CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-dogfood

Run end-to-end browser-based QA on the current branch — test all changed user flows as real personas, auto-fix what's safe within bounded autonomy, escalate the rest, and emit an auditable report to docs/dogfood-reports/. Use when the user asks to dogfood a branch, run end-to-end QA, or browser-test the changed flows.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-engineered process skill: deterministic phases, explicit validation and feedback loops, bounded autonomy with a trust boundary, and concrete artifacts (state files, report template, exit codes). The main improvements are trimming the duplicated report-format content and moving the persona/template blocks into reference files.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (never explains Playwright, dev servers, or Conventional Commits) and every section carries operational content, but Phase 7's report bullets duplicate the full 'Reporting format' template and '--no-serve' is explained twice — minor over-explanation that could be trimmed, matching the 4 anchor rather than the every-token-earns-its-place 5.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: concrete invocation commands ('/ce-dogfood --resume <run-id>'), exact file paths ('.dogfood-state/<run-id>.json', 'docs/dogfood-reports/<run-id>.md'), a copy-paste-ready persona YAML and report template, explicit exit codes, and a fix loop specified as red-before/green-after regression tests; app-agnostic steps like 'Start the app's dev server' are justified flexibility.

5 / 5

Workflow Clarity

Seven phases are clearly sequenced with explicit validation checkpoints (readiness = 'GET / returns 200', regression test red before/green after, re-test scenario plus adjacent journeys after each fix) and a feedback loop, and the auto-fix batch operation is bounded by an explicit trust boundary and escalation rules — matching the top anchor with error-recovery loops.

5 / 5

Progressive Disclosure

As a single-file skill it is well organized with clearly signaled sections, but the persona YAML and the full report template (~50 lines combined) are inlined and would sit better in reference files, so it matches 'good structure with minor organization gaps' rather than the clear-overview-with-references 5 anchor.

4 / 5

Total

18

/

20

Passed

Description

92%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.

A strong description: concrete, comprehensive, third-person, and with an explicit 'Use when' trigger clause using natural user phrasing. The only gap is a handful of missing trigger synonyms (e.g., 'e2e tests', 'smoke test').

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline ('test all changed user flows as real personas', 'auto-fix what's safe within bounded autonomy', 'escalate the rest', 'emit an auditable report to docs/dogfood-reports/') in third-person voice, matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

It explicitly answers both what (the full QA → bounded auto-fix → escalation → auditable report pipeline) and when ('Use when the user asks to dogfood a branch, run end-to-end QA, or browser-test the changed flows') with concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

'dogfood a branch', 'run end-to-end QA', and 'browser-test the changed flows' are natural phrases users would say, giving good coverage, but common variations like 'e2e tests', 'smoke test', or 'regression test' are missing — so it fits the 4 anchor rather than comprehensive synonym coverage at 5.

4 / 5

Distinctiveness Conflict Risk

The branch-scoped dogfooding niche with an auto-fix/escalation loop and distinct triggers ('dogfood a branch', 'browser-test the changed flows') gives minimal overlap risk with generic test-runner skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agranado2k/ai-report-platform

Path

.agents/skills/ce-dogfood/SKILL.md

Reviewed

Table of Contents

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.