dogfood-tui

Structured TUI dogfooding and QA workflow using agent-tty. Use for exploratory testing, bug hunting, release-readiness validation, and UX review of terminal applications.

Quality

85%

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

82%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 tight, highly actionable skill body built around a copy-paste session skeleton and a well-sequenced workflow with prerequisite validation and checklists. The main gap is the absence of an explicit error-recovery feedback loop in the workflow.

Suggestions

Add a short validate→fix→retry loop in the Dogfooding Workflow (e.g., 'If doctor --json fails, resolve the reported renderer/browser gaps before continuing') to push workflow_clarity from 4 to 5.

Tighten the prose in 'Choose the Evidence Instrument' — the snapshot-width caveat could be one sentence instead of a paragraph — to move conciseness toward 5.

Consider extracting the Issue Taxonomy or Report Template into a one-level-deep reference file so progressive_disclosure can reach 5 for a skill of this length.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no basic-concept padding, and the prose is agent-tty-specific guidance Claude would not already know (snapshot width caveat for wide glyphs, when to prefer source reading over a session). A few explanatory sentences could still be tightened, keeping it just below the 5 anchor.	4 / 5
Actionability	Provides a copy-paste-ready bash session skeleton plus concrete subcommands and flags throughout (doctor --json, snapshot --format text --json, wait --screen-stable-ms, record export --format webm --json), covering the common dogfooding cases.	5 / 5
Workflow Clarity	A clearly sequenced 10-step workflow with an explicit prerequisite checkpoint (doctor --json before screenshot/recording work) and supporting checklists (Evidence Checklist, Report Template). It stops short of a 5 because there is no explicit validate→fix→retry feedback loop for error recovery.	4 / 5
Progressive Disclosure	Single ~108-line file organized into seven clearly-headed sections with no deeply nested references. Structure is good and content is appropriately placed; it is not a 5 only because, at this length, a couple of referenceable blocks (Issue Taxonomy, Report Template) could optionally be split out, though single-file is defensible.	4 / 5
	Total	17 / 20 Passed

Description

87%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 well-crafted description that explicitly covers both what the skill does and when to use it, with concrete, natural trigger terms and a distinct niche. Minor specificity upside would come from naming concrete technical operations rather than activity categories.

Dimension	Reasoning	Score
Specificity	Names the domain ('TUI dogfooding and QA workflow using agent-tty') and lists several concrete activities ('exploratory testing, bug hunting, release-readiness validation, ... UX review'). Not a 5 because these are use-case categories rather than concrete technical operations like 'extract text' or 'fill forms'.	4 / 5
Completeness	Clearly states what the skill does and provides an explicit 'Use for ...' trigger clause with concrete phrases, matching the 5 anchor's 'what AND when with concrete trigger phrases' example.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ('exploratory testing', 'bug hunting', 'release-readiness validation', 'UX review', 'terminal applications', 'TUI'). Good coverage but a few natural synonyms ('manual testing', 'regression testing', 'QA') are missing, so it sits below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche as the QA layer over agent-tty with distinct triggers ('dogfooding', 'release-readiness validation', 'UX review of terminal applications'), giving minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: coder/agent-tty
Path: skill-data/dogfood-tui/SKILL.md
Commit: ebff2c2

Reviewed: 4 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.