adroll
AdRoll integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdRoll data.
Install with Tessl CLI
npx tessl i github:membranedev/application-skills --skill adroll72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
67%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 adequately identifies the AdRoll integration and includes an explicit 'Use when' clause, which is good. However, it relies heavily on generic action verbs ('manage', 'automate') rather than AdRoll-specific capabilities, and lacks natural trigger terms users might actually say when needing this skill.
Suggestions
Replace generic actions with AdRoll-specific capabilities like 'manage retargeting campaigns, track ad performance, create audience segments'
Add natural trigger terms users would say such as 'retargeting', 'display ads', 'ad campaigns', 'audience targeting'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AdRoll) and mentions general actions ('Manage data, records, and automate workflows'), but these are generic actions that could apply to any integration rather than specific AdRoll capabilities like managing campaigns, audiences, or ad performance. | 2 / 3 |
Completeness | Explicitly answers both what ('Manage data, records, and automate workflows') and when ('Use when the user wants to interact with AdRoll data'), meeting the requirement for explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes 'AdRoll' as a key trigger term and 'AdRoll data', but misses natural variations users might say like 'retargeting', 'ad campaigns', 'display ads', or specific AdRoll features. | 2 / 3 |
Distinctiveness Conflict Risk | 'AdRoll' is a distinct product name which helps differentiation, but 'Manage data, records, and automate workflows' is generic language that could overlap with many other integration skills. | 2 / 3 |
Total | 9 / 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.
This skill provides solid, actionable CLI commands for AdRoll integration via Membrane with good concrete examples. However, it opens with unnecessary platform explanation, lacks validation checkpoints in workflows, and could benefit from better content organization with external references for the lengthy actions table.
Suggestions
Remove the introductory paragraph explaining what AdRoll is - Claude already knows this context
Add validation steps after connection creation (e.g., 'Verify connection: membrane connection list --json | grep CONNECTION_ID')
Move the popular actions table to a separate ACTIONS.md file and reference it from the main skill
Add error handling guidance for common failure scenarios (e.g., expired auth, invalid connection ID)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'AdRoll is a marketing platform that helps businesses...') that Claude already knows. The overview hierarchy diagram and some setup instructions could be tighter, but most content is reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable CLI commands throughout with specific flags and options. The action table, proxy request examples, and connection setup are all copy-paste ready with concrete syntax. | 3 / 3 |
Workflow Clarity | Steps for setup and connection are listed but lack explicit validation checkpoints. The workflow doesn't include error handling or verification steps (e.g., confirming connection succeeded before proceeding to actions). | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the popular actions table is quite long and could be referenced externally. No external file references are used despite the content length warranting some separation. | 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 | |
- 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.