Name: mediamath
Rating: 52 (1 reviews)
Author: membranedev

mediamath

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

Quality

58%

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/mediamath/SKILL.md

Quality

Content

51%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 gives solid executable CLI guidance for connecting to and calling MediaMath, but it is bloated by a massive inlined list of resource names that should live in a separate reference file, and it over-explains auth concepts. Workflow sequencing is good though it lacks an explicit pre-action validation checkpoint.

Suggestions

Move the long list of MediaMath resource/entity names into a dedicated references file (e.g. references/resources.md) and link to it from a short overview section.

Trim explanatory prose about Membrane handling auth/refresh and what a DSP is, which Claude already knows, to tighten token usage.

Add an explicit validation checkpoint (e.g. confirm connection state is READY and verify action inputSchema) before running actions or proxy requests.

Dimension	Reasoning	Score
Conciseness	A ~140-line wall of inlined resource/entity names and padded explanations of Membrane/auth concepts Claude largely already knows makes the body noticeably verbose and token-heavy.	2 / 5
Actionability	Concrete, executable CLI commands (install, login, connection ensure/get, action list/run, request) with flag tables make the guidance mostly copy-paste ready with only minor gaps.	4 / 5
Workflow Clarity	The connection flow is sequenced with state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED) and poll/retry loops, though it lacks an explicit validation checkpoint before running actions.	4 / 5
Progressive Disclosure	The huge inlined resource/entity list (~140 items) clearly belongs in a separate reference file, and there are no bundle files to offload it; structure is minimal rather than appropriately split.	2 / 5
	Total	12 / 20 Passed

Description

65%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 distinctive and includes an explicit 'Use when' trigger, but its action list ('manage data, records, automate workflows') is generic and could be much more specific to MediaMath's actual capabilities. Keyword coverage relies almost entirely on the brand name rather than natural domain phrases.

Suggestions

Replace generic verbs ('manage data, records') with concrete MediaMath actions like 'create and manage campaigns, strategies, tactics, audiences, and pixels'.

Add natural trigger phrases a user would say, e.g. 'Use when the user wants to manage MediaMath ad campaigns, build audiences, or pull performance reports'.

Reference key domain terms (campaigns, DSP, programmatic, reporting) so the skill triggers on natural language rather than only the brand name.

Dimension	Reasoning	Score
Specificity	Names the domain and a few concrete actions ('Manage data, records, and automate workflows'), but these are generic and not a comprehensive, specific action list like the score-5 anchor.	3 / 5
Completeness	It states what it does (MediaMath integration, manage data/records/automate workflows) and provides an explicit 'Use when the user wants to interact with MediaMath data' clause; the 'when' could be more specific about campaign/ad tasks.	4 / 5
Trigger Term Quality	It surfaces the key term 'MediaMath' and 'interact with MediaMath data', but lacks common natural synonyms or variations a user would say (e.g., campaigns, ad buying, DSP); keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The MediaMath brand name is a strong, distinctive trigger with minimal overlap risk against other skills, fitting the clear-niche anchor.	5 / 5
	Total	15 / 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/mediamath/SKILL.md
Commit: f484c82

Reviewed: 6 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.