spec-dogfood
对活动分支或 PR 做 diff 范围内的自主浏览器 QA：映射受影响用户流、驱动 agent-browser、修复小故障并补回归测试、记录需人工决策的阻塞，并写出可留存报告。
ASCII 链路图
Codebase -> Spec -> Plan -> Tasks -> Code -> Review -> Knowledge
|
v
spec-dogfood
entry: spec-dogfood
type: workflow command基本信息
| 字段 | 内容 |
|---|---|
| Skill | spec-dogfood |
| 类型 | workflow command |
| 研发链路位置 | Review |
| 当前入口 | spec-dogfood |
| 兼容别名 | /spec:dogfood、$spec-dogfood |
| Source | skills/spec-dogfood/SKILL.md |
| Governance | src/cli/contracts/dual-host-governance/skills-governance.json（supported-host skills governance） |
描述
Hands-off, diff-scoped browser QA of the active branch or PR. Use when a branch needs autonomous user-flow dogfooding before review or shipping: map changed flows, drive agent-browser, fix small breakages with regression tests, record human-decision blockers, and write a durable report. Do not use for collaborative UI polish, ordinary browser smoke tests, code review, implementation planning, or broad whole-app exploration.
Source 契约摘要
When To Use
Use when a PR, branch, or current non-trunk branch needs autonomous browser dogfooding before review or shipping: changed-flow mapping, persona-aware journey testing, small fixes, regression tests, and a durable report.
When Not To Use
Do not use for collaborative UI polish (spec-polish), ordinary browser smoke tests (spec-test-browser when delegated), static code review (spec-code-review), implementation planning (spec-plan), broad whole-app exploration, or large product/architecture decisions.
Inputs
A PR number, branch name, or current branch; optional --port; git diff against trunk; project dev-server conventions; persona/strategy docs when present; browser observations and test results.
Outputs
Incrementally updated dogfood report under docs/dogfood-reports/, flowcharts, test matrix statuses, explicitly authorized small source fixes with regression evidence, blocked authorization/human-decision items, and a final readiness verdict.
Artifacts
docs/dogfood-reports/<YYYY-MM-DD>-<branch-slug>-dogfood.md, authorized source/test changes, commits only when separately requested, transient screenshots in OS temp, and optional reusable learnings handed to spec-compound.
Failure Modes
Trunk target with no diff, unsafe checkout or dirty working tree, missing agent-browser, missing or failing dev server, external-interaction flows needing human verification, ambiguous fixes requiring human product/architecture decisions, or failing automated suite after browser matrix completion.
Workflow
Resolve the target branch/PR, optionally isolate with spec-worktree, analyze the diff, map changed user flows, build a matrix, start the app, execute each scenario with agent-browser, fix only small unambiguous issues, update the report throughout, then run the automated suite and finalize the verdict.
Downstream Consumers
Human reviewers, spec-code-review, spec-work for larger follow-up fixes, spec-compound for reusable learnings, and PR/commit workflows that consume the readiness evidence.
何时使用
- 分支在 review 或 shipping 前需要自主 user-flow dogfooding。
- 需要按 diff 映射受影响流程并在浏览器中验证。
- 需要记录小故障修复与人工决策阻塞。
工作步骤
- 读取 diff、PR、文档、计划、task pack 或专项审查输入。
- 按风险域选择 always-on 与 conditional reviewer personas。
- 合并、去重和校准 findings，区分 safe_auto、gated_auto、manual 和 advisory。
- 输出修复、残留风险或下一步处理建议。
输出
- review findings、safe_auto fixes、residual risks、audit report 或 release checklist。
- 当 reviewer dispatch 不可用时，输出明确的 report-only fallback 覆盖说明。
Agent 调度
- 这是 persona agents 的主要使用层：correctness、testing、security、performance、scope、design 等按证据触发。
- review workflow 自身负责任务边界、合成和最终判断。
本 skill 当前没有 skill-local references/agents 或 references/personas 文件；默认由 orchestrator 直接完成，或按阶段需要临时调用其他 skill 的专家。
边界
- 不用于协作式 UI polish、普通浏览器 smoke test、代码 review 或实现规划。
- 不做无边界的全 App 探索。
源码校准
- 本页由
website/scripts/generate-skill-detail-pages.js从上游 source skill 生成。 - 当前入口、兼容别名与宿主投递 metadata 来自
src/cli/contracts/dual-host-governance/skills-governance.json。 - 当 source skill 或 governance contract 变化后，应重新运行
npm run reference:pages并执行npm run content:audit。