CtrlK
BlogDocsLog inGet started
Tessl Logo

neural-link

Expert tactical knowledge on sequencing Neural Link MCP tools to inspect, debug, and manipulate live Neo.mjs applications. Triggers: Use this skill if the user asks you to interact with the browser, inspect the UI natively, patch live code, or use the Neural Link.

62

Quality

73%

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 ./.agents/skills/neural-link/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

An extremely lean gateway skill that excels at conciseness and progressive disclosure but offloads all executable guidance and validation to the reference file, leaving the body itself only vaguely actionable and without inline workflow safeguards.

Suggestions

Add a short inline summary of the core workflow chains (discovery, patching protocol with mandatory get_method_source before patch_code) so the body is actionable even before opening the handbook.

Surface the key destructive-operation safeguard inline, e.g. a one-line note that patch_code requires enableHotPatching and a prior get_method_source call, to satisfy validation-checkpoint expectations in the body.

Include a one-line pointer to the session-invalidation rule (flush sessionId after reload_page) since it is a critical failure mode users would hit immediately.

DimensionReasoningScore

Conciseness

The body is a single lean sentence that defers all detail to the bundled handbook, assuming Claude's competence with no concept re-explanation or padding; every token earns its place.

5 / 5

Actionability

It gives only a high-level directive ('use the view_file tool to read... operational-handbook.md before invoking any native MCP tools') with no inline concrete steps, commands, or examples; executable specifics live entirely off-page.

2 / 5

Workflow Clarity

A single prerequisite step (read the handbook first) is sequenced, but the body itself contains no validation checkpoints or feedback loops for the destructive live-patching operations the skill governs; the cap for destructive ops without inline validation applies.

3 / 5

Progressive Disclosure

Clear single-purpose overview with one well-signaled, one-level-deep reference (operational-handbook.md) that exists as a real bundle file, and content appropriately split out of the overview.

5 / 5

Total

15

/

20

Passed

Description

83%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, specific description that clearly states both capability and explicit trigger conditions in third person. Minor room for broader synonym coverage and slightly tighter distinctiveness on generic UI-inspection phrasing.

DimensionReasoningScore

Specificity

Names the domain (Neural Link MCP tools, Neo.mjs) and several concrete actions ('inspect, debug, and manipulate live Neo.mjs applications', 'interact with the browser, inspect the UI natively, patch live code'), with minor coverage gaps around specific tool families.

4 / 5

Completeness

Explicitly answers both 'what' (expert tactical knowledge on sequencing Neural Link MCP tools to inspect/debug/manipulate live Neo.mjs apps) and 'when' (an explicit 'Triggers: Use this skill if...' clause listing concrete trigger conditions).

5 / 5

Trigger Term Quality

Includes natural user phrases ('interact with the browser', 'inspect the UI natively', 'patch live code', 'use the Neural Link') that a user would plausibly say, though it leans slightly on the proper noun 'Neural Link' rather than broad synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The Neo.mjs / Neural Link niche is specific and unlikely to collide with general skills, but the shared trigger 'inspect the UI' has minor overlap risk with generic browser-inspection skills.

4 / 5

Total

17

/

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
neomjs/neo
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.