Name: seven
Rating: 61.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

seven

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

82%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 executable Membrane CLI commands and a well-sequenced connection state machine, but it has minor redundancy and a couple of placeholder-ish sections that slightly reduce conciseness and organization.

Suggestions

Label the referenced "Step 2" explicitly or remove the dangling cross-reference so the workflow sequence is unambiguous.

Merge the redundant "Popular actions" section into "Searching for actions" to remove the duplicated action-list command.

Flesh out or remove the thin "Seven Overview" section so every section earns its place.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with executable commands and legitimately novel Membrane flow details, but the "Popular actions" section duplicates the "Searching for actions" command and a few marketing-style asides could be trimmed, fitting anchor 4 over anchor 5.	4 / 5
Actionability	Copy-paste-ready commands cover the common cases end-to-end ("npm install -g @membranehq/cli@latest", "membrane connection ensure ... --json", "membrane action run <actionId> --connectionId=CONNECTION_ID --json", plus a proxy flags table), matching anchor 5's fully executable coverage.	5 / 5
Workflow Clarity	The connection flow has an explicit state sequence with a feedback loop (poll with --wait, handle CLIENT_ACTION_REQUIRED, then poll again), but "skip to Step 2" references a Step 2 that is never labeled, a minor gap that fits anchor 4 rather than anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is organized into clear sections with no nested references, fitting anchor 4; the thin "Seven Overview" and placeholder-like "Popular actions" sections are minor organization gaps keeping it below anchor 5.	4 / 5
	Total	17 / 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 and is anchored to a named app, but relies on a single generic verb ("Manage") and a thin, generic trigger phrase rather than concrete actions and natural trigger terms.

Suggestions

Replace the generic verb "Manage" with concrete actions per entity (e.g. "Create and update Goals, list Users, apply Filters").

Expand the trigger clause with natural phrases users would say, such as habits, routines, or goal tracking, plus synonyms.

Verify the entity list (Organizations, Users, Goals, Filters) matches Seven's actual habit-tracking domain to avoid misleading triggers.

Dimension	Reasoning	Score
Specificity	Quotes "Manage Organizations, Users, Goals, Filters" name the domain and several concrete entities, but the single verb "Manage" is generic, matching anchor 3 (domain + objects) better than anchor 2's minimal-action example and below anchor 4's multiple specific actions.	3 / 5
Completeness	Both a "what" ("Manage Organizations, Users, Goals, Filters") and an explicit "when" ("Use when the user wants to interact with Seven data") are present; the "when" is somewhat generic, matching anchor 4 rather than the concrete-trigger anchor 5 and above the no-trigger anchor 3.	4 / 5
Trigger Term Quality	The clause "Use when the user wants to interact with Seven data" supplies a reasonable trigger phrase, but coverage is thin with no synonyms or task-level terms (e.g. habits, goals), fitting anchor 3's "some relevant keywords but missing common variations."	3 / 5
Distinctiveness Conflict Risk	Naming the specific app "Seven" with the trigger "interact with Seven data" gives a clear niche with minor overlap risk, fitting anchor 4; the generic SaaS entity list keeps it below anchor 5's fully distinct triggers.	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/seven/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.