CtrlK
BlogDocsLog inGet started
Tessl Logo

compass-ai

Compass AI integration. Manage data, records, and automate workflows. Use when the user wants to interact with Compass AI 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/compass-ai/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable integration guide with executable commands and a clear state-driven workflow including feedback loops. Main improvements would be tightening a few editorial lines and clarifying the step numbering.

DimensionReasoningScore

Conciseness

The body is largely command-focused and avoids explaining concepts Claude already knows, with only minor editorial padding like 'so you can focus on the integration logic' and 'This is the fastest way to get a connection' that could be trimmed.

4 / 5

Actionability

It provides fully executable, copy-paste-ready commands across all common cases (install, login, connect, search, run, proxy) with real flags and a concrete options table, covering the workflow end-to-end.

5 / 5

Workflow Clarity

A clear sequence runs from install through auth, connection, and action execution, with explicit state-based checkpoints and a poll/verify feedback loop for connection readiness; minor gaps include inconsistent step numbering and no validation step before running actions.

4 / 5

Progressive Disclosure

The single-file body is well-organized into clear sections with easy navigation and overview material up front; with no bundle files present it stays appropriately self-contained, though it carries no one-level-deep references that would justify a 5.

4 / 5

Total

17

/

20

Passed

Description

62%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 covers both what and when and anchors on a specific product name, but relies on generic action language and lacks rich trigger-term coverage. Tightening the action verbs and adding concrete trigger phrases would lift it.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with specific Compass AI actions such as querying company financials, screening stocks, and configuring price alerts.

Expand the 'Use when...' clause with concrete natural-language triggers users would actually say, e.g. 'Use when the user wants to look up company financials, run a stock screener, or set price alerts in Compass AI.'

Add domain synonyms and natural terms (e.g. 'company data', 'stock screener', 'alerts') to broaden trigger coverage beyond the generic word 'data'.

DimensionReasoningScore

Specificity

It names the Compass AI domain plus several action-words ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete, fitting the 'names domain and a few actions but not comprehensive' anchor.

3 / 5

Completeness

It explicitly answers both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with Compass AI data'), though the 'when' clause could be more specific with concrete triggers.

4 / 5

Trigger Term Quality

The product name 'Compass AI' plus generic terms 'data' and 'records' give some natural keywords, but common variations and synonyms are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Tying the skill to the specific named product 'Compass AI' gives it a clear niche with minor overlap risk, though the generic 'manage data/records' phrasing keeps it from a clean distinct-trigger score of 5.

4 / 5

Total

14

/

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.