Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

basin

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

Quality

69%

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

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 delivers strong, concrete, copy-paste-ready CLI guidance with a well-sequenced connection workflow that includes real polling and error-recovery loops. Its weaknesses are the filler "Basin Overview" section, an inlined 20-row action catalog that should live in a reference file, and a dangling "Step 2" reference that breaks the otherwise clear sequence.

Suggestions

Delete or rewrite the "Basin Overview" section — "When to use which actions: Use action names and parameters as needed" conveys no actionable information.

Move the 20-row Popular actions table to a references/ file (e.g. references/actions.md) and keep a short pointer plus a note that "membrane action list --intent" discovers the full catalog dynamically.

Fix the dangling "skip to Step 2" reference by numbering the workflow steps explicitly, and add a brief validation/confirmation guideline for destructive actions (delete form, project, submission).

Dimension	Reasoning	Score
Conciseness	Most of the body is lean, executable CLI content, but it is padded by the vacuous "Basin Overview" section ("When to use which actions: Use action names and parameters as needed"), a concept-paragraph intro, and a 20-row bulk action table, matching the anchor for mostly efficient with some unnecessary explanation that could be tightened. Not 4 because those sections are noticeably superfluous; not 2 because the core guidance is not verbose.	3 / 5
Actionability	Nearly every section gives copy-paste-ready commands ("npm install -g @membranehq/cli@latest", "membrane connection ensure \"https://usebasin.com\" --json", "membrane action run <actionId> --input '{\"key\": \"value\"}' --json") plus a proxy flag table, matching the anchor for mostly executable guidance with minor gaps. Not 5 because <actionId> is never concretely tied to the action keys in the table, and placeholders like CONNECTION_ID and QUERY are left unresolved.	4 / 5
Workflow Clarity	The install → login → connect → poll-until-READY → search → run sequence is clear and includes genuine feedback loops (state polling, CLIENT_ACTION_REQUIRED handling, error-state instructions), matching the anchor for a clear sequence with most checkpoints present. Not 5 because the text says "skip to Step 2" but no Step 2 is ever labeled, and destructive actions (delete form/project/submission) appear with no verification guidance. Not 3 because the documented workflow contains explicit checkpoints and error recovery.	4 / 5
Progressive Disclosure	Section structure is good, but the 20-row Popular actions catalog is bulk API-reference material inlined in SKILL.md that belongs in a separate reference file (or could be dropped entirely since "membrane action list --intent" discovers actions dynamically), matching the anchor for some structure with content that should be separate inline. No bundle files exist, and the under-50-lines exception does not apply to this ~160-line body.	3 / 5
	Total	14 / 20 Passed

Description

61%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 has an explicit and correctly voiced 'Use when...' trigger anchored to a distinctive product name, which gives it low conflict risk. However, the 'what' half is buzzword-level ("Manage data, records, and automate workflows") with no concrete capabilities and no natural synonyms like forms or submissions, leaving both specificity and trigger coverage weak.

Suggestions

Replace "Manage data, records, and automate workflows" with the concrete operations the skill actually supports, e.g. "List, create, update, and delete forms, submissions, projects, and webhooks in Basin".

Expand the 'Use when' clause with the natural phrases users would say: "Use when the user mentions Basin, form submissions, form backends, or wants to manage form data".

Include the file/service context (e.g. usebasin.com) so the skill triggers even when the user references Basin by domain rather than name.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Basin domain but the actions are generic buzzwords with no concrete operations (no mention of forms, submissions, webhooks, or projects), matching the anchor for naming the domain with minimal or generic actions. It is not 3 because no specific concrete action is listed, and not 1 because the domain itself is identified.	2 / 5
Completeness	Both parts are explicitly present in third person: the 'what' ("Manage data, records, and automate workflows") and the 'when' ("Use when the user wants to interact with Basin data"), matching the anchor for having both with room to be more specific. Not 5 because the 'what' is generic rather than concrete; not 3 because the 'when' clause is explicit, not merely implied.	4 / 5
Trigger Term Quality	"Basin" and "interact with Basin data" are distinctive relevant keywords, but natural variations users would actually say — forms, form backend, submissions, webhooks — are absent, matching the anchor for some relevant keywords but missing common variations or synonyms. Not 4 because the keyword set is essentially one product name with no synonyms or extensions.	3 / 5
Distinctiveness Conflict Risk	"Basin" is a unique product name and the trigger requires it ("interact with Basin data"), giving a clear niche with distinct triggers and minimal risk of firing for the wrong skill.	5 / 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
Revision: f484c82

Reviewed: 16 days ago

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.

basin

Table of Contents

Is this your skill?