Name: the-trade-desk
Rating: 55.2 (1 reviews)
Author: membranedev

the-trade-desk

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

Quality

63%

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/the-trade-desk/SKILL.md

Quality

Content

63%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 content is a well-organized, command-rich integration guide with a strong connection workflow including polling and state-handling checkpoints. It is held back by minor verbosity/redundancy and by being a single monolithic file rather than splitting detailed reference material into separate files.

Suggestions

Tighten or remove explanatory padding such as 'so you can focus on the integration logic rather than auth plumbing' and consolidate the repeated membrane/npx CLI invocation forms into one canonical pattern.

Move the detailed proxy flag reference and the connection-state handling into a separate references file (e.g. REFERENCES.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit error-recovery step for action runs (e.g., how to inspect the output/error field and retry), turning the action workflow into a validate-then-retry feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly command- and table-driven and reasonably lean, but includes some removable explanation ('so you can focus on the integration logic rather than auth plumbing'), a brief platform primer Claude largely knows, and repeated CLI invocation variants (membrane vs npx @membranehq/cli) that could be tightened — fitting 'mostly efficient but with some unnecessary explanation'.	3 / 5
Actionability	Concrete, copy-paste-ready commands are provided throughout (install, login, connection ensure with --json, action run, proxy with a full flag table), covering the common cases; minor gaps remain in the form of unfilled placeholders (CONNECTION_ID, <actionId>, 'QUERY'), placing it just below fully executable across all cases.	4 / 5
Workflow Clarity	The connection setup is a clear sequence with explicit validation checkpoints — --wait polling, state branching (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), and re-poll after user action — which provides feedback loops; it is not a 5 because the action-running and proxy sections lack an explicit error-recovery checklist.	4 / 5
Progressive Disclosure	No bundle files exist and all content lives in a single ~145-line SKILL.md with good section headers, but nothing is split out to references and no external file pointers are signaled; this matches 'some structure but content that could be separate is inline', and the size exceeds the under-50-line simple-skill exception.	3 / 5
	Total	14 / 20 Passed

Description

62%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 successfully pairs a what-statement with an explicit 'Use when' trigger and anchors the skill to a distinct named platform. Its main weakness is generic action verbs and a single, somewhat vague trigger phrase rather than concrete, varied trigger terms.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete capabilities specific to The Trade Desk (e.g., 'manage campaigns, line items, and creatives; run and schedule reports').

Expand the trigger clause with natural variations users say, e.g., 'Use when the user wants to manage The Trade Desk campaigns, ad groups, line items, creatives, or reports.'

Dimension	Reasoning	Score
Specificity	Names the domain (The Trade Desk) plus a few action verbs ('Manage data, records, and automate workflows'), but the actions ('manage', 'automate') are generic rather than concrete, comprehensive operations — matching the anchor that lists 1-2 concrete actions but is not comprehensive.	3 / 5
Completeness	Both 'what' (manage data, records, automate workflows) and an explicit 'when' clause are present; the 'when' is explicit but somewhat generic ('interact with The Trade Desk data'), matching the anchor where both exist but the 'when' could be more specific — not a 5 because the trigger phrases are not concrete and varied.	4 / 5
Trigger Term Quality	The trigger 'Use when the user wants to interact with The Trade Desk data' includes the natural proper-noun keyword users would say, but offers only one phrasing with no synonyms or variations, fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Tying the skill to the named platform 'The Trade Desk' gives it a clear niche with minimal conflict risk against unrelated skills; it is not a 5 only because the generic 'data, records' language leaves minor overlap with other data-management skills.	4 / 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/the-trade-desk/SKILL.md
Commit: f484c82

Reviewed: 4 days ago

Table of Contents

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.