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.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skill-data/dogfood-tui/SKILL.mdQuality
Discovery
75%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 well-structured with clear 'what' and 'when' components and occupies a distinct niche. Its main weaknesses are that the listed activities are somewhat high-level categories rather than concrete actions, and the trigger terms could better cover natural user language variations for terminal testing scenarios.
Suggestions
Add more concrete actions like 'navigate menus, test keyboard shortcuts, validate rendering, capture and report bugs' to increase specificity.
Include more natural user trigger terms such as 'CLI app', 'terminal UI', 'console application', 'manual testing', 'smoke test' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TUI dogfooding/QA) and lists several activities (exploratory testing, bug hunting, release-readiness validation, UX review), but these are category-level descriptions rather than concrete specific actions like 'run test scenarios', 'capture screenshots', or 'file bug reports'. | 2 / 3 |
Completeness | Clearly answers both what ('Structured TUI dogfooding and QA workflow using agent-tty') and when ('Use for exploratory testing, bug hunting, release-readiness validation, and UX review of terminal applications'). The 'Use for' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'dogfooding', 'QA', 'bug hunting', 'exploratory testing', 'terminal applications', and 'TUI', but misses common user variations like 'test my CLI app', 'manual testing', 'smoke test', 'terminal UI', or 'console application'. The term 'agent-tty' is tool-specific jargon users may not naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of TUI/terminal applications, agent-tty tooling, and dogfooding/QA workflow creates a very specific niche that is unlikely to conflict with other skills. The scope is clearly bounded to terminal application quality assurance. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable skill with a clear workflow, executable code examples, and well-defined validation steps. Its main weakness is that it packs a lot of reference material (issue taxonomy, report template, evidence checklist) inline rather than splitting it into supporting files, making it longer than necessary for the primary workflow. The content is domain-specific and genuinely useful, with minimal explanation of things Claude already knows.
Suggestions
Consider extracting the Issue Taxonomy and Report Template sections into separate referenced files (e.g., ISSUE_TAXONOMY.md, REPORT_TEMPLATE.md) to keep the main skill focused on the workflow.
The Evidence Checklist could be condensed into a shorter inline checklist with a reference to a more detailed version if needed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some content that could be tightened—the evidence checklist and issue taxonomy sections are thorough but somewhat verbose. The report template, while useful, adds significant length. However, most content is domain-specific knowledge Claude wouldn't inherently know. | 2 / 3 |
Actionability | The recommended session skeleton provides fully executable, copy-paste-ready bash commands. Each workflow step specifies exact CLI flags (--format text --json, --screen-stable-ms 1000) and distinguishes between run/type/send-keys with clear use cases. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced from environment setup through session destruction, with explicit validation checkpoints (doctor --json before work, wait on observable state instead of blind sleeps, snapshot/screenshot for evidence). The feedback loop of 'repeat for every meaningful scenario' is well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear section headers, but it's a monolithic file with no references to supporting documents. The evidence checklist, issue taxonomy, and report template could reasonably be split into separate reference files, especially since the skill is over 80 lines of substantive content. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- coder/agent-tty
- Commit
a05d4e5
- 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.