Name: plaid
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

plaid

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

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/plaid/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 body is highly actionable with executable Membrane CLI commands and a state-driven connection workflow, but it carries explanatory padding about Plaid itself and keeps everything in one monolithic file rather than splitting detail into referenced files.

Suggestions

Remove the introductory paragraph defining what Plaid is and the 'burn less tokens' rationale; assume Claude's knowledge and keep only integration guidance.

Fix the step numbering so 'Step 2' and '1b' resolve to clearly labeled, sequential headings.

Extract the proxy options table and clientAction state reference into a separate REFERENCE.md and link to it one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Most of the CLI workflow is tight and command-driven, but the opening 'Plaid is a service that enables applications to connect to users' bank accounts...' paragraph explains a concept Claude already knows, and phrases like 'This will burn less tokens' add padding.	3 / 5
Actionability	It supplies copy-paste-ready commands (npm install, membrane login, connection ensure, action list/run, request) and a full proxy-options table, with only minor gaps such as placeholder CONNECTION_ID and the circular 'discover via action list' guidance in Popular actions.	4 / 5
Workflow Clarity	The connect-to-poll-to-run sequence is clearly ordered with state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED) and a poll-again feedback loop, but references to 'Step 2' and an oddly numbered '1b' heading introduce minor structural gaps.	4 / 5
Progressive Disclosure	Section headers organize the body, but at ~160 lines all content is inlined with no bundle files and no one-level-deep references; the proxy options table and clientAction state detail would be clearer split into separate reference files.	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 correctly pairs a 'what' with an explicit 'Use when' trigger and anchors on a distinctive proper noun, but its action list is generic and it lacks the natural synonyms (bank accounts, transactions, payments) that would sharpen triggering.

Suggestions

Replace generic verbs with concrete Plaid actions, e.g. 'Link bank accounts, fetch transactions, verify identity, and retrieve balances'.

Add natural trigger keywords users actually say, such as 'bank accounts, transactions, payments, account verification'.

Tighten the 'when' clause to name the specific intents, e.g. 'Use when the user wants to connect to bank accounts or retrieve transaction/payment data via Plaid'.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Plaid domain alongside a couple of action verbs, but the actions are generic rather than concrete like the score-4 anchor's 'fills forms, converts pages'.	3 / 5
Completeness	Both a 'what' ("Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with Plaid data") are present, but the when is generic rather than listing concrete trigger phrases, so it stops short of 5.	4 / 5
Trigger Term Quality	It surfaces the keyword "Plaid" and a "Use when the user wants to interact with Plaid data" trigger, but misses natural synonyms a user might say such as bank accounts, transactions, or payments.	3 / 5
Distinctiveness Conflict Risk	Naming the proper noun "Plaid" carves out a clear niche with low conflict risk, though the generic "Manage data, records" phrasing leaves minor overlap risk with other data-integration 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/plaid/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.