check-tests

Run the local test evidence check

Quality

54%

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 ./projects/skill-router/examples/skills/check-tests/SKILL.md

Quality

Content

41%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.

The body is maximally lean but nearly content-free: it supplies two behavioral constraints while omitting every executable detail of the check itself. The skill's failure mode is the opposite of verbosity — it needs concrete commands, the location of the check, and a definition of 'evidence'.

Suggestions

State how to run the check concretely: the command or script to execute (e.g. a path in scripts/ or an exact invocation) rather than an unadorned directive.

Define what counts as 'evidence' and what 'missing' looks like, so the stop condition is actionable rather than interpretable.

Show the expected shape of the result (e.g. a short example with source paths) so 'keep source paths in the result' has a concrete target.

Dimension	Reasoning	Score
Conciseness	The body is two sentences with zero padding and no explanation of concepts Claude already knows; every token present is an instruction. This matches anchor 5 ('Lean and efficient; assumes Claude's competence; every token earns its place').	5 / 5
Actionability	'Keep source paths in the result. Stop when evidence is missing.' provides no command, script path, tool, or steps for actually running the check — the entire 'how' is absent, making it entirely abstract direction. Even anchor 2's example names a tool and concrete steps, so this sits at anchor 1.	1 / 5
Workflow Clarity	No sequence of steps is given and the single action is ambiguous: 'evidence' is undefined, where/how the check runs is unstated, so the simple-skill exception (unambiguous single action) does not apply. This matches anchor 1 ('Steps missing or incoherent; no sequence').	1 / 5
Progressive Disclosure	The body is under 50 lines with no bundle files and nothing that belongs in a separate file is inlined, so nothing is mis-placed. However, structure is a bare heading with no section organization, which falls short of anchor 5's 'well-organized sections' for a simple skill.	4 / 5
	Total	11 / 20 Passed

Description

45%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.

The description states a clear but thin 'what' with a single generic action, no 'when to use' guidance, and only partial natural trigger coverage. It is serviceable but reads more like an internal command name than a discovery-oriented skill description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when asked to run the local test evidence check or verify test results before reporting.'

Make the 'what' concrete by naming the key actions the check performs (e.g. locate test output, capture source paths, report or halt).

Include natural synonyms such as 'tests', 'test results', or 'verify' so the description matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	The description 'Run the local test evidence check' names the domain but offers only a single generic action ('run ... check') with no detail on what the check does, matching the anchor 'Names the domain but actions are minimal or generic'. It falls short of anchor 3, which expects at least 1-2 concrete actions beyond naming the domain.	2 / 5
Completeness	A plain 'what' is stated (runs a local check), but there is no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	'Test' and 'check' are keywords users would naturally say, but the phrasing 'test evidence check' is somewhat internal/jargon-adjacent and common variations (tests, test results, verify, validate) are absent. This sits at 'Some relevant keywords but missing common variations or synonyms', above anchor 2 because genuine natural terms are present.	3 / 5
Distinctiveness Conflict Risk	'Local test evidence check' is somewhat specific but the broad terms 'test' and 'check' create overlap risk with generic test-running, code-review, and CI skills. It matches anchor 3 ('Somewhat specific but could still overlap with similar skills') rather than anchor 4's 'minor overlap risk only'.	3 / 5
	Total	11 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/ai-engineering-from-scratch
Path: projects/skill-router/examples/skills/check-tests/SKILL.md
Commit: c02ca08

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.