Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

adroll

AdRoll integration. Manage data, records, and automate workflows. Use when the user wants to interact with AdRoll data.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/adroll/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, command-first operational guide with good connection-state branching and a solid actions catalog. Its weaknesses are modest padding in the intro and best-practices prose, a missing worked action example, and broken 'Step 2' cross-references that slightly disrupt the workflow sequence.

Suggestions

Cut the opening paragraph describing what AdRoll is and the filler line "Use action names and parameters as needed"; Claude does not need the platform's marketing background, only the operational commands.

Add one worked end-to-end example, e.g. `membrane action run get-campaign-report --connectionId=... --input '{"advertisable": "EID", "startDate": "2026-10-01", "endDate": "2026-10-28"}' --json`, so parameter shape and output handling are unambiguous.

Fix the dangling "skip to **Step 2**" references by numbering the workflow steps explicitly (1. Connect, 2. Search for actions, 3. Run actions), and add a brief note on handling errors returned in action run output.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command-driven content, but it includes unnecessary padding: the opening paragraph explaining what AdRoll is ("AdRoll is a marketing platform that helps businesses run advertising campaigns across different channels..."), the filler line "Use action names and parameters as needed", and grammatically sloppy best-practice prose ("This will burn less tokens"). Fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not 4 because the marketing-platform explainer is background Claude does not need.	3 / 5
Actionability	Concrete, copy-paste-ready commands cover install, login (including headless completion), connection setup, state polling, action search, action run, and proxy requests, plus a flags table. Not 5 because there is no worked example invoking a real action with actual parameters (e.g., get-campaign-report with an EID and date range).	4 / 5
Workflow Clarity	The install → login → connect → poll/branch → search → run sequence is clear, with a genuine feedback loop for connection readiness (CLIENT_ACTION_REQUIRED → user acts → poll again) and error states pointing to the error field. Not 5 because the text says "skip to Step 2" but no Step 2 heading exists, and there is no guidance on validating or handling errors in action run output.	4 / 5
Progressive Disclosure	A single well-sectioned ~155-line file with clear headers, a popular-actions table, and a proxy options table; no bundle files exist so all content is appropriately inline at overview level. Not 5 because the under-50-lines exception does not apply and the actions table / proxy details could plausibly be split into a reference file.	4 / 5
	Total	15 / 20 Passed

Description

61%Weight 40%Scale 1-5

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 is distinct and has an explicit 'Use when' clause, but its capability statement is generic. Naming the concrete AdRoll objects and operations (campaigns, ad groups, ads, segments, reports) would improve both specificity and trigger coverage.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with concrete AdRoll capabilities, e.g. "Retrieve campaign, ad group, and ad performance reports; list and manage advertisables, ads, and audience segments; send requests to the AdRoll API via a managed proxy."

Expand the 'Use when' clause with natural trigger phrases users would actually say, such as "Use when the user mentions AdRoll, their ad campaigns, ad groups, audience segments, or advertisable/report data."

Drop the vague filler terms "data" and "records" in favor of AdRoll-specific vocabulary (advertisables, segments, EIDs), which doubles as trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the AdRoll domain but the actions are generic; no concrete AdRoll capabilities (campaigns, ad groups, ads, segments, reports) are stated. It matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions.	2 / 5
Completeness	Both a 'what' ("Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with AdRoll data") are present. Not 3 because the 'when' is explicit rather than weakly implied; not 5 because the 'what' is vague and the 'when' lacks concrete trigger phrases.	4 / 5
Trigger Term Quality	The dominant natural term "AdRoll" is present, but common variations users would say ("campaigns", "ads", "ad groups", "segments", "reports") are absent. Fits 'Some relevant keywords but missing common variations or synonyms'; not 4 because the only genuine trigger term is the brand name.	3 / 5
Distinctiveness Conflict Risk	"AdRoll" is a clear niche with distinct triggers, and the 'Use when' clause is scoped specifically to AdRoll data, giving minimal conflict risk with other skills.	5 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/adroll/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

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.

adroll

Table of Contents

Is this your skill?