CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

59%

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/AI-Agents-Safe-Coding-Skills/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

36%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 has a sensible section skeleton but is largely a shell: empty anti-pattern sections, a placeholder-only Sharp Edges table, and no code or executable guidance anywhere. Claude reading it would learn which Plaid concepts matter but not how to perform any of the operations.

Suggestions

Replace the placeholder Sharp Edges table with real issues and concrete solutions (e.g., actual error codes, retry logic, or links to specific reference files), and populate the Anti-Patterns sections with what to do instead.

Add executable examples for the core flow: a sample /link/token/create request and a public_token-to-access_token exchange with key parameters.

Turn the Patterns into an ordered workflow (create token → initialize Link → exchange token → fetch data) with a validation step for error responses like ITEM_LOGIN_REQUIRED, and replace the 'When to Use' boilerplate with concrete applicability conditions.

DimensionReasoningScore

Conciseness

The body is terse and does not over-explain concepts Claude knows, but it carries noticeable wasted tokens: Pattern 1 repeats the frontmatter description verbatim, the Sharp Edges table has 8 placeholder rows ('Issue | critical | See docs') that convey nothing, and the 'When to Use' section is generic boilerplate. This fits 'mostly efficient but includes some unnecessary content that could be tightened' rather than the lean anchor 5 or the padded anchor 2.

3 / 5

Actionability

The patterns name real API concepts ('/transactions/sync', 'ITEM_LOGIN_REQUIRED', 'PENDING_DISCONNECT webhook') but give only high-level hints with no executable steps, request examples, parameters, or error-handling code — matching 'minimal concrete guidance; high-level hints but missing the specific steps to execute'. The Anti-Patterns sections contain headings with zero content and every Sharp Edges solution is the placeholder 'See docs', so it cannot reach anchor 3's 'some concrete guidance'.

2 / 5

Workflow Clarity

A rough flow is implied (create link_token, run Link, exchange public_token, call APIs) but no steps are sequenced, no validation checkpoints exist for the token-exchange and update-mode flows, and error-recovery guidance is reduced to 'See docs'. This sits between 'steps missing' (1) and 'steps listed but validation gaps' (3), closer to the anchor for a rough sequence with many gaps and absent validation.

2 / 5

Progressive Disclosure

The body has clear top-level sections (Patterns, Anti-Patterns, Sharp Edges, When to Use) with no nested references, but the Sharp Edges solutions point to 'See docs' — an unsignaled, non-existent destination — and no references/, scripts/, or assets/ directories exist, so navigation to detail is broken. This matches 'some structure but could be better organized; references present but not clearly signaled' rather than the well-organized anchor 4/5.

3 / 5

Total

10

/

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 distinct and appropriately terse, naming the Plaid niche and two concrete token-lifecycle actions, but it omits any 'Use when...' trigger guidance and misses several capabilities the body covers (transactions sync, webhooks, item error handling). Adding an explicit trigger clause and one or two more actions would raise completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. 'Use when integrating Plaid Link, exchanging Plaid tokens, or syncing bank account transactions.'

Mention one or two more concrete capabilities (e.g., /transactions/sync, ITEM_LOGIN_REQUIRED handling) so coverage matches the body content.

DimensionReasoningScore

Specificity

The description names the domain (Plaid Link) and exactly two concrete actions — 'Create a linktoken for Plaid Link, exchange publictoken for accesstoken' — which matches the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage (no mention of transactions, webhooks, or item error handling covered in the body). It is not a 4 because only two actions are listed, and not a 2 because those actions are specific rather than generic.

3 / 5

Completeness

The 'what' is clear (token creation and exchange) but there is no 'Use when...' clause or any equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than merely vague, and not a 2 because the 'what' half is concrete and specific.

3 / 5

Trigger Term Quality

Strong natural keywords for the niche — 'Plaid Link', 'link token', 'public token', 'access token', and 'users change passwords' — which are phrases a developer working with Plaid would actually say. It is not a 5 because common variations like 'bank accounts', 'financial data', 'fintech', or 'transactions' are missing, and not a 3 because the core terms go well beyond a generic domain mention.

4 / 5

Distinctiveness Conflict Risk

Plaid is a uniquely named third-party service and the token lifecycle terminology is unambiguous, giving a clear niche with distinct triggers and minimal conflict risk with other skills. No neighboring anchor fits better since generic overlap is essentially zero.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/plaid-fintech/SKILL.md

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.