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

swell

Swell integration. Manage Organizations, Pipelines, Users, Filters. Use when the user wants to interact with Swell data.

Quality

68%

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/swell/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 highly actionable with concrete, copy-paste CLI commands and a strong connection state machine, but it is padded with marketing/vague material and lacks validation checkpoints for the destructive proxy and action-run operations.

Suggestions

Trim the marketing intro and the vague Swell Overview bullet hierarchy; keep only domain context Claude lacks.

Add an explicit verify/validate step after `membrane action run` and `membrane request` (e.g. check the `output`/response status before declaring success) to lift workflow clarity above the destructive-operation cap.

Fix the "Step 2" cross-reference by numbering the post-connection sections consistently, and remove the duplicate action-list command in "Popular actions".

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient concrete commands and a flags table, but it carries unnecessary padding — the marketing intro ("to improve their online reputation and customer experience"), "so you can focus on the integration logic rather than auth plumbing", and the vague Swell Overview bullet hierarchy — fitting "mostly efficient but includes some unnecessary explanation" rather than the lean score 4.	3 / 5
Actionability	It provides copy-paste-ready executable commands for the full path (install, login, connection ensure, connection get --wait, action list/run, request) plus a concrete proxy-flags table, matching "fully executable; copy-paste ready; specific examples cover the common cases."	5 / 5
Workflow Clarity	The connection-readiness state machine (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR with a poll-again loop) is well sequenced, but the proxy and action-run steps support destructive methods (POST/PUT/PATCH/DELETE) with no validation/verification checkpoint, and the "Step 2" reference is unlabeled; the missing-validation cap for destructive operations holds this at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is organized into clear headed sections with no nested/deep references, fitting "good structure; most content appropriately placed; minor organization gaps" rather than 5 given the redundant "Popular actions" command repeat and the odd Swell Overview hierarchy.	4 / 5
	Total	15 / 20 Passed

Description

67%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 covers both what and when with a named platform and several concrete managed entities, but its trigger language is thin and generic, omitting the natural domain terms (reviews, surveys, web chat) a user would actually say.

Suggestions

Add concrete trigger phrases users naturally say, e.g. "Use when the user mentions Swell reviews, surveys, web chat, or customer feedback."

Replace the single verb "Manage" with a few distinct concrete actions (e.g. create, list, update, filter) to lift specificity toward 5.

Tie the managed entities to the platform's real domain so the trigger is less generic and conflict risk drops.

Dimension	Reasoning	Score
Specificity	The phrase "Manage Organizations, Pipelines, Users, Filters" lists several concrete entity-level actions, matching the "lists several specific actions; minor gaps" anchor rather than the 1-2 actions of score 3 or the fully comprehensive coverage of score 5.	4 / 5
Completeness	It states both a clear "what" ("Swell integration. Manage Organizations, Pipelines, Users, Filters.") and an explicit "when" ("Use when the user wants to interact with Swell data."), but the "when" is broad rather than concrete trigger phrases, matching score 4 not the fully concrete triggers of score 5.	4 / 5
Trigger Term Quality	It offers "interact with Swell data" / "Swell" as keywords but omits the natural domain terms users actually say (reviews, surveys, web chat), matching the "some relevant keywords but missing common variations" anchor; not a 2 because "Swell" is a concrete, named trigger rather than fully generic.	3 / 5
Distinctiveness Conflict Risk	The named platform "Swell" gives a distinct niche with low conflict risk, but the generic entity names (Organizations, Users, Filters) and broad "interact with Swell data" trigger create minor overlap risk, fitting "mostly distinct; minor overlap risk" rather than the minimal-risk score 5.	4 / 5
	Total	15 / 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/swell/SKILL.md
Commit: f484c82

Reviewed: 4 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.