CtrlK
BlogDocsLog inGet started
Tessl Logo

watsonx-ai

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

55

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/watsonx-ai/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body is a well-structured, highly actionable guide to driving WatsonX AI through the Membrane CLI, with a clear connection workflow and error-state handling. It loses points mainly to conciseness padding and a few loose workflow labels.

Suggestions

Trim the marketing-style opening paragraph and the vague Project/Data/Notebook overview bullets, which add tokens without actionable value.

Remove the duplicated action-list command in 'Popular actions' (it already appears in 'Searching for actions') or merge the two sections.

Clarify the 'skip to Step 2' references by labeling the workflow steps explicitly (e.g., 'Step 1: Connect', 'Step 2: Discover and run actions').

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete CLI commands, but includes padding such as the marketing-style overview, the vague nested Project/Data/Notebook bullet list, and a repeated action-list command in 'Popular actions' that already appeared in 'Searching for actions'.

3 / 5

Actionability

Provides many concrete, executable commands (install, login, connection ensure, action run, request) plus a flags table, with only minor gaps such as unfilled <actionId> and CONNECTION_ID placeholders.

4 / 5

Workflow Clarity

There is a clear install→authenticate→connect→poll→search→run sequence with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) acting as validation; minor gaps like the loosely labeled 'Step 2' reference keep it below 5.

4 / 5

Progressive Disclosure

Content is organized into well-signaled sections with no external bundle files and no need for nested references; the only minor gap is that the lengthy connection-state reference could optionally live in its own file.

4 / 5

Total

15

/

20

Passed

Description

57%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 what the skill does and when to use it, anchored to a specific product niche. Its main weakness is generic action verbs and a single trigger phrase lacking synonyms.

Suggestions

Replace generic verbs ('Manage', 'automate') with concrete WatsonX-specific operations (e.g., 'query datasets, manage training records, trigger model deployments').

Add more natural trigger variations users might say, such as 'WatsonX data', 'WatsonX records', or 'WatsonX workflows'.

Tighten the 'when' clause to name the specific WatsonX tasks (data, records, automation) that should route to this skill.

DimensionReasoningScore

Specificity

Names the WatsonX AI domain plus a few actions ('Manage data, records, and automate workflows'), but the verbs are generic ('manage', 'automate') rather than concrete operations, fitting the 'actions minimal or generic' anchor better than the 3 anchor.

2 / 5

Completeness

Both the 'what' (WatsonX AI integration managing data, records, workflows) and an explicit 'when' clause are present, though the 'when' could be more specific about which user requests map to this skill.

4 / 5

Trigger Term Quality

Includes one natural trigger phrase ('Use when the user wants to interact with WatsonX AI data'), but lacks synonyms or variations a user might say, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Tied to a named product (WatsonX AI) with a distinct trigger, making it mostly distinguishable; minor overlap risk with general data/AI skills keeps it just below the 5 anchor.

4 / 5

Total

13

/

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.