Name: r3
Rating: 51.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

r3

R3 integration. Manage data, records, and automate workflows. Use when the user wants to interact with R3 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/r3/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 body is highly actionable with concrete Membrane CLI commands and a well-instrumented connection flow, but it is held back by a large inlined entity list that wastes tokens and by missing validation guidance for destructive action runs and proxy calls. No bundle files are present, so the entity list cannot be offloaded as currently structured.

Suggestions

Move the ~180-item entity list into a references/ file (e.g. ENTITIES.md) and replace it with a one-line pointer plus the existing 'membrane action list' discovery command.

Add a validation/confirmation checkpoint before destructive operations — e.g. confirm with the user before 'membrane action run' or proxy requests using POST/PUT/DELETE, and verify responses for batch operations.

Resolve placeholders in examples (CONNECTION_ID, QUERY, <agentType>) with concrete values or a clear note on how to obtain them, to push actionability toward copy-paste ready.

Dimension	Reasoning	Score
Conciseness	An inlined ~180-item bulleted list of entity names consumes substantial tokens that the skill itself says should be discovered via 'membrane action list', fitting 'noticeably verbose; several unnecessary... padded sections'; the CLI sections are efficient but the list drags the whole down.	2 / 5
Actionability	Concrete, copy-paste-ready commands are given throughout (npm install, membrane login, connection ensure, action list/run, request) with flags and JSON examples, but placeholders like CONNECTION_ID, QUERY, and <agentType> keep it just short of fully executable level 5.	4 / 5
Workflow Clarity	The connection flow is well sequenced with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR and re-polling), but running actions and proxying arbitrary POST/PUT/DELETE requests are potentially destructive yet lack any validation step, capping this at 3 per the destructive-operation guideline.	3 / 5
Progressive Disclosure	Section headers organize the CLI workflow reasonably, but the ~180-line entity list is content that clearly belongs in a separate reference file and is inlined directly, matching 'some structure... content that should be separate is inline'.	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 answers both what and when with an explicit 'Use when' clause and names a specific platform, but its actions and trigger keywords are generic and miss natural synonyms. It is solid but lacks the concrete, comprehensive phrasing of the top anchors.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete capabilities (e.g. 'Create and update cases, contacts, tasks, invoices, and trust requests; automate case workflows').

Add natural trigger keywords and synonyms users would actually say, such as 'R3', 'Corda', 'cases', 'contacts', and 'time entries'.

Tighten the 'when' clause with concrete triggers, e.g. 'Use when the user wants to create or update R3/Corda cases, contacts, tasks, invoices, or trust records.'

Dimension	Reasoning	Score
Specificity	Names the domain ('R3 integration') and a couple of actions ('Manage data, records, and automate workflows'), but the actions are generic ('manage', 'automate') rather than concrete, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor rather than the more concrete level 4.	3 / 5
Completeness	Both 'what' ('R3 integration. Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with R3 data') are present and explicit, but the trigger is generic so it lands at 'both present, when could be more specific' rather than the fully concrete level 5.	4 / 5
Trigger Term Quality	The main keyword is 'R3' with the trigger 'interact with R3 data', but common synonyms (e.g. Corda, linked in the body docs) and natural phrasings are missing, fitting 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	Naming the specific R3 platform gives it a clear niche with minimal conflict risk, but the generic 'manage data, records' phrasing could overlap with general data-management skills, so it is 'mostly distinct; minor overlap risk' rather than fully distinct.	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/r3/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.