install-verification

Use before claiming that the package can be installed or published. Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries.

Quality

73%

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 ./skills/install-verification/SKILL.md

Quality

Content

71%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 admirably lean and has a clear sequence with an explicit completion gate, but it references scripts and paths that are not bundled and leaves the inspection criteria implicit. Fixing the broken script references and stating what each check should verify would materially raise actionability and progressive disclosure.

Suggestions

Bundle the referenced scripts (scripts/verify-package.sh, scripts/public_safety_check.sh, scripts/install.sh) or replace the commands with inline, self-contained checks so the guidance is actually executable.

For each inspected item, state the acceptance criterion (e.g. ".agents/ must contain a manifest.json; AGENTS.md must list all bundled agents") instead of the bare word "inspect".

Add a brief feedback loop: if a required file is missing or a check fails, name the remediation step before re-running rather than only "Do not claim completion".

Dimension	Reasoning	Score
Conciseness	The body is extremely lean — two script commands, a bulleted path list, and one gating sentence — with no padded explanations and every token earning its place.	5 / 5
Actionability	Concrete commands and a specific file list are present, but the referenced scripts (scripts/verify-package.sh, scripts/public_safety_check.sh) do not exist in the bundle and "inspect" never says what constitutes a passing result for each item.	3 / 5
Workflow Clarity	A clear run-then-inspect-then-gate sequence is present with an explicit checkpoint ("Do not claim completion if any required file is missing"), but there is no error-recovery feedback loop and inspection criteria are left implicit.	4 / 5
Progressive Disclosure	Sections are organized (Run / Then inspect / gate), but the body points to scripts/*.sh and path entries that are not present in any bundle directory, so the references are broken rather than clearly navigable.	3 / 5
	Total	15 / 20 Passed

Description

75%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 and clearly answers both what the skill does and when to use it, listing several concrete verification targets. It is mostly distinct but uses a single somewhat unnatural gating trigger and one repeated verb rather than multiple distinct actions.

Suggestions

Reframe the trigger in natural user language, e.g. "Use when checking whether a package is ready to install or publish" and list a couple more concrete trigger situations.

Vary the verbs beyond the single "Verifies" to convey distinct actions (e.g. "Checks structure, validates schemas, confirms executable scripts, enforces public-safety boundaries").

Add common synonyms or file extensions users might say (e.g. ".agents/", "plugin", "skill package") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Verifies structure, adapters, schemas, executable scripts, and public-safety boundaries" names the domain plus five concrete things checked, listing several specific items with only minor coverage gaps.	4 / 5
Completeness	It answers "what" (verifies structure/adapters/schemas/scripts/boundaries) and "when" ("Use before claiming that the package can be installed or published"), but the single gating trigger could name more situations to reach full explicitness.	4 / 5
Trigger Term Quality	Terms like "installed", "published", "package", and "verify" give good keyword coverage with synonyms, though the "Use before claiming..." trigger is slightly unnatural and no file extensions are named.	4 / 5
Distinctiveness Conflict Risk	The install/publish verification niche plus "public-safety boundaries" and "adapters" is mostly distinct, though generic "verifies structure/schemas" language could overlap with general validation skills.	4 / 5
	Total	16 / 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: 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.