CtrlK
BlogDocsLog inGet started
Tessl Logo

plaid-fintech

Create a linktoken for Plaid Link, exchange publictoken for accesstoken. Link tokens are short-lived, one-time use. Access tokens don't expire but may need updating when users change passwords.

43

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-bundle-commerce-payments/skills/plaid-fintech/SKILL.md

The canonical home for this skill is plaid-fintech in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

18%Scale 1-5

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

This skill is essentially a skeleton or template with no actionable content. It names relevant Plaid concepts (link tokens, transaction sync, item errors) but provides zero executable guidance — no code examples, no API call structures, no concrete parameters, and no real workflow steps. The Sharp Edges table is entirely placeholder text, and the 'When to Use' section is a meaningless tautology.

Suggestions

Add concrete, executable code examples for the core workflow: creating a link_token via POST /link/token/create with required parameters, and exchanging a public_token via POST /item/public_token/exchange.

Replace the placeholder Sharp Edges table with actual Plaid-specific issues (e.g., sandbox vs production environment differences, rate limits, webhook signature verification) with real solutions.

Add a numbered step-by-step workflow for the link token → public token → access token flow, including validation steps (e.g., checking response status, handling error codes like INVALID_PUBLIC_TOKEN).

Either populate the anti-patterns with brief explanations of why they're harmful and what to do instead, or remove them to save tokens.

DimensionReasoningScore

Conciseness

The content is relatively brief but includes placeholder/template content (the Sharp Edges table with generic 'Issue' and 'See docs' entries) and a tautological 'When to Use' section that wastes tokens. The anti-patterns section lists items without any explanation, which is lean but unhelpfully so.

3 / 5

Actionability

There is no executable code, no concrete commands, no API endpoints with parameters, no example requests/responses. Every section is abstract description — 'Create a link_token,' 'Use /transactions/sync,' 'Handle ITEM_LOGIN_REQUIRED errors' — without showing how to actually do any of it. The Sharp Edges table contains only placeholder text ('Issue', 'See docs').

1 / 5

Workflow Clarity

There is no sequenced workflow. The link token creation and exchange process (create link_token → user completes Link → exchange public_token for access_token) is described in a single sentence without steps, validation, or error handling. No checkpoints or feedback loops exist anywhere.

1 / 5

Progressive Disclosure

The content has some section structure (Patterns, Anti-Patterns, Sharp Edges) but no references to any external files, no links to documentation, and the Sharp Edges table just says 'See docs' without specifying which docs. There are no bundle files to support the content. The anti-patterns are listed as headers with no body content.

2 / 5

Total

7

/

20

Passed

Description

70%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 reasonably specific about Plaid Link token operations and includes useful lifecycle details about token behavior. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are domain-specific and distinctive but could benefit from more natural user-facing language.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to integrate Plaid, connect a bank account, or exchange Plaid tokens.'

Include natural user-facing synonyms like 'connect bank account', 'Plaid integration', 'bank linking', or 'financial data access' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Lists several specific actions: creating a link token, exchanging public token for access token. Also mentions token lifecycle details (short-lived, one-time use, non-expiring access tokens, password change scenarios). Minor gaps—doesn't mention other Plaid operations like retrieving accounts or transactions.

4 / 5

Completeness

The 'what' is clearly stated (create link tokens, exchange tokens), with useful lifecycle context. However, there is no explicit 'when' clause or trigger guidance (e.g., 'Use when...'). Per rubric guidelines, missing 'Use when...' caps completeness at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'Plaid Link', 'linktoken', 'publictoken', 'accesstoken', and 'Plaid'. However, it's missing some natural user phrases like 'connect bank account', 'Plaid integration', 'bank linking', or 'financial data' that users might naturally say.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive—Plaid Link token creation and public-to-access token exchange is a very specific niche. The mention of 'Plaid Link', 'linktoken', 'publictoken', and 'accesstoken' makes it clearly distinguishable from other skills with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

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.