waza-runner

Run evaluations on Agent Skills to measure their effectiveness. USE FOR: "run skill evals", "evaluate my skill", "test skill quality", "check skill triggers", "skill compliance check", "measure skill performance", "run evals on [skill-name]", "grade skill execution". DO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter (use sensei), or general testing unrelated to skills.

Quality

70%

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 ./waza-runner/SKILL.md

Quality

Content

50%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.

A well-organized overview with tables and concrete CLI examples, but it is held back by duplicated trigger text, placeholder/descriptive workflow steps lacking validation checkpoints, and two broken reference links.

Suggestions

Add validation checkpoints to the Workflow (e.g. verify eval.yaml parses and graders run before reporting), since this is a batch execution process.

Create the missing references/WRITING-TASKS.md and references/GRADERS.md, or remove their links from the References section to avoid dead navigation.

Remove the 'When to Use' bullets (or the redundant tagline/intro) since the same triggers already live in the frontmatter description, improving token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (tables and lists instead of prose, no over-explanation of known concepts), but the 'When to Use' bullets duplicate the frontmatter triggers and the intro restates the tagline, so it could be tightened — matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It offers some concrete guidance (real CLI commands like `waza run ./my-skill/eval.yaml -o results.json` and a JSON output sample), but the Workflow steps and Commands use placeholders/descriptive verbs ('Parse task definitions', 'Execute', `<skill-name>`) rather than fully copy-paste-ready instructions, matching the 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The 4-step Workflow has a clear sequence, but it lacks any validation/checkpoint steps for a batch eval-execution process; per the rubric, missing feedback loops in batch operations caps workflow_clarity at 2.	2 / 3
Progressive Disclosure	The References section is well-signaled and one level deep, but only EVAL-SPEC.md actually exists in the bundle — WRITING-TASKS.md and GRADERS.md are referenced yet missing, so navigation is only partially functional.	2 / 3
	Total	8 / 12 Passed

Description

90%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.

A strong description with explicit USE FOR/DO NOT USE FOR trigger guidance and a clear niche. Its only weakness is specificity — the core capability is stated as a single action rather than a list of concrete operations.

Dimension	Reasoning	Score
Specificity	It names the domain and core action ("Run evaluations on Agent Skills to measure their effectiveness") but does not enumerate multiple distinct concrete operations, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It answers both 'what' (run evaluations on skills to measure effectiveness) and 'when' (explicit USE FOR triggers) plus a DO NOT USE FOR boundary, clearly satisfying the 'both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	The USE FOR list supplies many natural phrases a user would actually say ("run skill evals", "evaluate my skill", "test skill quality", "grade skill execution"), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The 'Agent Skills' niche combined with the explicit DO NOT USE FOR routing (skill-authoring, sensei) gives it a clear, distinct niche unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: microsoft/waza
Path: waza-runner/SKILL.md
Commit: f466c4f

Reviewed: 13 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.