linuxfoundation

Everything Intercom for LFX — Angular app integration (code) and Fin AI optimization (support/CX). Use this skill for: adding or fixing Intercom in an LFX Angular app, auditing integrations against the LFX canonical pattern, correcting missing JWT pre-set, broken shutdown, missing Auth0 claim, wrong app IDs, or absent CSP entries — AND for Fin Guidance writing, Help Center optimization, resolution rate improvement, Fin escalation patterns, Copilot tips, Topics Explorer, Fin Attributes, daily review rituals, and Fin best practices. Routes to the right section based on context. Trigger on: any Intercom question, "Fin tips", "improve Fin", "Fin guidance", "Fin resolution rate", "Help Center optimization", "Copilot tips", "Angular Intercom", "IntercomService", "JWT Intercom", "Fin re-engagement", "Fin handoff", or any Intercom-related support or development question.

Starting point for LFX development. Describe what you want in plain language and this skill routes you to the right workflow.

Create a new ticket in the LFXV2 Jira project (linuxfoundation.atlassian.net). Guides the user through picking an issue type (Bug, Story, Task, Epic), writing a concise summary, and capturing the requirement, feature, or bug context — collecting reproduction steps for bugs. Optionally attaches a parent epic, labels, or priority if the user provides them. Submits the ticket via Atlassian MCP and returns the URL. Use this skill any time someone asks to "create a Jira ticket", "open an LFXV2 ticket", "file a bug", "log a story", "write up a feature request", "draft a ticket", or any variation of submitting work into LFXV2.

Generate compliant backend code for LFX repos — Express.js proxy endpoints (lfx-v2-ui) or Go microservice code (resource services). Encodes the three-file pattern, logging conventions, Goa DSL, NATS messaging, and microservice proxy usage.

Understand LFX system architecture, decide where code should go, trace data flows, and explain design decisions. Works across all LFX repos. Use when asking "where should this go?", "how does X work?", or "should I create a new module?". Read-only — does not generate code.

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 someone wants to address PR feedback, fix review comments, resolve PR threads, or iterate on a pull request after review.

Guided development workflow for building, fixing, updating, or refactoring code across any LFX repo. Researches inline, then delegates code generation to specialized skills. Use whenever someone wants to add a feature, fix a bug, modify existing code, create something new, refactor, or implement any code change.

Use when adding a new snowflake-connector data source to crowd.dev — a new platform or a new source within an existing platform that needs buildSourceQuery, transformer, activity types, migration, and all associated type registrations scaffolded.

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", "add npm worker", "add OSV worker", "add deps.dev worker".

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", "resume packages worker", "get packages-db running", "packages-db stopped", "restart the 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 choose X?").

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 needs a Signed-off-by trailer added retroactively, or when sign-off was forgotten during rebase / cherry-pick / amend.

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 any PR, to check if code is ready, or to validate a branch before review.

Review a pull request against CDP architecture standards — fetches PR diff, verifies previous comments are addressed, validates PR metadata (title, branch, JIRA key, size), runs a code-standards enforcer against every file in `.claude/rules/` and `.claude/hooks/guard-protected-files.sh`, and drafts inline review comments with suggested fixes. NEVER auto-posts comments or submits reviews — always presents a draft in the terminal for user approval before any comment lands on the PR. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check this PR", or "audit code".

Use when adding a new snowflake-connector data source to crowd.dev — a new platform or a new source within an existing platform that needs buildSourceQuery, transformer, activity types, migration, and all associated type registrations scaffolded.

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 choose X?").

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 `.claude/hooks/guard-protected-files.sh`, and drafts inline review comments with suggested fixes. NEVER auto-posts comments or submits reviews — always presents a draft in the terminal for user approval before any comment lands on the PR. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check this PR", or "audit code".

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 won't start.

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 the `lfx-self-serve-code-reviewer` subagent with the canonical full-branch prompt — the subagent audits the PR branch's diff against `origin/main` and renders a markdown review covering general code review, upstream API contracts, and repo conventions (rules, checklists, architecture). This skill body adds what only a post-PR skill can do: verifying prior review comments are addressed, walking the PR-shape checklist (branch/ JIRA/commits/DCO+GPG/rebase/diff-size/protected-files/PR-title/external-refs), applying new-contributor educational tone, presenting a draft for explicit approval, and posting via /review only after user go-ahead. NEVER auto-posts comments or submits reviews. Use when reviewing PRs, checking PR quality, validating code changes, or when the user says "review", "check

Pre-PR shape check on local lfx-self-serve work. Audits PR-shape sanity (branch name, JIRA reference, conventional-commit format, rebase status, DCO + GPG signing per commit, total diff size, and protected files touched) against the target base branch. Does NOT audit code — code audits run post-commit via the `lfx-self-serve-code-reviewer` and `lfx-self-serve-learnings-reviewer` subagents (launched via the Agent tool), drained before this check. Use once before opening a PR, after the post-commit review queue has returned clean.

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 needs a Signed-off-by trailer added retroactively, or when sign-off was forgotten during rebase / cherry-pick / amend.

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, refactor, or implement any code change.

Environment setup from zero — prerequisites, clone, install, env vars via 1Password, and dev server. Use for getting started, first-time setup, broken environments, install failures, or missing env vars.

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

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 Nuxt 4.3+.

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

Upgrade all Go dependencies, fix payload/contract changes introduced by upstream LFX V2 services, and run a query service argument review pass. Use when upgrading dependencies, after upstream service contract changes, or for periodic maintenance of the lfx-mcp codebase.

Validate MCP search tool filter parameters against the live OpenSearch resources index and upstream indexer-contract documentation. Use after any filter bug report or indexer contract change to identify broken, missing, or incorrectly implemented filter parameters.

Render PERMISSIONS.md from @fgadoc annotations in the OpenFGA model. Use after any change to model.yaml 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 this skill when the user asks about "AAIF member onboarding", "new member setup", "membership tier validation", "mailing list provisioning", "compliance screening", "silo health", "onboarding checklist", "D1-D5 deliverables", "member offboarding", "working group enrollment", "election management", "press release drafting", "logo validation", "renewal intelligence", "churn prediction", "engagement scoring", "contact role management", "calendar provisioning", "onboarding call scheduling", or any task related to managing Linux Foundation AAIF member organizations, contacts, and their access across Salesforce, Groups.io, Google Calendar, Discord, GitHub, LFX Platform, and HubSpot systems.