Name: rasa-1
Rating: 52.8 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

rasa-1

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

Quality

58%

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/rasa-1/SKILL.md

Quality

Content

63%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 actionable and reasonably well-sequenced for the Membrane/Rasa workflow, with concrete CLI examples and state-handling checkpoints. It loses points for some background padding, a thin overview section, and lack of progressive disclosure via reference files for the longer reference material.

Suggestions

Trim concept-level padding (the 'Rasa is an open-source...' sentence and the bare overview tree) since Claude already knows what Rasa is.

Add an explicit validate/retry feedback loop after action runs and connection errors (e.g., on CONFIGURATION_ERROR, surface the error field, fix, and re-run) to reach the workflow_clarity 5 anchor.

Move the proxy flag table and action-discovery details into a reference file (e.g., REFERENCE.md) and link to it one level deep, improving progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes mild padding such as explaining what Rasa is ("Rasa is an open-source conversational AI framework..."), the truncated overview tree, and repeated action-list instructions that could be tightened, fitting the 3 anchor.	3 / 5
Actionability	It provides mostly executable CLI commands with flags and JSON output examples covering connect, search, run, and proxy flows, with only minor gaps (e.g., placeholder CONNECTION_ID and no resolved example), matching the 4 anchor.	4 / 5
Workflow Clarity	The connection flow is clearly sequenced with state checks (READY / BUILDING / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and polling loops, giving explicit checkpoints; it stops short of 5 because there is no explicit validate-then-retry loop or checklist for error recovery.	4 / 5
Progressive Disclosure	The content is organized into sections with no bundle files present and no external references, so structure exists but some content (the proxy flag table, popular actions) is inline where a reference file could help; given the under-50-line exception does not apply to this ~140-line skill, the 3 anchor fits.	3 / 5
	Total	14 / 20 Passed

Description

53%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' trigger and names the Rasa domain, but its capability list is generic and verbose-light. Strengthening it with concrete Rasa-specific actions and trigger synonyms would improve specificity and distinctiveness.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Rasa-specific actions (e.g., 'train models, inspect trackers, query conversation events, run custom actions').

Add natural trigger synonyms and entities users say (e.g., 'Use when the user mentions Rasa assistants, chatbots, training data, trackers, or conversation events').

Tighten phrasing so the 'what' reads as a distinct, niche capability rather than broad data/automation language that overlaps with other skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Rasa integration") and a few generic verbs ("Manage data, records, and automate workflows") but the actions are minimal and generic rather than concrete capabilities; it falls below the 3 anchor because no specific concrete actions are enumerated.	2 / 5
Completeness	It provides a clear (if generic) 'what' and an explicit 'Use when...' clause ("Use when the user wants to interact with Rasa data"), so both are present, though the 'when' could be more specific, matching the 4 anchor.	4 / 5
Trigger Term Quality	It includes a natural trigger phrase ("interact with Rasa data") plus the product name, but lacks synonyms or file/extension variants users might say, fitting the 3 anchor of relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	"Rasa integration" names a niche, but the generic verbs ("Manage data, records, automate workflows") overlap broadly with many data/automation skills, fitting the 3 anchor of somewhat specific but with overlap risk.	3 / 5
	Total	12 / 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/rasa-1/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.