Name: install-verification
Rating: 63.2 (1 reviews)
Author: agentlas-ai

install-verification

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

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/install-verification/SKILL.md

The canonical home for this skill is install-verification in agentlas-ai/Agentlas-OS

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 content is exceptionally concise and provides concrete commands with a clear validation gate, making it highly actionable for a simple verification skill. Its main weakness is that referenced scripts are not bundled and there is no error-recovery guidance when verification fails.

Suggestions

Bundle the referenced scripts (verify-package.sh, public_safety_check.sh, install.sh) under scripts/ so the commands actually resolve, or note where they originate.

Add a brief error-recovery loop: what to inspect or fix when a required file is missing before re-running verification.

Clarify what 'inspect' should confirm for each listed path (e.g., presence vs. expected contents) so the validation checkpoint is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or explanation of concepts Claude already knows — 'Run', a code block, 'Then inspect', a bulleted list, and a one-line completion gate — so every token earns its place per the 'lean and efficient' anchor.	5 / 5
Actionability	It gives concrete, copy-paste-ready commands (scripts/verify-package.sh, scripts/public_safety_check.sh) and a specific inspect list, but the referenced scripts are not present in any bundle, leaving a minor gap that keeps it below the fully executable 5.	4 / 5
Workflow Clarity	The sequence is clear — run verification scripts, then inspect required files, then gate completion on no missing files — with an explicit validation checkpoint, but it lacks an error-recovery feedback loop for what to do when a file is missing, fitting the 'clear sequence with most checkpoints; minor validation gaps' anchor.	4 / 5
Progressive Disclosure	The short, single-purpose body is well organized into Run/inspect/gate sections, but it references scripts/ paths that do not exist in the bundle, a minor navigation/organization gap that prevents the 5 even under the simple-skill exception.	4 / 5
	Total	17 / 20 Passed

Description

67%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 concise, uses an explicit 'Use when...' trigger, and names three concrete capabilities, but its trigger terms are somewhat technical and lack natural synonyms. It is a solid, mostly distinct description with room to broaden trigger phrasing.

Suggestions

Add natural-language trigger synonyms a user might actually say (e.g., 'agent plugin', 'skill bundle', 'runtime discovery') alongside the technical terms.

Make the 'when' clause more specific about the situations that call for verification (e.g., 'after generating an agent package, before publishing').

Consider naming the output artifacts or file types involved to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (agent package install verification) and three concrete actions — 'can be installed, discovered by runtimes, and checked without private dependencies' — which matches the 'lists several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	It states both the 'what' (verifying install/discovery/dependency safety) and an explicit 'when' via the 'Use when...' clause, but the trigger could be more specific, matching the 'has both what and when; when could be more explicit' anchor.	4 / 5
Trigger Term Quality	Relevant terms like 'verifying', 'installed', 'discovered by runtimes', and 'private dependencies' appear, but they skew technical and omit common natural variations a user might say, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'generated agent package' niche with install/discovery/dependency triggers is clearly distinct from most skills, with only minor overlap risk against general packaging skills, fitting the 'mostly distinct; minor overlap risk' anchor rather than the fully conflict-free 5.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/install-verification/SKILL.md
Commit: a7988bb

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.