CtrlK
BlogDocsLog inGet started
Tessl Logo

install-verification

Use when verifying that a generated agent package can be installed, discovered by runtimes, and checked without private dependencies.

74

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplar of lean, actionable verification guidance: concrete scripts, a specific checklist, and an explicit completion gate with no wasted tokens. No changes are needed.

DimensionReasoningScore

Conciseness

The body is lean with no padding or explanation of concepts Claude already knows; every line (the run block, the inspect checklist, the completion gate) earns its place. It is not level 2 because nothing could be tightened or removed without losing guidance.

3 / 3

Actionability

It gives concrete executable commands ("scripts/verify-package.sh", "scripts/public_safety_check.sh"), a specific file/directory checklist to inspect, and a clear completion criterion. It is not level 2 because the guidance is copy-paste ready rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

The sequence Run → inspect → "Do not claim completion if any required file is missing" provides an explicit validation checkpoint for a simple verification skill. It is not level 2 because the checkpoint is stated outright rather than merely implied.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external bundle references (references/scripts/assets are empty) and is organized into clear run and inspect sections, so the simple-skill allowance applies. It is not level 2 because there is no monolithic wall of text or nested references.

3 / 3

Total

12

/

12

Passed

Description

85%

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 specific, complete, and distinctive, with an explicit use-trigger. Its only weakness is trigger-term quality: the phrasing centers on the model's claim rather than natural user keywords, limiting discoverability.

Suggestions

Reframe the trigger around natural user phrasings, e.g. "Use when the user asks to verify a package can be installed or published, or before declaring an install/publish task complete."

Add common keyword variations such as "installable", "publishable", "package validation", or "release readiness" so the skill surfaces for the terms users actually say.

DimensionReasoningScore

Specificity

"Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries" lists multiple specific concrete verification targets rather than a single vague verb, matching the level-3 anchor. It is not level 2 because the enumeration is comprehensive, not just a domain plus a few actions.

3 / 3

Completeness

It explicitly answers both "what" ("Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries") and "when" ("Use before claiming that the package can be installed or published") with an explicit trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

"Use before claiming that the package can be installed or published" surfaces relevant keywords ("package", "installed", "published"), but the trigger is framed around the model's own claim rather than natural user phrasings and omits common variations. It is above level 1 because real keywords are present, but below level 3 due to thin coverage.

2 / 3

Distinctiveness Conflict Risk

The package install/publish verification niche with public-safety boundaries is specific and unlikely to fire for unrelated skills. It is not level 2 because the scope is sharply bounded rather than broadly overlapping.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
agentlas-ai/Agentlas-OS
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.