ce-dogfood

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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a tightly written, well-structured orchestrator skill: lean prose, an explicit invariant phase order with validation checkpoints and feedback loops, and clean one-level-deep references to real bundle files. The only minor gap is that most executable detail lives in references/phases.md rather than inline, which is appropriate for the format but keeps actionability just short of fully copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean throughout, assuming Claude's competence — it never explains what a browser, QA, a persona, or a diff is — and every section (Boundaries, Prerequisites, Artifact Root, Phase order) carries operational load, not padding.	5 / 5
Actionability	Concrete commands and paths are present ("command -v agent-browser", "mktemp -d \"${TMPDIR:-/tmp}/ce-dogfood-XXXXXX\"", "git rev-parse --show-toplevel", the branch-slug rule), but the bulk of executable phase detail is deliberately delegated to references/phases.md, so the body alone is not fully copy-paste-complete.	4 / 5
Workflow Clarity	A clear invariant phase order (Scope -> analyze diff -> map flows -> derive matrix -> serve -> execute -> fix loop -> report) with explicit validation and feedback loops — "A fix is not done until a regression test fails before it and passes after" — plus explicit terminal states and the once-run suite check, which is exactly the checkpoint discipline the rubric rewards for batch/risky work.	5 / 5
Progressive Disclosure	SKILL.md is a focused overview that points one level deep to real, clearly signaled references — references/phases.md and references/dogfood-report-template.md (both verified to exist) — with no nested-reference chains, giving easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, distinctive, and concrete about what the skill does, but it lacks an explicit when-to-use / trigger clause, capping its completeness. Adding a "Use when..." sentence with natural trigger phrases would lift both completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause (e.g. 'Use when you need to dogfood the active branch end-to-end in a real browser, run e2e or smoke checks before merge, or verify user-visible changes feel right to product personas').

Broaden trigger terms to include synonyms users actually say, such as 'end-to-end test', 'e2e', 'smoke test', or 'manual QA pass'.

Consider dropping or relocating the trailing 'Manual invocation only.' since it is an invocation constraint rather than a capability or trigger; it dilutes the capability list.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — "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" — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The "what" is explicit and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance; "Manual invocation only." is a constraint, not a when-to-use trigger, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong natural terms ("browser QA", "dogfood", "user flows", "regression tests") but missing common synonyms a user might say (e.g. "end-to-end test", "smoke test", "e2e"); the closing "Manual invocation only." is a constraint rather than a trigger.	4 / 5
Distinctiveness Conflict Risk	"Hands-off, diff-scoped browser QA of the active branch" plus the distinctive "dogfood" framing carves a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-dogfood/SKILL.md
Commit: 082c83e

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.