Name: journey
Rating: 52.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

journey

Journey integration. Manage Journeys. Use when the user wants to interact with Journey data.

Quality

59%

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/journey/SKILL.md

Quality

Content

61%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 a usable, mostly executable CLI integration guide with good sectioning, but it carries product fluff, a broken step numbering scheme, and no validation checkpoints for the mutating operations it enables. Fixing the sequence and trimming the marketing prose would most improve it.

Suggestions

Remove the opening marketing paragraph and the filler 'When to use which actions' line; Claude already understands what a journaling app is.

Fix the workflow numbering (drop the orphaned '1b', label 'Step 2') and add a validation checkpoint after mutating calls, e.g. re-fetch or verify the affected entry after `membrane action run` / proxy POST/DELETE.

Either populate the 'Popular actions' section with concrete action examples or remove it to avoid the impression of coverage that isn't there.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean executable commands, but it opens with product-marketing prose ('Journey is a journaling app that allows users to record their thoughts, experiences, and memories...') and includes filler ('When to use which actions: Use action names and parameters as needed.'), matching 'mostly efficient but includes some unnecessary explanation'; it is not 4 because these padded sections are clearly removable.	3 / 5
Actionability	It provides concrete, executable CLI commands with real flags for install, login, connection, action list/run, and proxy requests, matching 'mostly executable guidance with minor gaps'; it is not 5 because placeholders like <actionId>/CONNECTION_ID remain and the 'Popular actions' section lists no concrete actions.	4 / 5
Workflow Clarity	A rough sequence exists (install -> auth -> connect -> search -> run) but is disorganized ('#### 1b' with no 1a, references to an unlabeled 'Step 2') and, critically, the mutating/batch-capable operations (action run, proxy POST/DELETE) have no validation or verification steps, which per the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	With no bundle files present, the single SKILL.md is well-sectioned (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices), matching 'good structure; most content appropriately placed'; it is not 5 because there are no one-level-deep reference links and the inline clientAction spec could be a separate reference.	4 / 5
	Total	14 / 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' clause and names a distinct app, but the capability statement is vague ('Manage Journeys') and trigger coverage is thin. Tightening it with concrete actions and richer trigger phrases would move it toward the top anchors.

Suggestions

Replace the generic 'Manage Journeys' with 2-3 concrete actions, e.g. 'Create, list, and search journal entries and comments'.

Expand the trigger clause with natural variations users would say, e.g. 'Use when the user wants to create journal entries, read or search Journey posts, or manage comments'.

Keep the explicit 'Use when' clause but tie it to specific data objects (entries, comments, users) listed in the body.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Journey integration. Manage Journeys.') but relies on the generic verb 'Manage' with no concrete actions, matching the 'names the domain but actions are minimal or generic' anchor; it falls below 3 because no concrete actions (e.g. create/read entries) are enumerated.	2 / 5
Completeness	Both a 'what' ('Journey integration. Manage Journeys.') and an explicit 'when' ('Use when the user wants to interact with Journey data') are present, satisfying the anchor for 4; it is not 5 because the 'what' is vague ('Manage Journeys') and the 'when' is generic rather than tied to concrete trigger phrases.	4 / 5
Trigger Term Quality	It includes a usable natural trigger ('Use when the user wants to interact with Journey data') plus the app name, but coverage is limited to 'Journey' with no synonyms, related phrases, or file extensions, matching 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Naming a specific third-party app ('Journey') gives a clear niche with minor overlap risk against other journaling/note skills, matching 'mostly distinct; minor overlap risk'; it is not 5 because the generic 'Manage Journeys' phrasing does not provide sharply distinct triggers.	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/journey/SKILL.md
Commit: f484c82

Reviewed: 5 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.