CtrlK
BlogDocsLog inGet started
Tessl Logo

testgen

Generate tests with expert routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test coverage.

80

1.07x
Quality

74%

Does it follow best practices?

Impact

87%

1.07x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/testgen/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 actionable and well-structured with concrete commands and a clear step sequence, but it loses points for repeated routing content, a missing validation checkpoint in the workflow, and reference files that are named but not present.

Suggestions

Consolidate the routing information (Step 4 diagram, Step 4 table, and 'Expert Routing Details' section) into one authoritative location to remove redundancy and reduce token cost.

Add an explicit validation checkpoint in Step 6 — e.g. run the generated tests, verify they pass, and fix failures before suggesting next steps — to satisfy the batch-operation feedback-loop requirement.

Either add the referenced frameworks.md and visual-testing.md files to a references/ bundle or remove the dangling references so navigation is not broken.

DimensionReasoningScore

Conciseness

Mostly token-efficient with diagrams, tables, and code blocks rather than concept over-explanation, but the routing information is repeated three times (Step 4 architecture box, Step 4 table, and the 'Expert Routing Details' section), which is more than minor padding.

3 / 5

Actionability

Provides concrete, mostly copy-paste-ready bash commands (test, rg, fd, jq, grep), real file patterns, and a TaskCreate example, but a few guidance blocks rely on undefined env vars ($TARGET) and the Task-tool invocation stays pseudocode-ish.

4 / 5

Workflow Clarity

The 6-step process is clearly sequenced, but for a generative/batch operation it only suggests running tests and auto-creates a task without an explicit validate-then-fix checkpoint, so the batch-operation validation cap holds it at 3.

3 / 5

Progressive Disclosure

Sections are well organized and reference files (frameworks.md, visual-testing.md) are signaled one level deep, but those referenced files are absent from the bundle, so navigation is good but not fully verified.

4 / 5

Total

14

/

20

Passed

Description

87%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 strong: it states concrete capabilities, provides explicit third-person trigger phrases, and occupies a distinct niche. Main room for improvement is adding synonyms and file extensions to push trigger quality to full coverage.

DimensionReasoningScore

Specificity

Names the domain plus three concrete capabilities ('expert routing, framework detection, and auto-TaskCreate'), but 'expert routing' and 'framework detection' stay somewhat abstract compared to fully concrete verbs, so it sits below the comprehensive-coverage anchor 5.

4 / 5

Completeness

Clearly states the 'what' (Generate tests with expert routing, framework detection, auto-TaskCreate) and explicitly answers 'when' via the concrete 'Triggers on: ...' clause with multiple trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Lists five natural phrases users would say ('generate tests, write tests, testgen, create test file, add test coverage') including the skill's own name, but omits common synonyms (e.g. 'unit tests', 'test coverage') and file extensions, keeping it just below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (test generation) with distinctive, test-specific triggers and the unique 'testgen' keyword, giving minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeverSight/skills_feed
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.