Name: rafflys
Rating: 51.2 (1 reviews)
Author: membranedev

rafflys

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

Quality

56%

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/rafflys/SKILL.md

Quality

Content

50%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 genuinely actionable, walking through the full Membrane CLI workflow with executable commands, but it is dragged down by a junk refusal paragraph pasted into the body and a total absence of validation checkpoints for destructive proxy/action calls. Organization is adequate but marred by the placeholder text and a skeletal overview.

Suggestions

Remove the placeholder refusal text ("I don't have enough information to do that. I'm a large language model...") from the top of the body — it is irrelevant padding that wastes tokens.

Add explicit validation/verification checkpoints before destructive operations, e.g. confirm the connection and dry-run/inspect an action before `membrane action run`, and warn before issuing DELETE/PUT via `membrane request`.

Flesh out the "Rafflys Overview" with the real action/entity map (the body already references Raffle/Participant/User) instead of the vague "Use action names and parameters as needed."

Dimension	Reasoning	Score
Conciseness	The body opens with a large padded non-sequitur ("I don't have enough information to do that. I'm a large language model...") and includes unnecessary prose like "so you can focus on the integration logic rather than auth plumbing", making it noticeably verbose despite the otherwise efficient command docs; it is not severe enough for level 1 because the command reference is tight.	2 / 5
Actionability	It provides concrete, copy-paste-ready commands across the full flow (npm install, membrane login, search/connect, action list/run, request with a flags table), covering the common cases with only minor gaps such as the generic "{ \"key\": \"value\" }" input example and the thin "Use action names and parameters as needed" overview.	4 / 5
Workflow Clarity	The install → login → connect → discover → run/proxy sequence is clearly ordered with headers, but there are no validation or verification checkpoints for destructive operations (the proxy explicitly supports DELETE/PUT and action run can mutate), which per the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	There are no bundle files and the skill is a single ~120-line document with logical section headers, but the "Rafflys Overview" section is skeletal and the interleaved refusal text breaks organization, leaving it at 'some structure but could be better organized' rather than well-placed.	3 / 5
	Total	12 / 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 cleanly states both what the skill does and when to use it, anchored to a distinct named app, so it clears the completeness floor. Its main weakness is relying on one generic verb ("Manage") and a thin set of trigger synonyms, which keeps specificity and trigger_term_quality in the mid range.

Suggestions

Replace the single verb "Manage" with distinct concrete actions per entity (e.g. "Create and update Organizations, build Pipelines, invite Users, configure Filters") to lift specificity.

Expand the 'Use when' clause with concrete trigger phrases users would actually say (e.g. "Use when the user mentions Rafflys, raffles, participants, or wants to manage Rafflys organizations/pipelines").

Add common synonyms and the app's domain terms (raffles, participants, campaigns) so trigger_term_quality covers natural variations.

Dimension	Reasoning	Score
Specificity	It names the Rafflys domain and four concrete entities ("Manage Organizations, Pipelines, Users, Filters"), but the single generic verb "Manage" is applied to all of them rather than listing multiple distinct actions, fitting the 'names domain and concrete items but actions are minimal/generic' anchor.	3 / 5
Completeness	Both 'what' ("Manage Organizations, Pipelines, Users, Filters") and 'when' ("Use when the user wants to interact with Rafflys data") are present and explicit, but the 'when' clause does not enumerate concrete trigger phrases, so it sits at 'has both what and when; when could be more specific' rather than the fully-enumerated level 5.	4 / 5
Trigger Term Quality	The app name "Rafflys" and the entity list provide relevant keywords and a natural trigger ("Use when the user wants to interact with Rafflys data"), but common variations/synonyms a user might actually say (e.g. raffles, participants, campaigns) are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Rafflys integration" is a uniquely named app niche with distinct triggers and low conflict risk, but the trigger guidance ("interact with Rafflys data") is generic rather than richly distinct, placing it at 'mostly distinct; minor overlap risk' rather than the minimal-conflict level 5.	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/rafflys/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.