verify
Confirm a story is actually done. Walk acceptance criteria against the implementation, check test coverage at the right layer, identify edge cases the tests miss. Adversarial about "done" — does not take coverage claims on trust.
60
72%
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 ./deliver/skills/verify/SKILL.mdQuality
Discovery
67%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 strong in specificity and distinctiveness, clearly articulating a unique skill around verifying story completion with concrete actions like walking acceptance criteria and identifying missed edge cases. Its main weaknesses are the lack of an explicit 'Use when...' clause and missing some natural trigger terms users might employ when requesting this type of review.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to verify a story is done, review acceptance criteria, check definition of done, or validate story completion.'
Include additional natural trigger terms like 'definition of done', 'DoD', 'verify completion', 'story sign-off', 'QA review', or 'ready for release'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: walking acceptance criteria against implementation, checking test coverage at the right layer, identifying edge cases tests miss, and being adversarial about 'done' claims. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific actions, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the actions described. | 2 / 3 |
Trigger Term Quality | Contains relevant terms like 'story', 'acceptance criteria', 'test coverage', 'edge cases', and 'done', but misses common user variations like 'definition of done', 'DoD', 'story review', 'QA check', 'verify completion', or 'sprint review'. | 2 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around story completion verification and acceptance criteria validation. The combination of acceptance criteria checking, test coverage analysis, and adversarial 'done' verification is distinctive and unlikely to conflict with general code review or testing skills. | 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 well-crafted verification skill with excellent actionability and workflow clarity. The three-move framework is concrete and the failure modes section shows sophisticated understanding of common verification pitfalls. The main weaknesses are moderate verbosity (the stance section and some failure mode descriptions could be tighter) and inline content that might benefit from being split into reference files for better progressive disclosure.
Suggestions
Trim the 'Your Stance' section — the adversarial posture is already conveyed by the three moves and failure modes; the philosophical framing adds tokens without new information.
Consider moving 'Failure Modes' and 'Cross-plugin context' to separate reference files to keep the main skill leaner and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and well-structured, but includes some sections that could be tightened — the 'Your Stance' section restates concepts already implied by the skill's purpose, and the 'What Verify Does NOT Do' section, while useful for boundary-setting, is somewhat verbose. The failure modes section adds value but could be more compact. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: the three-move framework gives specific steps (walk each AC individually, name the test by file and name, mentally mutate the implementation), the structured report format is clearly defined with exact categories, and the transitions section gives precise handoff triggers with example phrasing. | 3 / 3 |
Workflow Clarity | The three-move workflow is clearly sequenced (walk ACs → check test layer → identify gaps), includes explicit validation checkpoints (mental mutation testing, layer-appropriateness checks), and has a clear verdict framework with specific criteria for done/almost done/not done. The transitions section provides clear feedback loops for each type of gap discovered. | 3 / 3 |
Progressive Disclosure | The skill references several external files (foundation/SKILL.md, foundation/model.md, foundation/guidelines.md, quality-engineer agent) which is good for navigation, but no bundle files are provided to verify these exist. The content itself is somewhat long and could benefit from splitting the failure modes or cross-plugin context into separate reference files rather than inlining everything. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- audenaert/etak
- Commit
632c389
- 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.