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

Blog Docs Log in Get started

xendit

Xendit integration. Manage data, records, and automate workflows. Use when the user wants to interact with Xendit 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/xendit/SKILL.md

Quality

Content

68%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 solid, mostly executable CLI guide with good section structure and runtime-based discovery instead of an inlined API reference. Its weaknesses are confusing step numbering in the connection workflow and missing validation/verification steps for destructive payment-API operations, which caps workflow clarity.

Suggestions

Add a verification/error-handling step after running actions and proxy requests (e.g., check the `output`/error field and confirm before destructive POST/DELETE).

Fix the step numbering: label the post-connection step explicitly as "Step 2" or restructure so "1b" and "Step 2" align.

De-duplicate the action-list command between "Searching for actions" and "Popular actions" to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean code blocks with brief prose, but contains minor trimmable fluff ("so you can focus on the integration logic rather than auth plumbing", "This is the fastest way to get a connection") and a redundant restatement of the action-list command in "Popular actions".	4 / 5
Actionability	It provides concrete, copy-pasteable commands throughout (install, login, connection ensure, action run, request) plus a flags table, but examples rely on unresolved placeholders (CONNECTION_ID, <agentType>) with no fully resolved end-to-end example.	4 / 5
Workflow Clarity	The connection flow is sequenced with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED), but the action-running and proxy workflows against a payment API lack validation/verification steps, and the "Step 2" reference and "1b" numbering are confusingly labeled.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections and avoids inlining a huge API reference by deferring to runtime `membrane action list` discovery, though "Searching for actions" and "Popular actions" overlap and the file has no separate reference files despite exceeding 50 lines.	4 / 5
	Total	15 / 20 Passed

Description

57%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 includes an explicit Use-when trigger and names the Xendit brand, giving it adequate completeness and distinctiveness. Its main weakness is vague, non-concrete action language and thin trigger-term coverage that omits the natural payment-related terms users would actually say.

Suggestions

Replace generic verbs with concrete Xendit operations, e.g. "Create and send invoices, manage payouts, and check balances."

Add natural trigger keywords users say, such as "payments", "invoices", "payouts", or "Xendit transactions".

Tighten the when clause to reference specific intents, e.g. "Use when the user wants to accept payments or send payouts via Xendit."

Dimension	Reasoning	Score
Specificity	Names the domain ("Xendit integration") but the actions are generic — "Manage data, records, and automate workflows" are abstract with no concrete Xendit operations like creating invoices or sending payouts.	2 / 5
Completeness	It has an explicit "Use when the user wants to interact with Xendit data" trigger and a stated what ("Manage data, records, and automate workflows"), but both are generic and could be more specific, fitting the "has both what and when; when could be more explicit" anchor.	4 / 5
Trigger Term Quality	"Xendit" and "Xendit data" are relevant brand keywords a user would say, but common natural variations (payments, invoices, payouts) are missing, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The named brand "Xendit" gives it a clear niche with minimal wrong-skill triggering, but the generic action vocabulary ("manage data, records, automate workflows") mirrors sibling Membrane integration skills, leaving minor overlap risk.	4 / 5
	Total	13 / 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/xendit/SKILL.md
Commit: f484c82

Reviewed: 3 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.