adroll
AdRoll integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdRoll data.
73
67%
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/adroll/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 correctly names the platform (AdRoll) and includes an explicit 'Use when' clause, which is good structurally. However, the capabilities described are extremely generic ('manage data, records, and automate workflows') and could apply to virtually any SaaS integration, failing to convey what AdRoll-specific actions are supported. It needs concrete, domain-specific actions and richer trigger terms.
Suggestions
Replace generic 'manage data, records, and automate workflows' with specific AdRoll actions like 'manage ad campaigns, create audience segments, pull retargeting performance reports, configure conversion tracking'.
Add natural trigger terms users would say, such as 'retargeting', 'ad campaigns', 'display ads', 'audience segments', 'ad performance metrics'.
Enhance distinctiveness by specifying AdRoll's niche (e.g., 'retargeting and digital advertising platform') to differentiate from other marketing/ad integrations.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'manage data, records, and automate workflows' without listing any concrete actions specific to AdRoll. It doesn't mention specific capabilities like managing ad campaigns, tracking conversions, managing audiences, or pulling performance reports. | 1 / 3 |
Completeness | It does answer both 'what' (manage data, records, automate workflows) and 'when' (when the user wants to interact with AdRoll data) with an explicit 'Use when' clause, though both parts are quite generic. | 3 / 3 |
Trigger Term Quality | It includes 'AdRoll' as a key trigger term which is specific, but lacks natural variations users might say such as 'ad campaigns', 'retargeting', 'ad performance', 'audience segments', or other AdRoll-specific terminology. | 2 / 3 |
Distinctiveness Conflict Risk | 'Manage data, records, and automate workflows' is extremely generic and could overlap with dozens of other integration skills. The only distinguishing element is the 'AdRoll' name, which helps but the rest of the description could apply to almost any SaaS integration. | 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 well-structured, actionable skill that provides clear CLI commands and a well-defined workflow with proper state handling and polling loops. Its main weaknesses are the unnecessary introductory explanation of AdRoll (which Claude already knows) and the monolithic structure that could benefit from splitting the popular actions table and detailed state handling into separate reference files.
Suggestions
Remove the opening paragraph explaining what AdRoll is — Claude already knows this. Start directly with the overview or working instructions.
Move the 'Popular actions' table to a separate reference file (e.g., ACTIONS.md) and link to it from the main skill to reduce token usage.
Remove the 'AdRoll Overview' bullet hierarchy — it's too sparse to be useful and doesn't add actionable information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explaining what AdRoll is (marketing platform, e-commerce companies, etc.) is unnecessary context Claude already knows. The Membrane CLI workflow sections are mostly efficient but could be tightened — e.g., the 'AdRoll Overview' bullet list adds little value, and some explanations like 'Membrane handles authentication and credentials refresh automatically' are slightly verbose. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready CLI commands for every step: installation, authentication, connection management, action search, action creation, and action execution. Input parameters and flags are clearly specified with examples including JSON input syntax. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced: install CLI → authenticate → ensure connection → handle connection states (with explicit state machine: BUILDING, READY, CLIENT_ACTION_REQUIRED, errors) → search actions → create if needed → run. Validation checkpoints and polling/retry loops are explicitly defined for both connections and actions. | 3 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's a fairly long monolithic document. The popular actions table and detailed connection state handling could be split into separate reference files. There are no references to external supplementary files beyond the official docs link. | 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
88db8c5
- 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.