activeprospect
ActiveProspect integration. Manage data, records, and automate workflows. Use when the user wants to interact with ActiveProspect data.
68
61%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/activeprospect/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 relies almost entirely on the 'ActiveProspect' brand name for differentiation while providing extremely vague capability descriptions. It has proper structural completeness with a 'Use when' clause, but the lack of specific actions and domain-relevant trigger terms makes it weak for skill selection among many options. The generic phrasing 'manage data, records, and automate workflows' could describe virtually any integration skill.
Suggestions
Replace vague actions with specific ActiveProspect capabilities, e.g., 'Configure LeadConduit flows, manage TrustedForm certificates, set up lead routing rules, and monitor lead delivery performance.'
Add domain-specific trigger terms users would naturally say, such as 'LeadConduit', 'TrustedForm', 'lead generation', 'consent verification', 'lead distribution', or 'lead buying/selling'.
Expand the 'Use when' clause with more specific scenarios, e.g., 'Use when the user mentions ActiveProspect, LeadConduit, TrustedForm, lead routing, or consent-based marketing workflows.'
| 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 leads', 'configure TrustedForm certificates', or 'set up LeadConduit flows' that would indicate what this skill actually does with ActiveProspect. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with ActiveProspect data) with an explicit 'Use when' clause. While the content is vague, the structural completeness requirement is met. | 3 / 3 |
Trigger Term Quality | It includes 'ActiveProspect' as a key trigger term, which is the product name users would mention. However, it lacks natural variations or related terms users might say (e.g., 'LeadConduit', 'TrustedForm', 'lead distribution', 'consent verification') that would help match real user queries. | 2 / 3 |
Distinctiveness Conflict Risk | 'ActiveProspect' as a 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. Only the brand name prevents a score of 1. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid, actionable CLI commands for interacting with ActiveProspect via Membrane, with good coverage of the full workflow from setup to execution. Its main weaknesses are the verbose introductory context and exhaustive action listing that Claude doesn't need, and the lack of explicit validation checkpoints in the workflow. The structure is adequate but could benefit from trimming unnecessary content and adding verification steps.
Suggestions
Remove or drastically shorten the introductory paragraph explaining what ActiveProspect is — Claude doesn't need industry context to use CLI commands.
Remove or collapse the full entity/action enumeration into a brief note like 'Supports Person, Event, List, Form, Campaign, and other entities — use `membrane action list --intent` to discover available actions.'
Add explicit validation checkpoints after key steps, e.g., verify connection succeeded with `membrane connection list --json` before proceeding to action discovery.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The introductory paragraph explaining what ActiveProspect is (lead acquisition platform, industries, etc.) is unnecessary context Claude doesn't need. The long enumeration of all entity types and actions adds bulk without much value since the skill already instructs to discover actions via search. However, the CLI commands themselves are reasonably concise. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready CLI commands for every step: installation, authentication, connecting, searching actions, creating actions, and running actions with parameters. Each command includes concrete flags and placeholders. | 3 / 3 |
Workflow Clarity | The workflow steps (install → authenticate → connect → discover/create → run) are present and sequenced, but there are no explicit validation checkpoints or error-handling feedback loops. The action creation section mentions polling and error states, which is good, but the overall flow lacks verification steps (e.g., confirming connection succeeded before proceeding). | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but the full list of all entity types and actions is inlined when it could be referenced externally or omitted entirely (since action discovery is built into the CLI). The skill is somewhat monolithic but not deeply nested. | 2 / 3 |
Total | 9 / 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
56d7336
- 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.