Name: mparticle
Rating: 53.6 (1 reviews)
Author: membranedev

mparticle

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

Quality

60%

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/mparticle/SKILL.md

Quality

Content

57%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 strong, actionable CLI integration guide with a clear connection workflow and feedback loops, but it is weakened by marketing padding, missing validation for destructive data operations, and a monolithic structure with no progressive disclosure to separate reference files.

Suggestions

Remove the marketing/background opening paragraph and filler lines so the body assumes Claude's competence and starts with the integration workflow.

Add validation/verification steps around action runs and proxy mutating requests (e.g. inspect outputSchema before running, verify the output field, dry-run or confirm before batch/DELETE).

Move the resource overview list and the proxy flag reference table into separate reference files and link to them from SKILL.md to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient CLI guidance, but the opening marketing paragraph ("MParticle is a customer data platform... used by marketing, product, and engineering teams to improve customer experiences and drive growth") is background padding Claude does not need, plus filler like "Use action names and parameters as needed."	3 / 5
Actionability	Concrete executable commands throughout (install, login, connection ensure, action list/run, proxy with a full flag table), but minor gaps remain: inconsistent `membrane` vs `npx @membranehq/cli` invocation, a repeated `action list` command, and placeholders like CONNECTION_ID never shown in a worked example.	4 / 5
Workflow Clarity	The install→auth→connect→search→run sequence is clear with good feedback loops for the connection state machine, but the core data-manipulation steps (running actions, proxying POST/PUT/PATCH/DELETE) include no validation or verification; per the destructive/batch cap this cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and the ~150-line body is entirely inline; it is well-sectioned, but reference-like content (the resource overview list, full connection state-machine, proxy flag table) is inlined rather than split into separate files, and no external references are signaled.	3 / 5
	Total	13 / 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 correctly pairs a what with an explicit Use-when trigger anchored on a distinct brand name, but its action language is generic and it lacks the broader domain vocabulary that would make triggers comprehensive. It is solid but not exemplary.

Suggestions

Replace generic verbs with concrete MParticle operations, e.g. "ingest events, manage audiences, resolve identities, and sync records".

Expand the trigger clause with natural variations users say, e.g. "Use when the user wants to send events, build audiences, or manage user identities in MParticle."

Add file-format or API synonyms where relevant (e.g. mParticle API, customer data platform) to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the MParticle domain and a few actions ("Manage data, records, and automate workflows"), but the verbs are generic (manage, automate) rather than concrete operations, so it does not reach the specific-action coverage of level 4.	3 / 5
Completeness	It states both a what ("MParticle integration. Manage data, records, and automate workflows.") and an explicit when ("Use when the user wants to interact with MParticle data."), but the when is a single generic trigger rather than the multiple concrete trigger phrases required for level 5.	4 / 5
Trigger Term Quality	"MParticle" is a strong natural brand keyword, but beyond it only generic terms (data, records, workflows) appear; common domain vocabulary like events, audiences, identity resolution, or CDP is missing.	3 / 5
Distinctiveness Conflict Risk	"MParticle" is a distinct named product giving a clear niche with low conflict risk, but the generic action phrasing leaves minor overlap risk with adjacent data-management skills, stopping short of level 5.	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/mparticle/SKILL.md
Commit: f484c82

Reviewed: 5 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.