21risk
21RISK integration. Manage data, records, and automate workflows. Use when the user wants to interact with 21RISK data.
58
67%
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/21risk/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 benefits from naming a specific product (21RISK) and including an explicit 'Use when' clause, which aids in selection. However, it is severely lacking in specificity — the actions described are generic placeholders that don't convey what the skill actually does within 21RISK. A user or Claude cannot distinguish what concrete capabilities this skill offers beyond the product name.
Suggestions
Replace vague terms like 'manage data, records, and automate workflows' with specific actions the skill performs, e.g., 'create and update risk assessments, manage action items, generate compliance reports'.
Add domain-specific trigger terms that users would naturally say, such as 'risk assessment', 'safety audit', 'compliance', 'hazard', or other 21RISK-specific concepts.
Expand the 'Use when' clause with more specific trigger scenarios, e.g., 'Use when the user mentions 21RISK, risk assessments, safety management, or wants to pull compliance data from 21RISK.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without specifying concrete actions. It doesn't explain what kind of data, what records, or what workflows — these are generic terms that could apply to almost any system. | 1 / 3 |
Completeness | The description answers both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with 21RISK data), with an explicit 'Use when' clause providing trigger guidance. | 3 / 3 |
Trigger Term Quality | The term '21RISK' is a strong, distinctive trigger keyword that users would naturally mention. However, beyond that product name, the other terms ('data', 'records', 'workflows') are overly generic and don't include domain-specific variations or natural phrases users might say (e.g., risk assessments, safety audits, compliance checks). | 2 / 3 |
Distinctiveness Conflict Risk | The '21RISK' product name provides good distinctiveness and is unlikely to conflict with other skills. However, the generic terms 'manage data, records, and automate workflows' could overlap with other integration or data management skills if the user doesn't explicitly mention 21RISK. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid integration skill with excellent actionability and workflow clarity—every step has executable commands and the connection flow handles edge cases well. The main weaknesses are moderate verbosity (the overview section, some redundant explanations) and a monolithic structure that could benefit from splitting detailed reference material into separate files.
Suggestions
Remove or condense the '21RISK Overview' bullet list—it lists entities without any actionable guidance and wastes tokens.
Consider moving the proxy request flags table and detailed CLIENT_ACTION_REQUIRED handling into a separate reference file to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary explanation (e.g., 'SaaS platform for managing risk and compliance' and the overview section listing entities without actionable detail). The Membrane CLI instructions are reasonably efficient but could be tightened—some sections like the proxy request table and best practices repeat information Claude would already understand. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands for every step: installation, authentication, connection setup, action discovery, action execution, and proxy requests. Commands are copy-paste ready with clear flag explanations and JSON output options. | 3 / 3 |
Workflow Clarity | The multi-step connection workflow is clearly sequenced with explicit state-based branching (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR, SETUP_FAILED). There are polling/retry loops for the BUILDING state and clear instructions for what to do at each state transition, including error states. | 3 / 3 |
Progressive Disclosure | The content is structured with clear sections and headers, but it's somewhat monolithic—the proxy request reference table, best practices, and detailed connection state handling could be split into separate files. The '21RISK Overview' section listing entities adds no actionable value and takes up space without linking to anything useful. | 2 / 3 |
Total | 10 / 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 | |
- Repository
- membranedev/application-skills
- Commit
f484c82
- 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.