CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

resource-management

Server-side Luzmo resource operations - CRUD, automation, and bulk API scripts. Use for listing, searching, creating, or deleting dashboards, datasets, themes, users, groups. Triggers on: "list all dashboards", "delete dataset", "bulk update", "automate", "script", "find resources". Critical: all deletes are irreversible and require explicit user confirmation before execution. Not for embedding saved dashboards/charts (use core), auth setup (use core), or data ingestion (use data-integration).

Quality

85%

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

78%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 well-structured operational skill with excellent progressive disclosure and highly actionable, product-specific guidance, including a properly validated workflow for irreversible deletes. Its main weakness is redundancy: the REST-verbs and delete-safety rules are each restated across three to four sections, and "Avoid", "Common Mistakes", and "Script Templates" overlap content already covered elsewhere.

Suggestions

Consolidate the REST-verbs rule into one place: keep it in "Core API Rules" and reduce "Avoid" and "Common Mistakes" to a one-line pointer instead of restating the full explanation in both sections.

Merge "Script Templates" into "Bundled References" since both sections point to the same two reference files, and mention each reference path once at the point of need rather than three times.

Add a short numbered sequence for the non-delete CRUD flow (consult the {action}{Resource}.md doc, build payload, run, check response) mirroring the explicit deletion workflow, which would close the remaining workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is dense with Luzmo-specific facts (POST-only architecture, regional base URLs, rate limits, export webhook details) and teaches nothing Claude already knows, but it could be tightened: the REST-verbs rule appears in "Core API Rules", "Avoid", and "Common Mistakes"; the delete-confirmation rule is stated in four sections; "Script Templates" largely duplicates "Bundled References"; and each reference path is pointed to three times. This duplication exceeds the "minor instances" of the anchor 4 example.

3 / 5

Actionability

Guidance is directly executable without padding: exact action names and body shapes ("`\"action\": \"get\"` with `\"find\"` wrapper"), base URLs, env var names, MCP tool names, and field-level specifics (channel_id, x-secret header, result.downloadUrl expiry, 429 behavior). Code templates are deliberately bundled one level deep in real, clearly-signaled reference files, which the scoring notes say is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

The destructive workflow is fully sequenced with explicit validation checkpoints (search first, show name/id, require the word "yes", only then delete), the Security Checkpoint is a checklist with a STOP rule, and error recovery routes to `troubleshooting`. However, the general create/update flow is implied by section order rather than an explicit sequence, a minor gap versus the anchor 5 example.

4 / 5

Progressive Disclosure

SKILL.md is a genuine overview: three real one-level-deep references (all verified present on disk), each described in "Bundled References" and invoked at the right moment (deletion-policy before handling deletes, delete-script-patterns when generating reusable scripts), with no nested reference chains and external specs linked rather than duplicated ("If content exists on developer.luzmo.com, link — do not duplicate specs here").

5 / 5

Total

17

/

20

Passed

Description

87%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 description: concrete capability list, explicit use-for and trigger phrases, and clear boundary routing to sibling skills. Only minor gaps in action coverage (update/associate) and a few missing natural synonyms keep specificity and trigger term quality at 4.

DimensionReasoningScore

Specificity

Lists several concrete actions ("listing, searching, creating, or deleting dashboards, datasets, themes, users, groups" plus "CRUD, automation, and bulk API scripts") with named resource types, but update and associate/dissociate are only implied by "CRUD", leaving minor gaps versus the comprehensive anchor.

4 / 5

Completeness

Explicitly answers both what ("Server-side Luzmo resource operations - CRUD, automation, and bulk API scripts") and when ("Use for listing, searching, creating, or deleting..." plus "Triggers on:" concrete phrases), and adds boundary exclusions ("Not for embedding... auth setup... data ingestion").

5 / 5

Trigger Term Quality

Triggers on natural user phrasings ("list all dashboards", "delete dataset", "bulk update", "automate", "script", "find resources") with good keyword coverage, but misses common variations such as "remove", "clean up", or "create a dashboard", so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Names the product, concrete resource types, and routes the highest-overlap domains away with explicit "use core" / "use data-integration" exclusions, giving a clear niche with minimal conflict risk; the only generic triggers ("automate", "script") are offset by these exclusions.

5 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

luzmo-official/agent-skills

Path

skills/resource-management/SKILL.md

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.