CtrlK
BlogDocsLog inGet started
Tessl Logo

databox

Databox integration. Manage data, records, and automate workflows. Use when the user wants to interact with Databox data.

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/databox/SKILL.md
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 a well-structured, highly actionable guide to driving Databox through the Membrane CLI, with a real state-polling feedback loop for connection setup. Its main weaknesses are a broken "Step 2" cross-reference and a lack of result verification after action runs.

DimensionReasoningScore

Conciseness

The body is dominated by lean executable commands and a flag table with minimal prose; the only trimmable padding is the ~40-line Databox entity list and the intro paragraph, so it sits at anchor 4 (efficient, minor over-explanation) rather than the fully lean anchor 5.

4 / 5

Actionability

Concrete, runnable commands cover every common case (install, login, connection ensure, wait/poll, action list/run, proxy) plus a flag table, but they rely on placeholders (CONNECTION_ID, <actionId>, <agentType>) and lack a fully-worked end-to-end example with real values, fitting anchor 4's 'mostly executable, minor gaps'.

4 / 5

Workflow Clarity

A clear sequence (install → auth → connect → wait → search → run) is present with a genuine feedback loop in the connection-polling section (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR states with re-polling), but the orphaned "skip to Step 2" reference (no Step 2 is labeled) and absent result verification after running actions are minor validation gaps at anchor 4.

4 / 5

Progressive Disclosure

No bundle files exist and the single SKILL.md is organized under clear section headers with no nested/dead references; the dynamic-action discovery is correctly delegated to a runtime command, placing it at anchor 4 (good structure, minor organization gaps) rather than anchor 5 since the inline entity list could be split out.

4 / 5

Total

16

/

20

Passed

Description

70%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 cleanly states both purpose and an explicit trigger clause anchored to the named product Databox, but its action language is generic rather than concrete. It is solid and usable with minor room to sharpen specificity.

Suggestions

Replace generic verbs with concrete Databox capabilities, e.g. "Pull metrics, build dashboards, create alerts and reports, and automate workflows" to lift specificity.

Add common natural trigger synonyms such as "KPIs", "dashboards", or "analytics" so users phrasing the need differently still match.

DimensionReasoningScore

Specificity

Quotes "Manage data, records, and automate workflows" name the Databox domain and enumerate several action verbs, but the actions are generic/abstract rather than concrete (cf. anchor 4's "Extracts text... fills forms"), matching anchor 3's '1-2 concrete actions, not comprehensive' despite listing three phrases.

3 / 5

Completeness

Both what ("Databox integration. Manage data, records, and automate workflows.") and an explicit when ("Use when the user wants to interact with Databox data.") are present; it stops short of anchor 5 because the 'what' is vague rather than concrete trigger phrases.

4 / 5

Trigger Term Quality

Natural terms present include "Databox", "data", "records", "workflows", and "interact with Databox data" — good coverage of the dominant product-name trigger with a couple natural variations, though a few synonyms are missing, fitting anchor 4.

4 / 5

Distinctiveness Conflict Risk

The named product "Databox" gives a clear niche with distinct triggers, but the generic action language ("manage data, records, automate workflows") leaves minor overlap risk with other data/analytics skills, matching anchor 4.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
membranedev/application-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.