CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-analytics

AI-powered analytics with Luzmo - /aiprompt API and IQ embed components. Use for natural language data queries, chart generation, agentic workflows (agent analyst|item, tasks), IQ Chat/Answer embedding (luzmo-iq-embed-chat, LuzmoIQChatComponent), "AI not working", wrong answers, quality optimization. Requires AI/IQ addon license. Use eagerly for any natural-language analytics feature. Not for standard chart embedding (use core for saved dashboards, data-visualization for Flex) or React Native (IQ embed components are web-only).

74

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-structured, highly actionable multi-path skill body with clear routing, an explicit security validation gate, and proper one-level-deep reference split; the only weakness is minor redundancy (a duplicated table and recurring scoping prose).

Suggestions

Dedupe the persisted-conversations table (lines 245-250): keep a single row per resource with the full doc URL rather than repeating aiconversation/aimessage/aimessageasset twice.

Consolidate the recurring token-scoping guidance (security checkpoint, Auth and scoping, Avoid, Hand Off) into one canonical statement with cross-references to reduce repeated prose.

DimensionReasoningScore

Conciseness

Largely dense and information-rich (tables, code, URLs) rather than padded prose, but the persisted-conversations table duplicates its three rows (short doc names then full URLs) and security/scoping guidance recurs across sections, so it could be tightened. Not level 3 because of that redundancy; not level 1 because it avoids explaining concepts Claude already knows.

2 / 3

Actionability

Provides executable, copy-paste-ready guidance: the full `/aiprompt` request body, the `iq.context` token example, SSE event ordering, exact component names per framework, and concrete doc URLs.

3 / 3

Workflow Clarity

The 'Choose the Right Path' table routes to sequenced Paths A–E, and the [CRITICAL] Security Checkpoint is an explicit validation gate ("If ANY checkbox is unchecked, STOP and fix before proceeding"); troubleshooting maps problem→cause→solution as a feedback loop.

3 / 3

Progressive Disclosure

Three real one-level-deep references (data-modeling-for-iq.md, agentic-integration.md, mcp-server.md — all present on disk) are listed with one-line summaries in a 'Bundled References' section, and quality-optimization detail is correctly deferred to a reference rather than inlined.

3 / 3

Total

11

/

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.

A strong, third-person description that states concrete capabilities, explicit positive and negative triggers, and natural user phrases, with clear boundaries against sibling skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and named surfaces — "natural language data queries, chart generation, agentic workflows (agent analyst|item, tasks), IQ Chat/Answer embedding (luzmo-iq-embed-chat, LuzmoIQChatComponent)" — matching the 'lists multiple specific concrete actions' anchor rather than the partial level-2 anchor.

3 / 3

Completeness

Explicitly answers both what ("AI-powered analytics with Luzmo - /aiprompt API and IQ embed components") and when ("Use for...", "Use eagerly for any natural-language analytics feature"), plus negative triggers ("Not for standard chart embedding...").

3 / 3

Trigger Term Quality

Includes natural phrases users would actually say ("AI not working", "wrong answers", "natural language data queries", "chart generation") alongside technical component names, giving good coverage; not merely jargon like the level-1 anchor.

3 / 3

Distinctiveness Conflict Risk

Clear Luzmo-AI niche with explicit disambiguation ("Not for standard chart embedding (use core... data-visualization...) or React Native"), making overlap with sibling skills unlikely.

3 / 3

Total

12

/

12

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_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
luzmo-official/agent-skills
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.