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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-dogfood/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a well-structured, highly actionable orchestration workflow with clear phased sequencing, validation checkpoints, feedback loops, and properly externalized reference files. Its only notable gap is conciseness, where repeated emphasis and verbose explanatory comments could be trimmed.

Suggestions

Consolidate the repeated 'never touch the trunk' guidance into a single Phase 0 statement and reference it rather than restating across phases.

Tighten the long inline comment block in the trunk-resolution bash to the essential qualification rule, trimming explanatory prose Claude can infer.

Dimension	Reasoning	Score
Conciseness	Largely efficient for a complex orchestrator — concrete commands and earned edge-case detail — but repeated emphasis (e.g. 'never touch the trunk' restated across phases) and long explanatory comments in the trunk-resolution block could be tightened, so it lands at 'mostly efficient but includes some unnecessary explanation' rather than level-3 leanness.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance — the agent-browser command sequence (open/snapshot/click/fill/errors), the trunk-resolution bash, and a concrete Mermaid flowchart — matching the 'fully executable code/commands; specific examples; copy-paste ready' anchor and clearly above the pseudocode level 2.	3 / 3
Workflow Clarity	Seven numbered phases (0-6) are clearly sequenced with explicit validation checkpoints (verify trunk ref exists, re-run failing scenarios, run the full automated suite before declaring ready) and a fix->regression-test->commit->re-run feedback loop, satisfying the 'clear sequence with explicit validation steps; feedback loops' anchor.	3 / 3
Progressive Disclosure	SKILL.md is an overview that signals one-level-deep references to real bundle files — 'instantiate references/dogfood-report-template.md' and 'Read references/test-matrix-taxonomy.md', both present in ./references/ — with detail appropriately split out and easy navigation, matching the 'clear overview with well-signaled one-level-deep references' anchor.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 and distinctive, clearly conveying a well-scoped QA orchestration niche with concrete actions. Its weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness and leaves trigger guidance implicit.

Suggestions

Append an explicit trigger clause, e.g. 'Use when you want to dogfood/QA a feature branch in a real browser before merging' to satisfy the 'when' half of completeness.

Soften jargon like 'diff-scoped' and 'active branch' with natural user phrasings (e.g. 'test my branch', 'QA this PR in the browser') to broaden trigger-term coverage.

Move 'Manual invocation only' from a trigger substitute into its own intent so the 'when' slot carries genuine activation language rather than a constraint.

Dimension	Reasoning	Score
Specificity	Lists multiple 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" — matching the 'lists multiple specific concrete actions' anchor rather than the single-domain level 2.	3 / 3
Completeness	Thoroughly answers 'what' but the only 'when' guidance is "Manual invocation only", a constraint rather than an explicit trigger; per the judging guideline, a missing 'Use when...' clause caps completeness at 2, and it is not level 3 because no explicit trigger guidance is present.	2 / 3
Trigger Term Quality	Contains relevant natural terms ("browser QA", "dogfood", "regression tests") but leans on orchestration jargon ("diff-scoped", "active branch") and lacks common trigger phrasings a user would actually say, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — diff-scoped browser QA of a specific branch producing a dogfood report — with distinct triggers unlikely to collide with other skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 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: a9f6d53

Reviewed: 7 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.