio. Matches the host-pinned commit range against the repo-owned knowledge base at docs/reviews/knowledge-base/ — patterns extracted from verified…

How to judge the implementation of an lfx-v2-campaign-service pull request: the Go quality dimensions (correctness, concurrency, error handling, tests, performance, readability, code truthfulness), how to hold the diff to the repo's documented standards, and…

Senior code-review method for lfx-v2-campaign-service pull requests. Use when the task is to review a PR for correctness, design, and security on this repo.

Repo-owned code-review brain for lfx-v2-meeting-service, the repo-code role of this repo's local pre-PR review. Audits one commit or range against this repo's written rule surface — CLAUDE.md, the FGA/indexer/event-processing/ITX contract docs, the Goa design…

Repo-owned empirical-review brain for lfx-v2-meeting-service, the repo-learnings role of this repo's local pre-PR review. Matches one commit or range against this repo's knowledge base of patterns extracted from real past PR review comments, applies the…

Launch the three local reviewers as Claude subagents when lfx-local-review selects the Claude fallback.

Senior code-review method for lfx-v2-meeting-service pull requests. Use when the task is to review a PR for correctness, design, and security on this repo.

How to judge the implementation of an lfx-v2-meeting-service pull request: the line-level grounding method, the quality dimensions, the traps specific to this Goa service's two surfaces (the ITX proxy and the v1 KV event pipeline), and the security anchors…

Post-commit code-convention audit for lfx-self-serve. Audits the latest commit in the lfx-self-serve repo against the repo documented rule surface: `.claude/rules/`, the four `docs/reviews/` checklists, architecture docs, and upstream API contracts. May be…

Post-commit empirical-pattern review for lfx-self-serve. Audits the latest commit in the lfx-self-serve repo against `docs/reviews/knowledge-base/` — patterns extracted from past PR review comments on this repo. May be launched from the LFX workspace root,…

Pre-PR shape check on local lfx-self-serve work. Audits PR-shape sanity (branch name, ticket reference — JIRA or GitHub Issue —, conventional-commit format, rebase status, DCO + GPG signing per commit, total diff size, and protected files touched) against the…

Mechanical pre-PR pipeline, license headers, format, lint, build, protected file check, commit verification, and PR change summary. Run as the final deterministic check inside Mode 2 of `CLAUDE.md`'s **Pre-PR review** section, after the preceding review, fix,…

Use when building any UI element in the crowdfunding frontend — covers when to use existing uikit components, how to extend them, and when to ask before creating new ones

Use when working on Nuxt 4+ projects - provides server routes, file-based routing, middleware patterns, Nuxt-specific composables, and configuration with latest docs. Covers h3 v1 helpers (validation, WebSocket, SSE) and nitropack v2 patterns. Updated for…

Use when editing .vue files, creating Vue 3 components, writing composables, or testing Vue code - provides Composition API patterns, props/emits best practices, VueUse integration, and reactive destructuring guidance

Render PERMISSIONS.md from @fgadoc annotations in the OpenFGA model. Use after any change to model.fga to keep the human-readable permissions reference in sync.

Populate @fgadoc:jtbd annotations in the OpenFGA model by scraping live API authorization rules from the dev Kubernetes cluster and synthesizing JTBD statements. Use when the model has new types or relations that need JTBD annotations refreshed.

Use when the user wants to bring up the local LFX platform stack, edit the OpenFGA authorization model and re-render permissions docs, update platform chart dependencies, or debug local stack install/sync issues. Fires on "bring up local LFX platform", "edit…