agencyzoom
AgencyZoom integration. Manage Organizations, Leads, Users, Goals, Filters. Use when the user wants to interact with AgencyZoom data.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/agencyzoom/SKILL.mdQuality
Discovery
75%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 effectively identifies a clear niche (AgencyZoom integration) and includes an explicit 'Use when' clause, making it complete and distinctive. However, it lacks specificity in the actions it can perform ('Manage' is too broad) and could benefit from more natural trigger terms that users might use when requesting AgencyZoom-related tasks.
Suggestions
Replace the vague 'Manage' with specific actions like 'Create, update, search, and delete Organizations, Leads, Users, Goals, and Filters'.
Add natural trigger terms users might say, such as 'CRM', 'insurance agency management', 'pipeline', or 'AgencyZoom API'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AgencyZoom) and lists entity types (Organizations, Leads, Users, Goals, Filters), but 'Manage' is vague—it doesn't specify concrete actions like create, update, delete, search, or export. | 2 / 3 |
Completeness | Answers both 'what' (manage Organizations, Leads, Users, Goals, Filters in AgencyZoom) and 'when' (Use when the user wants to interact with AgencyZoom data), with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes 'AgencyZoom' as a strong trigger term and entity names like 'Organizations', 'Leads', 'Users', 'Goals', 'Filters', but misses natural variations users might say such as 'CRM', 'insurance agency', 'pipeline', or specific action-oriented terms. | 2 / 3 |
Distinctiveness Conflict Risk | AgencyZoom is a specific product name, making this highly distinctive and unlikely to conflict with other skills. The trigger is clearly scoped to AgencyZoom interactions. | 3 / 3 |
Total | 10 / 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—the CLI commands are concrete and the connection state machine is well-documented with clear branching logic. The main weaknesses are some unnecessary introductory context about AgencyZoom (Claude doesn't need to know what a CRM is or what insurance agents do) and the lack of progressive disclosure through supporting bundle files for the action reference table and proxy documentation.
Suggestions
Remove the introductory paragraph explaining what AgencyZoom is and what insurance agents use it for—Claude already knows this and it wastes tokens.
Remove or significantly trim the 'AgencyZoom Overview' bullet hierarchy section, which adds no actionable value.
Consider extracting the popular actions table and proxy request details into separate reference files to improve progressive disclosure and keep the main SKILL.md focused on the core workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what AgencyZoom is and what insurance agents use it for is unnecessary context for Claude. The overview hierarchy section adds little value. However, the CLI commands and action table are reasonably efficient. | 2 / 3 |
Actionability | The skill provides fully executable CLI commands for authentication, connection setup, action discovery, action execution, and proxy requests. Commands are copy-paste ready with clear parameter placeholders and the popular actions table gives concrete action keys. | 3 / 3 |
Workflow Clarity | The connection workflow is clearly sequenced with explicit state checks (READY, BUILDING, CLIENT_ACTION_REQUIRED, errors), polling instructions, and branching logic for different states. The authentication flow handles both interactive and headless environments with clear steps. | 3 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear sections, but it's all in a single monolithic file with no bundle files for reference. The popular actions table and proxy request documentation could be split into separate reference files to keep the main skill leaner. | 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.