alethia

Drive a real browser with plain English via Alethia — the patent-pending zero-IPC agent-driven testing runtime. Use when the user asks to smoke-test a local app, run an accessibility (WCAG) or security (NIST SP 800-53) audit, prove the EA1 safety gate works, bootstrap test coverage on an unknown page, run parallel multi-page checks, or export a cryptographically signed evidence pack. Requires the @vitronai/alethia MCP server to be configured. Trigger patterns include "test this page," "verify the login flow," "audit accessibility," "compliance audit," "run WCAG/NIST," "check that deletes are blocked," and similar.

Quality

94%

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

Quality

Content

88%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.

A highly actionable, well-sequenced skill body that earns its length with Alethia-specific knowledge and concrete examples. The main improvement is trimming time-sensitive version detail and considering splitting a couple of the longer example sections out of the main file.

Suggestions

Move the version-specific 'bridge 0.6.1' / 'Server transport closed unexpectedly' troubleshooting into an 'Old patterns' or 'Deprecated' section, or generalize it, so time-sensitive content does not bloat the main flow.

Consider extracting the four-example 'Dev feedback loop' eval block into a reference file, keeping one representative example inline, to tighten the main SKILL.md.

The 'NLP patterns that work well' and 'NLP patterns that trip the resolver' sections overlap with 'How to drive Alethia in NLP'; merging or cross-linking them would reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly lean and focused on Alethia-specific concepts Claude does not already know, but a few sections could be trimmed — notably the version-specific 'bridge 0.6.1' troubleshooting, which is time-sensitive information not placed in a deprecated/old-patterns section.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance across the common cases — NLP step examples, tool calls with concrete parameters, bash install/cache-clear commands, and JavaScript eval snippets.	5 / 5
Workflow Clarity	Multi-step flows are clearly sequenced with explicit validation ('confirm it's actually available' before use) and a feedback loop (read nearMatches/suggestedFix then retry); destructive and batch operations are validated via the 'expect block:' primitive and assert_safety regression check.	5 / 5
Progressive Disclosure	Well-organized single-file skill with clearly headed sections and no nested references; organization is good, though some detail (e.g., the four eval examples, expanded NLP patterns) could arguably be split out, keeping it just below the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

100%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.

A strong, concrete description that explicitly answers what and when with a rich set of natural trigger phrases and a distinct niche. The only minor blemish is the 'patent-pending zero-IPC agent-driven' phrasing, which borders on buzzword, but it does not undermine the concrete capability list.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — smoke-testing, WCAG/NIST audits, proving the EA1 gate, bootstrapping coverage, parallel multi-page checks, and exporting a signed evidence pack — covering the skill's surface comprehensively.	5 / 5
Completeness	Clearly states both what the skill does ('Drive a real browser with plain English via Alethia') and when to use it ('Use when the user asks to…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit 'Trigger patterns include' clause surfaces natural user phrases such as 'test this page,' 'verify the login flow,' 'audit accessibility,' 'compliance audit,' and 'run WCAG/NIST,' with synonyms covered.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — agent-driven browser testing via the Alethia MCP server with WCAG/NIST audits and the EA1 safety gate — with distinct triggers and minimal overlap risk.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vitron-ai/alethia-mcp
Path: skills/alethia/SKILL.md
Commit: 0ada961

Reviewed: 2 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.