AccountScore integration. Manage data, records, and automate workflows. Use when the user wants to interact with AccountScore data.
44
46%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/accountscore/SKILL.mdQuality
Discovery
57%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 follows the correct structural pattern with a 'Use when' clause, and the product name 'AccountScore' provides some distinctiveness. However, the capabilities described are extremely vague and generic—'manage data, records, and automate workflows' could describe almost any integration tool. The description fails to communicate what AccountScore actually is or what specific operations can be performed.
Suggestions
Replace vague actions with specific AccountScore capabilities, e.g., 'Retrieve account scoring data, generate financial risk assessments, pull open banking reports' or whatever the actual capabilities are.
Add natural trigger terms users might say, such as specific AccountScore features, data types, or file formats (e.g., 'bank transaction analysis', 'credit scoring', 'affordability checks').
Clarify what AccountScore is (e.g., 'open banking data platform') so Claude can distinguish it from other integrations that also manage data and records.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The actions listed ('manage data, records, and automate workflows') are extremely vague and generic. There are no concrete, specific actions like 'create reports', 'pull credit scores', or 'sync account records'. These phrases could apply to virtually any integration. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' ('Use when the user wants to interact with AccountScore data'). While the content is vague, the structure explicitly addresses both questions with a 'Use when' clause. | 3 / 3 |
Trigger Term Quality | It includes the product name 'AccountScore' which is a useful trigger term, but lacks any natural keywords a user might say beyond that. Terms like 'data', 'records', and 'workflows' are too generic to serve as meaningful triggers. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'AccountScore' as a specific product name provides some distinctiveness, but the generic actions ('manage data, records, automate workflows') could easily overlap with any other integration or data management skill. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a generic Membrane CLI integration template with 'AccountScore' substituted in. It lacks AccountScore-specific actionable content—no specific endpoints, action examples, data schemas, or domain-specific workflows. The content is verbose with explanations Claude doesn't need (what AccountScore is, what churn prediction means) while missing the specific details that would actually help Claude interact with AccountScore effectively.
Suggestions
Remove the introductory explanation of what AccountScore is and what churn prediction means—Claude already knows these concepts. Start directly with integration instructions.
Add AccountScore-specific examples: actual endpoint paths for the proxy, sample action IDs/names, example input/output for common operations like retrieving account scores or customer data.
Factor out generic Membrane CLI instructions (authentication, connection management, proxy usage) into a shared reference file, keeping only AccountScore-specific content in SKILL.md.
Add concrete workflow examples for common AccountScore tasks (e.g., 'Get churn score for an account', 'List at-risk accounts') with specific commands and expected outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and includes significant unnecessary explanation. The opening paragraph explains what AccountScore is and what churn prediction means—concepts Claude already knows. The Membrane CLI setup, authentication flows, and connection state machine are generic Membrane patterns repeated across many skills, not specific to AccountScore. The 'AccountScore Overview' section with just 'Account > Score > Configuration' adds no value. | 1 / 3 |
Actionability | The skill provides concrete CLI commands for authentication, connection setup, action discovery, and proxy requests, which is good. However, there are no AccountScore-specific examples—no actual action IDs, endpoint paths, or sample inputs/outputs for AccountScore operations. The guidance is generic Membrane usage rather than AccountScore-specific actionable steps. | 2 / 3 |
Workflow Clarity | The connection setup workflow is reasonably well-sequenced with state handling (READY, CLIENT_ACTION_REQUIRED, etc.) and polling instructions. However, there are no validation checkpoints for the actual AccountScore operations, no error recovery guidance for failed actions, and the overall workflow from 'connect' to 'accomplish a task' lacks a clear end-to-end sequence. | 2 / 3 |
Progressive Disclosure | The content is structured with headers and sections, but it's essentially a monolithic document with no references to supporting files. The Membrane CLI generic instructions (authentication, connection management, proxy requests) could be factored out into a shared reference, keeping only AccountScore-specific content inline. No bundle files are provided to support progressive disclosure. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
f484c82
Table of Contents
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.