CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-man-kw

Use when testing the man golden build

Quality

55%

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 ./tests/golden/phase2/man_kw/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 a well-structured, mostly executable man-page reference with real one-level-deep bundle files and clear navigation. Its main weaknesses are redundant statistics sections, a truncated option string, a non-actionable prose-only example, and the absence of any workflow or validation sequence.

Suggestions

Deduplicate the statistics: present counts once (e.g. only in 'Documentation Statistics') rather than repeating 'Total Man Pages: 3' across sections.

Replace the 'Prose-only example with no command' entry with an actual executable command or remove it, and complete the truncated '--fol...' option text.

If the skill is meant to support testing the golden build, add a short workflow with validation steps (e.g. how to run/verify the man pages) rather than only listing extracted reference data.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes redundant sections (statistics appear in both 'Man Page Overview' and 'Documentation Statistics') and a truncated option string ('--fol...') that could be tightened; not 4 because the duplicated stats and truncation are clear padding/looseness, not 2 because it is not heavily verbose.

3 / 5

Actionability

Concrete executable command syntax and runnable examples ('git log -3', 'curl https://example.com') are provided; minor gaps (a 'Prose-only example with no command' and the truncated option text) keep it just below fully executable; not 3 because most guidance is genuinely copy-paste ready.

4 / 5

Workflow Clarity

This is a reference/lookup skill with no multi-step process or validation checkpoints; it is organized but lacks any sequence, fitting the middle anchor; not higher because no workflow or checkpoints are present, not lower because the reference structure itself is coherent.

3 / 5

Progressive Disclosure

The body points to real one-level-deep reference files (references/version_control_01.md, references/other_02.md, references/index.md, all verified present) with a clear Navigation section; not 5 because some inlined reference content (quick command reference, options, examples) overlaps with what lives in the bundle, leaving minor organization gaps.

4 / 5

Total

14

/

20

Passed

Description

28%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 thin trigger clause that names a niche domain but provides no concrete capabilities and merges a vague 'what' into a 'when' statement. It is barely distinguishable and lacks natural user-facing trigger terms.

Suggestions

Add a concrete 'what' clause stating the skill's capabilities, e.g. 'Look up syntax, options, and examples for golden-man-kw command-line tools.'

Expand trigger terms with natural user phrasing such as 'man pages', 'command syntax', 'command-line options', or 'golden build' rather than only 'testing'.

Combine what and when explicitly: 'Look up golden-man-kw command syntax, options, and examples. Use when testing the man golden build or checking command-line tool usage.'

DimensionReasoningScore

Specificity

The phrase 'testing the man golden build' names a domain but the only action ('testing') is minimal and generic, matching the 'Names the domain but actions are minimal or generic' anchor; not a 3 because no second concrete action is given, not a 1 because a domain is named.

2 / 5

Completeness

Only a 'when' clause ('Use when testing the man golden build') is present with no clear 'what' describing capabilities, matching the 'only when is present without what' anchor; not 3 because no concrete 'what' is stated.

2 / 5

Trigger Term Quality

'testing', 'man', 'golden build' are project-specific jargon with only one or two generic keywords; natural user phrases are missing, fitting the 'one or two generic keywords' anchor rather than the fuller keyword coverage of 3.

2 / 5

Distinctiveness Conflict Risk

'man golden build' is a fairly specific niche term reducing conflict risk, but 'testing' is generic and the vague scope keeps it at 'somewhat specific but could still overlap'; not 4 because the description is too thin to clearly establish a distinct niche.

3 / 5

Total

9

/

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

yusufkaraaslan/Skill_Seekers

Path

tests/golden/phase2/man_kw/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.