Name: basin
Rating: 58.4 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

basin

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

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/basin/SKILL.md

Quality

Content

72%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 copy-paste CLI commands and a strong connection-state feedback loop, but it documents destructive actions without validation checkpoints and inlines a large action catalog that would benefit from a separate reference file. Adding pre-delete verification guidance and splitting the action reference would raise the weakest dimensions.

Suggestions

Add a validation/verification checkpoint before destructive actions, e.g. confirm the target form/submission ID and run a get/list to verify before 'membrane action run' on a delete action.

Move the 20-row 'Popular actions' table into a separate reference file (e.g. ACTIONS.md) and link to it from a short overview, keeping only a few representative examples inline.

Trim minor padding such as the 'form backend as a service' definition and the 'focus on integration logic rather than auth plumbing' aside.

Dimension	Reasoning	Score
Conciseness	Largely lean and executable with command tables and flags, but has minor trimmable padding such as the 'form backend as a service' intro sentence and 'so you can focus on the integration logic rather than auth plumbing'; not anchor 5 due to these small over-explanations.	4 / 5
Actionability	Provides fully executable, copy-paste-ready CLI commands with real flags and placeholders (e.g. 'membrane action run <actionId> --connectionId=CONNECTION_ID --json') plus a complete proxy options table covering the common cases.	5 / 5
Workflow Clarity	The connection flow has an explicit state-by-state feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR with re-polling), but destructive actions (Delete Form/Project/Submission) are documented with no validation or verification checkpoint, which caps workflow clarity at 3 per the destructive-operation guideline.	3 / 5
Progressive Disclosure	No bundle/reference files exist and the body is a single ~160-line file; the 20-row 'Popular actions' catalog is bulk that would naturally belong in a separate reference file but is inlined, so structure is present but content that should be split out is not.	3 / 5
	Total	15 / 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 answers both 'what' and 'when' with a named, distinct niche, but its action list is generic and it lacks the natural form/submission trigger terms a user would actually say. Strengthening it with concrete Basin capabilities and form-related triggers would lift specificity and trigger quality.

Suggestions

Replace generic verbs with concrete Basin capabilities, e.g. 'Collect form submissions, manage forms and projects, configure form webhooks'.

Add natural trigger terms users actually say — 'forms', 'form submissions', 'form backend' — to the 'Use when' clause.

Make the trigger more specific, e.g. 'Use when the user wants to collect or manage form submissions, forms, or webhooks in Basin'.

Dimension	Reasoning	Score
Specificity	Names the Basin domain and lists several actions ('Manage data, records, and automate workflows'), but the actions are generic ('manage data', 'automate workflows') rather than concrete Basin-specific capabilities like form submissions or webhooks.	3 / 5
Completeness	Provides both a clear 'what' ('Basin integration. Manage data, records, and automate workflows.') and an explicit 'when' ('Use when the user wants to interact with Basin data'), though the 'when' clause is somewhat generic and could be more specific.	4 / 5
Trigger Term Quality	Includes relevant keywords ('Basin', 'data', 'records', 'workflows') and a usable trigger phrase, but omits the natural terms users would actually say for a form backend ('forms', 'submissions', 'form backend'), so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	The named 'Basin integration' niche and 'interact with Basin data' trigger are mostly distinct with only minor overlap risk against other data-integration skills; not anchor 5 because 'manage data/records/workflows' is broad phrasing.	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/basin/SKILL.md
Commit: f484c82

Reviewed: ~2 hours 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.