CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

auto-write-test-rules

Use when adding or proposing a new test ONLY if the test rules are not present

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/auto-write-test-rules/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 and correctly delegates all detail to a single clearly-referenced file, but it is cryptic: the instruction is a bare pointer with an unexplained qualifier ('regardless of path setting') that leaves the reader guessing about precedence and intent. One or two clarifying words would make the guidance fully actionable without hurting token efficiency.

Suggestions

Explain what 'regardless of path setting' means in one clause (e.g., 'even if settings.json or project config points elsewhere, this file takes precedence') so the instruction is unambiguous.

State what to do with the referenced rules, e.g., 'Apply the rules in @.claude/rules/testing.md when writing the new test', to make the guidance self-contained.

Briefly confirm the guardrail from the description ('only if test rules are not present') in the body so the trigger condition and action are aligned.

DimensionReasoningScore

Conciseness

The body is a single line ('Use @.claude/rules/testing.md regardless of path setting') with zero padding or explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

It gives one concrete pointer (an exact path, '@.claude/rules/testing.md') but no specifics about what to do with it, and 'regardless of path setting' is unexplained jargon — concrete guidance with missing key details.

3 / 5

Workflow Clarity

As a single-action skill the simple-skill exception would allow a 5, but the qualifier 'regardless of path setting' introduces ambiguity (which path setting? what overrides what?), so the single action is not fully unambiguous.

4 / 5

Progressive Disclosure

A single, clearly signaled, one-level-deep file reference with no inline bloat — the entire body is a pointer, which is exactly the appropriate split for this skill; no bundle files exist to verify, but the structure itself is optimal.

5 / 5

Total

17

/

20

Passed

Description

36%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 is a well-scoped trigger clause with a useful conditional guard, but it answers only 'when' and never 'what' — the skill's actual capability is entirely unstated. Users and Claude can tell when it might fire but not what it does, which caps both specificity and completeness.

Suggestions

Add a 'what' clause stating the capability, e.g., 'Writes project test rules to .claude/rules/testing.md. Use when adding or proposing a new test ONLY if the test rules are not present.'

Broaden trigger coverage with natural synonyms users say, such as 'write', 'create', or 'unit test', while keeping the description concise.

Keep the conditional guard but pair it with the outcome (what gets created or applied when the condition holds) so the description is self-contained.

DimensionReasoningScore

Specificity

The description names the domain ('adding or proposing a new test', 'test rules are not present') but states no action the skill itself performs — it is a pure trigger statement with no capability described, matching 'names the domain but actions are minimal or generic'.

2 / 5

Completeness

Only the 'when' is present ('Use when adding or proposing a new test ONLY if...') with no 'what' whatsoever — the reader cannot tell what the skill does (write test rules? lint tests?) — matching the anchor 'only when is present without what'.

2 / 5

Trigger Term Quality

'adding or proposing a new test' includes natural phrasing users would say, but misses common variations such as 'write', 'create', 'unit test', 'test case', or file extensions — relevant keywords with missing synonyms.

3 / 5

Distinctiveness Conflict Risk

The conditional guard ('ONLY if the test rules are not present') gives it some distinctiveness from generic test-writing skills, but without any stated capability it could still overlap with any skill that fires on test-related requests.

3 / 5

Total

10

/

20

Passed

Validation

100%

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

dlt-hub/dlt

Path

.claude/skills/auto-write-test-rules/SKILL.md

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.