CtrlK
BlogDocsLog inGet started
Tessl Logo

extensions

Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use when a user asks for a dashboard, widget, calculator, or any interactive mini-app that calls external APIs. Distinct from LLM "tools" (function calls) — see note below.

71

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, code, and clear workflows backed by validation and feedback loops. Its weaknesses are conciseness (a basic Alpine directive table and a redundant 'What extensions are' section) and progressive disclosure (reference-style content kept inline rather than fully delegated to references/api.md).

Suggestions

Remove or shrink the 'Alpine.js patterns' directive table (x-data, x-show, x-if, etc.) — this is basic Alpine knowledge Claude already has; keep only the framework-specific hard rules (template wrapping, Alpine.data() for non-trivial components).

Delete the later '## What extensions are' section (line ~191); it duplicates '## CRITICAL: What Extensions Are' and the terminology note, adding tokens without new information.

Move the full in-iframe helper-signature list and the edits-operations table into references/api.md, leaving the SKILL.md body a lean overview that names the helpers and points to api.md for exhaustive signatures — tightening progressive disclosure to a one-level pointer structure.

DimensionReasoningScore

Conciseness

Mostly efficient and framework-specific (helpers, actions, persistence model), but the 'Alpine.js patterns' directive table restates basic Alpine knowledge Claude already has, and the later '## What extensions are' section repeats the earlier 'CRITICAL: What Extensions Are' content; not a 1 because the bulk is genuinely non-obvious framework detail, not a 3 because of the redundancy and the basic-knowledge table.

2 / 3

Actionability

Provides executable commands ('pnpm action create-extension ...'), HTTP API bodies, copy-paste payloadJson edit examples, and concrete field/operation tables; not a 2 because the guidance is complete and executable rather than pseudocode with missing details.

3 / 3

Workflow Clarity

Create and edit flows are sequenced with explicit validation (expectedMatches, missing-targets-fail, format:true) and an error-recovery feedback loop ('If a focused edit fails, inspect the current body and adjust its target; do not retry unchanged arguments'); not a 2 because checkpoints and feedback loops are explicit, not merely implied.

3 / 3

Progressive Disclosure

Two real, one-level-deep, well-signaled references (api.md, examples.md) with 'read this when...' guidance, but the ~500-line body retains reference-style inline content (full helper-signature list, Alpine.js directive table, edits-operations table) that overlaps the delegated api.md; not a 3 because the overview is a monolith rather than a lean pointer-and-summary, not a 1 because references exist and are clearly signaled.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, third-person, and answers both what and when with an explicit 'Use when' trigger and natural user terms. It also proactively distinguishes extensions from LLM tools, minimizing conflict risk.

DimensionReasoningScore

Specificity

Quotes 'Creating, editing, and managing extensions' — three concrete verbs naming the skill's actions, matching the multiple-specific-actions anchor; not a 2 because it is comprehensive rather than naming only a partial subset.

3 / 3

Completeness

Clearly states what ('Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes') and when ('Use when a user asks for a dashboard, widget, calculator...'), an explicit Use-when trigger; not a 2 because the when-clause is explicit, not merely implied.

3 / 3

Trigger Term Quality

Quotes 'dashboard, widget, calculator, or any interactive mini-app that calls external APIs' — these are natural terms a user would say, with good variation coverage; not a 2 because common user phrasings are well represented rather than partially missing.

3 / 3

Distinctiveness Conflict Risk

Quotes 'sandboxed Alpine.js mini-apps that run inside iframes' and 'Distinct from LLM "tools" (function calls)' — a clear niche with an explicit disambiguation from the most likely conflicting concept; not a 2 because the distinction is made explicit rather than left to overlap.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (519 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

13

/

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.