Name: fountain
Rating: 49.6 (1 reviews)
Author: membranedev

fountain

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

Quality

53%

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/fountain/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 content delivers concrete, executable Membrane CLI guidance with a solid connection-state workflow, but it is generic boilerplate not specialized to Fountain, over-explains the screenwriting concept, and omits verification steps for potentially destructive action/proxy calls. Structure is clean for a single-file skill.

Suggestions

Add a verification step after `membrane action run` and proxy requests (e.g. inspect the `output` field / response status and confirm the expected change) so destructive operations have a feedback loop.

Trim the introductory screenwriting explainer and the auth-plumbing aside; assume Claude knows what Fountain is and what auth refresh entails.

Specialize the examples with Fountain-specific actions or endpoints rather than only generic `--intent=QUERY` placeholders to reduce overlap with other Membrane skill guides.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient CLI guidance, but the opening paragraph explains what Fountain/screenwriting is (concept Claude already knows) and includes padded lines like "so you can focus on the integration logic rather than auth plumbing", fitting the score-3 anchor of mostly efficient with some unnecessary explanation.	3 / 5
Actionability	Concrete copy-paste commands are provided throughout (membrane login, connection ensure, action list/run, request with a full flag table), with minor gaps such as the unresolved CONNECTION_ID placeholder, matching the score-4 anchor of mostly executable guidance with minor gaps.	4 / 5
Workflow Clarity	The connection flow has explicit state polling and retry checkpoints, but the action-run and proxy workflows (which support destructive methods like DELETE/PUT) lack any result verification step, so the destructive-operation cap holds this at the score-3 anchor.	3 / 5
Progressive Disclosure	The single-file body is well sectioned (Overview, Working with Fountain, Popular actions, Proxy, Best practices) with no bundle files to navigate; it slightly exceeds the simple-skill threshold at ~140 lines but stays well-organized, fitting the score-4 anchor of good structure with minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

46%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 the required what/when structure but relies on generic Membrane boilerplate actions and only the brand name as a trigger, weakening specificity and trigger quality. It is functional but not tailored to what Fountain (screenwriting) actually does.

Suggestions

Replace generic actions with Fountain-specific capabilities, e.g. "Parse, edit, and validate Fountain-format screenplays and manage script elements."

Add natural user-facing trigger terms such as "screenplays", "scripts", "screenwriting", or ".fountain files" to the Use-when clause.

Tie the when-condition to concrete scenarios (e.g. "Use when the user wants to write or convert screenplays in Fountain syntax") to reduce overlap with other integration skills.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Fountain domain but the actions are generic boilerplate rather than concrete capabilities; matches the score-2 anchor "Names the domain but actions are minimal or generic."	2 / 5
Completeness	Both a "what" (manage data, records, automate workflows) and an explicit "Use when the user wants to interact with Fountain data" trigger are present, but the "when" is generic rather than specific to concrete triggers, matching the score-4 anchor.	4 / 5
Trigger Term Quality	Only the brand keyword "Fountain" appears via "interact with Fountain data"; the natural terms a user would say (screenplay, script, screenwriting) are absent, fitting the score-2 anchor of one or two generic keywords missing natural phrases.	2 / 5
Distinctiveness Conflict Risk	Naming the specific Fountain app gives some distinctiveness, but the identical "manage data, records, automate workflows" phrasing is reused across Membrane integrations, so it could still overlap with sibling skills per the score-3 anchor.	3 / 5
	Total	11 / 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/fountain/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.