CtrlK
BlogDocsLog inGet started
Tessl Logo

auxiliary-only-skill

A skill that uses only shell and config code blocks for testing contamination.

48

Quality

50%

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 ./crates/skill-validator-rs/tests/golden-corpus/fixtures/testdata/auxiliary-only-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 compact, well-organized set of setup, configuration, and run instructions with concrete commands and no wasted tokens. Its main weaknesses are the reference to a non-existent start.sh and the absence of any explanation of what the service does or how to verify it started.

DimensionReasoningScore

Conciseness

The body is lean and efficient — short section labels, minimal fenced blocks, and no explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Guidance is mostly executable ('brew install jq yq', complete YAML and JSON configs, './start.sh --config config.yaml'), but the referenced start.sh does not exist in the bundle and the installed tools are never used in any subsequent task, leaving minor gaps that keep it below fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

The Setup → Configuration → Running sequence is clear and the operations are non-destructive so no validation cap applies, but the workflow ends at an absent script and never states what 'the service' does or what to verify afterward — minor gaps consistent with anchor 4.

4 / 5

Progressive Disclosure

Sections are well-organized and the file is short, which the simple-skill exception could reward with a 5, but scoring against the actual bundle structure the only referenced path ('./start.sh') is a dangling reference with no bundle files present, matching the 'minor organization gaps' anchor.

4 / 5

Total

17

/

20

Passed

Description

17%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 reads as an internal test annotation rather than a user-facing skill description: it documents the skill's composition for contamination-testing purposes and omits any capability, trigger, or use-case guidance. It would never surface naturally in response to a user request.

Suggestions

State concrete capabilities in third person (e.g., 'Installs jq/yq, generates server configuration files, and starts the service') instead of describing the skill's internal composition.

Add an explicit 'Use when...' trigger clause naming the natural phrases or tasks that should activate this skill.

Include natural trigger keywords and synonyms users would actually say, replacing the meta-jargon 'testing contamination'.

DimensionReasoningScore

Specificity

The description names a domain ("uses only shell and config code blocks") but the closest thing to an action is "for testing contamination", which describes the skill's internal composition rather than any concrete user-facing capability; it never lists what the skill actually does.

2 / 5

Completeness

It offers only a vague "what" (a statement about the skill's composition, not a capability) and no "when" guidance at all — there is no "Use when..." or equivalent trigger clause, which caps completeness at 3; it sits at 2 because the "what" is unclear.

2 / 5

Trigger Term Quality

There are no natural keywords a user would say when needing this skill; "shell and config code blocks" and "testing contamination" are internal/meta testing jargon, matching the anchor for purely technical jargon with no natural terms.

1 / 5

Distinctiveness Conflict Risk

Naming no functional domain, the description provides no distinct triggers and fails to meaningfully distinguish the skill from others; it is slightly more specific than a fully generic phrase like "helps with documents", keeping it above 1.

2 / 5

Total

7

/

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
pantheon-org/tekhne
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.