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).

68

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

77%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 validation checkpoints for destructive/batch operations, clean one-level reference bundling, and concrete actionable guidance. Its main weakness is redundancy: the POST-only and delete-confirmation rules are each restated three to four times across Avoid, Common Mistakes, and dedicated sections, which inflates token cost without adding new information.

Suggestions

Merge the 'Avoid' section into 'Common Mistakes' (or vice versa) — both restate POST-only, delete confirmation, and credential exposure already covered in 'Core API Rules' and the 'Deletion Safety Rule'; keep only the versions that add new symptom/frequency detail.

Fold 'Script Templates' and 'Association Flows' into 'Bundled References' and the 'Action Map' respectively — both sections currently restate pointers and mappings already given one section earlier.

Add one minimal inline request-body example (e.g., a 'get' call with a 'find' filter for searchDashboard) so the most common call shape is executable without opening a reference file.

DimensionReasoningScore

Conciseness

No concept-teaching padding and it assumes Claude's competence, but the same rules are restated across many sections: POST-only appears in Core API Rules, Avoid, and Common Mistakes; the delete-confirm rule appears in the Security Checkpoint, Deletion Safety Rule, Avoid, and Common Mistakes; 'Script Templates' and 'Association Flows' largely duplicate 'Bundled References' and the Action Map. Several sections could be merged or cut.

3 / 5

Actionability

Highly actionable instruction guidance: exact base URLs, action names, doc-URL patterns, an intent-to-action table, the literal confirmation word 'yes', and dry-run flag patterns; code templates are properly delegated to references/script-examples.md. Minor gap: no sample request body (e.g., a 'find' filter shape) inline.

4 / 5

Workflow Clarity

Clear sequences with explicit validation: the deletion workflow is search -> show -> require 'yes' -> delete-only-after-confirmation with a stop-when-nothing-found branch; the Security Checkpoint is a checkbox gate ('If ANY checkbox is unchecked, STOP'); rate limits specify exponential backoff retry, and 401/403/404 errors route to troubleshooting — validation for both destructive and batch operations is present.

5 / 5

Progressive Disclosure

SKILL.md is a well-sectioned overview; all three referenced files (script-examples.md, deletion-policy.md, delete-script-patterns.md) exist, are one level deep, and are clearly signaled with per-file descriptions in 'Bundled References'; specs are delegated to developer.luzmo.com rather than duplicated ('If content exists on developer.luzmo.com, link — do not duplicate specs here').

5 / 5

Total

17

/

20

Passed

Description

88%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: third-person, concrete, with explicit what/when clauses, natural trigger phrases, a critical safety flag, and negative scope boundaries. Main residual risk is overlap with sibling Luzmo skills and a slightly generic 'script' trigger.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('listing, searching, creating, or deleting') across named resource types ('dashboards, datasets, themes, users, groups'), with 'CRUD, automation, and bulk API scripts' covering the update side; coverage is comprehensive for the domain.

5 / 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...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Six natural trigger phrases ('list all dashboards', 'delete dataset', 'bulk update', 'automate', 'script', 'find resources') give good coverage, but update/associate phrasings are missing and the bare term 'script' is generic enough to over-trigger.

4 / 5

Distinctiveness Conflict Risk

Clear niche (server-side Luzmo CRUD) with explicit 'Not for' redirects to core and data-integration, but sibling skills like theming/analytics-studio/ai-analytics also field resource CRUD requests and aren't excluded, leaving minor overlap risk.

4 / 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.