菜单
Drafts a concise Jira description for an FXA task. Gathers context via targeted interview, researches relevant patterns in the repo, outputs a clean description, and optionally files the ticket via the Atlassian MCP. Returns the new FXA-N key when filed.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
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.
| name | fxa-jira-feature-description |
| description | Drafts a concise Jira description for an FXA task. Gathers context via targeted interview, researches relevant patterns in the repo, outputs a clean description, and optionally files the ticket via the Atlassian MCP. Returns the new FXA-N key when filed. |
| user-invocable | true |
Draft a Jira description for an FXA task, and optionally file the ticket via the Atlassian MCP. Do not create, edit, or suggest changes to any source files.
If a planning doc, epic description, or tech spec was provided, read it first and infer what, why, packages, and constraints before asking anything.
Required information:
fxa-auth-server, libs/accounts/passkey)If all four are clear from provided context, proceed directly to Step 2. Otherwise ask for only what is missing in a single message. Also invite related PRs, tickets, existing approach notes, design mockups, or flow diagrams that would add useful context.
Search only the packages identified in Step 1. Find the most relevant existing patterns: similar feature, nearby route, equivalent component. Expand to the broader repo only if nothing relevant is found there.
Identify:
Incorporate findings directly into the draft — do not list them separately or ask for confirmation. Surface genuine blockers as Open Questions.
Design: (Figma link if applicable. Note that all copy, strings, and visual specs should be taken from the latest Figma file — do not reproduce design details here as they may change before implementation. Omit if no design involved.)
Background: Why this is needed and what it enables. 2–4 sentences.
Acceptance Criteria: Observable, testable outcomes. Each item verifiable without reading the code. Include criteria for tests, metrics emission, and security events where applicable to this task.
Implementation Steps: Numbered steps with file paths, method names, and structural guidance. Reference the nearest existing pattern for each step. No code snippets — file locations, types, and patterns only.
Tests: What needs to be tested. Unit, integration, and snapshot coverage expectations. Reference the nearest existing test file as a pattern. Omit if covered inline above.
Metrics & Security Events: (omit if not applicable)
Any StatsD metrics or security events (log.info, request.emitMetricsEvent, customs checks) that should be emitted. Reference the nearest equivalent for naming conventions.
Key Reference Files: Specific files the implementer should read before starting. One line each.
Out of Scope: (omit if not needed)
Open Questions: (omit if none)
After producing the draft (Step 3), check whether the Atlassian MCP is available in the current session (look for mcp__atlassian__createJiraIssue in the available tools). If not available, stop — the user files the ticket manually using the drafted description.
If available, ask the user via AskUserQuestion whether to file now:
If the user picks "Skip", stop and output the draft. If "File now", call mcp__atlassian__createJiraIssue with:
cloudId: mozilla-hub.atlassian.net (the Atlassian MCP accepts the site hostname directly; fall back to getAccessibleAtlassianResources if the call ever rejects this form).projectKey: FXAissueTypeName: Tasksummary: the one-line "what" sentence from Step 1 / the leading description sentencedescription: the full drafted body from Step 3 (Background, AC, Implementation Steps, etc.)contentFormat: markdownSurface the returned FXA-N key and the issue URL. That key is this skill's return value when invoked inline by another skill (e.g. /fxa-pr-open uses it to populate the Closes: line).