mozilla

Generates a daily FxA triage summary. Queries Jira, GitHub, Bugzilla, and optionally Sentry, then outputs a Slack-ready update with detailed analysis. Use when starting triage duties or preparing the daily triage post.

Generates a two-audience changelog from merged PRs in the FxA monorepo: a plain-language product summary and an engineer handoff with operational notes. Name a train (e.g. "341") or pass any git range; with no argument it defaults to the in-development train on main (the latest release tag up to HEAD — not a deployed stage/prod train), framed as the range the train owner is accountable for. Use for train-owner handoffs, train summaries, or "what shipped" questions.

Simplifies and refines code in the FXA monorepo using project-specific conventions. Use when asked to simplify, clean up, or refine recently written code. Focuses on recently modified code unless instructed otherwise.

Reviews changed React/TSX code for component design, hooks misuse, performance, accessibility, and state management issues. Reports findings with severity and concrete fix recommendations. Operates on files changed vs main.

Fast single-pass FXA-specific commit review covering security, conventions, logic/bugs, tests, and migrations. No subagents — runs directly in the main context.

Thorough FXA-specific commit review using parallel specialist agents. Covers security, TypeScript, logic/bugs, test quality, and architecture. Agents explore call sites, git history, and monorepo conventions.

Drafts Jest tests for changed code. Defaults to staged/unstaged changes or the most recent commit. Output is a starting point for review, not final.

Reviews a test file for violations of FXA testing guidelines, then suggests concrete repairs. Does not auto-apply changes — output is a repair plan for engineer review.

Use this skill to audit tables for missing column descriptions and classify each missing column into the correct base schema promotion target (global.yaml, app_<product>.yaml, or <dataset_name>.yaml). Accepts a dataset name and an optional table filter — omit the filter to audit all tables in the dataset. Outputs a per-column recommended_target report for use in _missing_metadata.yaml. Composable with schema-enricher (Step 6).

Use this skill when looking up, auditing, or managing column descriptions from global, application-specific, and dataset-specific column definition YAML files (bigquery_etl/schema/global.yaml, bigquery_etl/schema/app_<name>.yaml, and bigquery_etl/schema/<dataset>.yaml). Use it to find a description for a specific column, list all columns in a base schema, audit which columns in a table's schema.yaml are covered by base schemas, or identify columns missing descriptions. Works with schema-enricher skill.

Use this skill when the prompt asks to create, open, or submit a pull request in the bigquery-etl repository. Handles branch creation, staging, committing, pushing, and opening a draft PR with a structured description. Triggered by phrases like "create a PR", "open a PR", "submit a PR", "push and open a PR".

Use this skill when looking up field descriptions for Mozilla Glean telemetry tables (tables ending in _live or _stable, e.g. <app>_stable.<ping>_v1). Fetches descriptions from the Glean Dictionary (dictionary.telemetry.mozilla.org) using WebFetch with targeted field extraction — only the fields referenced in query.sql, never the full table schema.

Use this skill when creating or updating DAG configurations (dags.yaml), schema.yaml, and metadata.yaml files for BigQuery tables. Handles creating new DAGs when needed and coordinates test updates when queries are modified (invokes sql-test-generator as needed). Works with bigquery-etl-core, query-writer, and sql-test-generator skills.

Use this skill to enrich schema.yaml files for BigQuery tables in the bigquery-etl repository. Handles creating schema.yaml when it doesn't exist, finding and filling missing column descriptions (from base schemas, upstream source schema, query context, or application context), validating columns against the query, and generating a summary with recommendations for where to add new descriptions (global.yaml, <dataset_name>.yaml, or app_<name>.yaml). Works with column-description-finder skill.

Use this skill to create or update README.md files for BigQuery ETL tables in the mozilla bigquery-etl repository. Follows layout conventions derived from comparing README files across the repo — rich style with emoji headings, Mermaid data flow diagram, graduated example queries, and concise metadata overview table. Requires schema.yaml with complete descriptions (run schema-enricher first if needed) and a complete metadata.yaml.

ALWAYS use this skill when users ask to "create a skill", "make a skill for...", "add a new skill", or similar requests. This skill guides the creation of effective skills in the bigquery-etl repository that extend Claude's capabilities with specialized knowledge for BigQuery ETL workflows, Mozilla data platform conventions, or telemetry analysis. CRITICAL - First checks for conflicts with existing skills and recommends using/updating existing skills when appropriate. Do NOT attempt to create skills without invoking this skill first.

File a Bugzilla bug directly via the BMO REST API with full power the prefilled enter_bug.cgi form can't do — create the bug AND upload one or more attachments (logs, patches, testcases, screenshots) AND set bug-/attachment-level flags (needinfo?, review?, sec-approval?, approval-mozilla-*?, tracking flags) in one confirmed operation. Also attaches files to, and sets flags on, existing bugs. Use when the user wants to actually submit a bug (not just open a draft form), attach files while filing, or set flags. For a simple file-it-myself-in-the-browser draft with no attachments, prefer the form-based `bug-filing` skill instead. Requires a Bugzilla API key.

Help prepare a Firefox security approval request by analyzing local commits/changes and drafting answers to the sec-approval questionnaire. Use when setting sec-approval? on a Bugzilla bug.

Help prepare a Firefox uplift approval request (Beta, Release, and/or ESR) by checking whether patches are already on the bug, auditing sanitization once for sec-* bugs, and drafting the approval comment per https://wiki.mozilla.org/Release_Management/Uplift_rules. Use after a fix is ready and needs to ride into a stabilization branch. May or may not follow sec-approval (sec-moderate typically skips sec-approval but may still need uplift).

Reference for constructing revision-pinned source, spec, and bug permalinks (Searchfox, GitHub, GitLab, googlesource, Codeberg, Chromium, FFmpeg, Bugzilla, specs). Use when citing code, specs, or bugs in analysis or reports and you need stable, revision-pinned URLs instead of trunk/HEAD links.

Firefox bug triage assistant for media, web conferencing, and graphics related issues.

Generate technical documentation for a specified technology domain with optional customization.

Generate or modify Firefox mozconfig build configuration files. Use when the user asks to create a mozconfig, configure a build, set up ASan/TSan/debug builds, or match try server configurations.

Firefox bug triage assistant for determining if a bug severity rating of S1 or S2 is warranted, and to gather information for triaging and prioritization.

Run the end-to-end loop for landing a legacy Fenix UI test converted onto the ui/efficiency framework: convert → file a Bugzilla bug → commit with the real bug number → track in Jira (conversion vs. enablement) → open a moz-phab review. Use this when a conversion is written and needs to become a filed bug, a properly-numbered commit, Jira tracking, and a submitted revision — i.e. the "paperwork + submit" workflow around a ui/efficiency conversion, not the test authoring itself (that's the efficiency-test-authoring skill). Also covers keeping the tracker/dashboards in sync after landing.

Author or convert Fenix Android UI tests onto the ui/efficiency framework. Use this whenever the task involves writing a new efficiency UI test, converting/porting a legacy ui/ (robot-based) test onto the efficiency framework, or building what a test needs — page objects, selectors, navigation-graph nodes/edges, or BasePage primitives. Trigger even when the user doesn't name the framework: "convert this smoke test", "add a page object for the bookmarks screen", "wire up navigation to Settings", "write an efficiency test for X" all qualify. Do NOT use for edits to legacy robot-based tests that are staying on the old framework, or for non-Android test work.

Review and authoring guidance for new/changed tests in the Fenix TAE efficiency framework (mobile/android/fenix/app/src/androidTest/java/org/mozilla/fenix/ui/efficiency). Use when reviewing a diff, PR, or Phabricator revision that adds or modifies files under that path — page objects, selectors, navigation edges, or test files. Also use when authoring a new test and self-checking before submission, when asked to check a test against TAE conventions, classify a test (presence/interaction/behavior), or judge whether a helper belongs in a page object vs. BasePage. Also use when auditing a converted test for assertion parity against the legacy test it replaces. Applies the framework's principles and anti-patterns as a review rubric with severity tiers.

End-to-end New Tab train-hop targeting for the Experimenter repo. From a single trainhop version string, files the GitHub targeting issue, branches, adds the NimbusTargetingConfig entry, lints, and stages a drafted commit. Use for "newtab trainhop targeting" requests.

Durable review guidance for Firefox's built-in IP Protection (VPN) module, covering panel UI, proxy/channel filtering, authentication, telemetry, and localization.

Use after tests pass on a Nova feature — before linting or formatting — to annotate changed files with @nova-cleanup instructions for post-launch automated cleanup.

This skill should be used when the user asks about browser automation, testing web pages, extracting content, filling forms, taking screenshots, or monitoring console/network activity. Activates for E2E testing, form automation, browsing tasks, or debugging web applications.

Navigate Firefox to a URL and take a DOM snapshot for interaction

Take a screenshot of a URL or the current page. Use when the user asks to capture, screenshot, or photograph a web page or URL.

Diagnose Firefox DevTools MCP setup issues. Activate when the firefox-devtools-mcp plugin fails to connect, its tools are not available, or the user reports Firefox DevTools not working in Cowork.

Scan everything that landed on mozilla-central (the Nightly train) in a recent window and propose release-note candidates — with bug number, whether the change is gated (and how), and a draft one-liner in the Release Management style. Use when the user wants to find release notes for recent landings, work the daily "what landed overnight" pass, or asks things like "what should we note from the last day", "find release-note candidates", "anything user-facing land this week". Complements review-release-notes (which critiques an existing draft); this one produces the candidate list from scratch.

Triage the recent community-filed Firefox bug queue and recent regressionwindow-wanted bugs. Pulls both lists, classifies each bug (duplicate, needs-info, regression, feature request, invalid, valid-new), attempts to find regressors where findable, and escalates shipped-channel functional regressions (chemspill-class). Use when the user wants to triage incoming user bugs, work the daily community bug queue, find regressors for recent regressions, or asks things like "triage the user bugs from the last day", "what came in overnight", "find the regressor for these", "anything chemspill-worthy in the queue".

Review draft Firefox release notes for style, tone, scoping, and audience-fit against the Mozilla Release Management Release Notes Style Guide. Use when the user wants release notes checked/edited before publishing — they may paste the notes, point to an exported file, or give a published-to-web Google Doc URL. Triggers on requests like "review these release notes", "check my relnotes draft", "do these notes follow the style guide".

Runs a read-only SQL query against the Customer Experience tables (moz-fx-data-shared-prod.customer_experience_derived) and returns results as a formatted table. Use when the question requires counts, aggregations, rankings, or distributions — not when it requires reading document text.

Runs VECTOR_SEARCH against the Customer Experience retrieval indexes (moz-fx-data-shared-prod.customer_experience_derived) and returns the top-K most semantically similar documents. Use after the embed skill has produced an embedding file.

Receives a text question and returns its embedding vector using gemini-embedding-001 via Vertex AI. Use this when you need a semantic embedding for a question — for downstream vector search, similarity comparison, or passing to another tool.

Run Base Load Engineer checks for the current day and produce a prioritized action list

Run pre-commit checks, review PR checklist, and draft a commit message for Relay changes

Cut a new stmo-cli release: curate the changelog, bump the version, open the release PR, tag it, let CI publish the GitHub Release with binaries, then publish to crates.io by hand. Use when the user asks to release, cut a release, ship a new version, or publish stmo-cli.

Sync the vendored stmo Claude skill (.claude/skills/stmo/SKILL.md) with a stmo-cli change and prepare delivery to the mozilla-firefox/firefox repo via moz-phab. Use after a stmo-cli change (new command, flag, or workflow behavior) that the firefox-facing skill should reflect, or as part of preparing a stmo-cli release.

Audit and update dependencies across Python, npm, and pre-commit ecosystems

Use this skill when working with Firefox documentation, including building documentation with `./mach doc`, fixing Sphinx build errors or warnings, modifying existing documentation, or adding new docs.

Invoke this skill whenever the user is contributing to the mozcloud Helm chart or its library charts — whether asking how to do something OR actually doing it. This includes: generating a new Helm template or helper file, modifying an existing template or helper, adding a new Kubernetes resource type to the chart, deciding where a file should live and what prefix to use, figuring out which file type to use (_helpers.tpl vs _*.yaml), handling version bumps after library chart changes, or understanding what must be done before a PR is ready. Always trigger when the user asks to create, write, add, modify, or refactor anything in the mozcloud chart — don't wait for them to ask about conventions explicitly.