CtrlK
BlogDocsLog inGet started
Tessl Logo

an

Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

56

Quality

64%

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/plugins/agent-native/skills/an/SKILL.md

The canonical home for this skill is an in BuilderIO/skills

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 efficient, actionable, and well-structured with concrete tool names, a usable JSON example, a focused-edit prompt template, and explicit readback validation in the edit workflow. It sits solidly at the 4-anchor across all dimensions, held from 5 by minor over-explanation and a few implicit checkpoints.

DimensionReasoningScore

Conciseness

The body is dense and instructive with no padding about what apps or MCP are; a few host-enumeration sentences could be trimmed, matching the 'efficient; minor instances of over-explanation' anchor.

4 / 5

Actionability

Concrete open_app JSON, named tools (list_apps, view-screen, run-host-webmcp-tool, ask_app, get-deck), and a copy-paste focused-task prompt give mostly executable guidance with only minor gaps for the less-common tools.

4 / 5

Workflow Clarity

A clear open → list → direct-tool-vs-ask_app → view-screen → readback sequence is present with a numbered edit checklist and explicit readback validation; not a 5 because a couple of checkpoints remain implicit.

4 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is well-organized into clear sections (Open the app, Work in Slides, Authentication, Failure handling) with no nested references; structure is good though there is nothing to point out to.

4 / 5

Total

16

/

20

Passed

Description

53%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 clearly states what the skill does and carves a distinct niche, but it lacks an explicit 'when to use' trigger clause and relies on specialized terminology over natural user phrasing, capping completeness and trigger quality at the midpoint.

Suggestions

Append an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks to open or drive an Agent-Native app like slides, or to operate a Dispatch app from the conversation').

Broaden trigger terms with user-natural synonyms and example app ids (e.g., 'slides', 'sheets') rather than only technical MCP terminology.

List a couple more concrete operations (e.g., 'open apps, drive their UI, read screen state') to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain ('Agent-Native workspace apps') and 1-2 concrete actions ('Open and operate') with mechanism detail, but does not enumerate a comprehensive list of specific actions as the score-4/5 anchors require.

3 / 5

Completeness

There is a clear 'what' (open and operate Agent-Native apps via Dispatch MCP) but no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant terms like 'Agent-Native workspace apps', 'Dispatch MCP', and 'inline app surfaces' are present but lean technical; common natural-user variations and synonyms are missing.

3 / 5

Distinctiveness Conflict Risk

The 'Agent-Native workspace apps through Dispatch MCP' niche is mostly distinct with minor overlap risk; not a 5 because the trigger phrasing is less crisp than the anchor's concrete example.

4 / 5

Total

13

/

20

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
BuilderIO/agent-native
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.