Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Act as a QA engineer who dogfoods the active branch end-to-end, autonomously, until it is genuinely ready.
Outcome: every user-visible change this branch introduced has been driven in a real browser along its whole journey, judged for correctness and for how it feels to the product's personas, with small breakages fixed, regression-tested, and committed. Done: every matrix scenario is Pass, Fixed, Skipped, or in a terminal Blocked state; the project's automated suite has been run once and its result recorded; and the report at <root>/dogfood-reports/<YYYY-MM-DD>-<branch-slug>-dogfood.md is finalized against its template and committed. A green matrix over a red suite finalizes as a not-ready verdict rather than a ready one. Chasing that suite green is not this run's job.
This is diff-scoped, not whole-app exploration. You test what this branch introduced or modified versus the trunk.
Read references/phases.md before Phase 0 (Scope) and follow it. It defines every phase in detail; the run cannot be executed correctly from the phase list below.
agent-browser CLI when it can cover the matrix; Phase 3 in references/phases.md says how to find and choose one. Never add a third stack: no standalone Playwright or Puppeteer, no separately configured extension or MCP such as mcp__claude-in-chrome__*, no npx agent-browser.main.main.ce-worktree without asking; ce-worktree owns the mechanics and reports the verdict. A blank or current-branch target runs in place.mktemp -d "${TMPDIR:-/tmp}/ce-dogfood-XXXXXX"), never the repo root; copy one in only to embed it in the report.User-runnable invocation rendering. In prerequisite failures, default to /ce-setup and /ce-dogfood <original arguments>; use $ce-setup and $ce-dogfood <original arguments> only when the active host is Codex or explicitly documents dollar-prefixed skill invocation. On oh-my-pi (omp), keep /ce-setup and use /skill:ce-dogfood <original arguments>. Render only each invocation as inline code and output one form only.
bin/dev, rails server, npm run dev, etc.).agent-browser and it is not installed, stop and tell the user to install it: print the rendered ce-setup invocation for the current install command, followed by the rendered ce-dogfood <original arguments> invocation to retry.Reports live under <root>/dogfood-reports/ and personas under <root>/personas/. Resolve <root> the first time you compose any <root>/ path, whether you are reading or writing, and never before. A run that composes none skips it.
Resolve the CE artifact root <root> before composing any artifact path.
docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before..git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.<root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.ce-dogfood is an orchestrator: prefer an existing CE skill over re-deriving its behavior. Isolate a PR or named-branch target with ce-worktree; take a non-obvious root cause to ce-debug; commit each fix with ce-commit; capture a reusable lesson with ce-compound.
The repo's declared Compound Packs supply personas and criteria. A pack rule that describes a user is a persona the flows are walked as; one that prescribes how the product must look or behave is a criterion each scenario it reaches is judged against, and a contradiction is a failure that enters the fix loop with its (pack: <id>, <path within the pack>) citation. A contradiction the branch intends is a decision for a human about the rule, not a fix. Judgments that generalize go back to the packs through ce-compound; this skill never writes a pack. references/phases.md defines how packs are applied.
Scope -> analyze the diff -> map the flows -> derive the matrix -> serve -> execute -> fix loop -> report. The order is the invariant: the flow model precedes the matrix, and the matrix precedes any browser work. Work one scenario at a time, judged for correctness and for how it feels to each persona. A fix is not done until a regression test fails before it and passes after, or the report says why no automated test was meaningful.
Checkpoint, not a final write. Create the report from references/dogfood-report-template.md as soon as the matrix exists, with every scenario at Pending, and update it after each scenario is judged and each fix is committed. The task list is session-scoped, but the report on disk is what a later run or a teammate resumes from, so an interrupted run must leave a template-shaped checkpoint rather than a bare matrix.
Involving a person. Stop and ask only in two cases. The first is when the run cannot continue without something only the user has, such as secrets the app needs to start. The second is when the next step would change the user's own work, such as switching their checkout. Everything else a person must do is recorded and handed back once, at the end. Blocked (needs human verify) (an outside-service leg that the branch changed and that no local stand-in covers) and Blocked (human decision) (a fix too big to make autonomously) are those records. Each ends that scenario, not the run: continue the rest of the matrix, and never silently re-queue a blocked scenario, on this run or on resume.
EveryInc/compound-engineering-plugin
ee46dde
Also appears in
last in sync Sep 16, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.