Name: rasa
Rating: 54.400000000000006 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

rasa

Rasa integration. Manage Assistants. Use when the user wants to interact with Rasa data.

Quality

61%

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/SKILL.md

Quality

Content

65%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 executable and reasonably concise with a well-structured connection workflow, but mutating operations lack validation checkpoints and everything lives in one inlined file with no progressive disclosure references.

Suggestions

Add explicit validation/verification guidance for mutating operations, e.g. verify a `action run` result or dry-run a destructive proxy `request` before committing.

Provide at least one fully filled worked example (real connection id and action id) so commands are copy-paste ready.

Split the proxy flag reference table and action input/output schema detail into a separate reference file linked from the body to improve progressive disclosure.

Trim promotional phrasing about Membrane to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with task-oriented command blocks, but contains minor promotional padding ("so you can focus on the integration logic rather than auth plumbing") and an agent-types aside. It is not a 5 because of this padding, and not a 3 because the verbosity is minor rather than noticeable.	4 / 5
Actionability	It provides concrete executable commands for install, login, connecting, action list/run, and proxy requests with a flag table. It is not a 5 because placeholders (CONNECTION_ID, actionId) are never filled with a concrete worked example, and not a 3 because guidance is clearly executable rather than pseudocode.	4 / 5
Workflow Clarity	The connect flow is well-sequenced with explicit states and polling, but mutating/destructive-capable operations (`action run`, proxy `request` with POST/PUT/PATCH/DELETE) lack any validation or verification step, capping this dimension at 3 per the rubric. It is not a 4 because the cap for missing validation on destructive operations applies, and not a 2 because a clear sequence with some checkpoints is present.	3 / 5
Progressive Disclosure	The skill is a single organized SKILL.md with no bundle files, and content that could be split (the proxy flag table, the action-schema description) is inlined. It is not a 4 because there are no external references or file splitting at all, and not a 2 because sections are clearly organized and not buried.	3 / 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 names the Rasa niche and includes an explicit trigger clause, but the capability list is thin ("Manage Assistants") and lacks concrete actions or keyword synonyms. It is adequate but not comprehensive.

Suggestions

Replace the generic "Manage Assistants" with concrete actions, e.g. "Manage Rasa assistants, models, connectors, trackers, and events."

Add natural trigger keywords and synonyms such as "Rasa chatbots, NLU models, conversational AI, intents" so users' phrasing matches.

Make the "when" clause more specific, e.g. "Use when the user wants to manage Rasa assistants, train or deploy models, or inspect tracker/event data."

Dimension	Reasoning	Score
Specificity	"Manage Assistants" is the only named action alongside the domain "Rasa", matching the anchor for naming the domain with minimal or generic actions. It is not a 3 because there is no comprehensive set of concrete actions, and not a 1 because at least one action is named.	2 / 5
Completeness	It states a "what" ("Rasa integration. Manage Assistants.") and an explicit "when" ("Use when the user wants to interact with Rasa data"). It is not a 5 because the "what" is not comprehensive with concrete trigger phrases, and not a 3 because the "when" is explicitly stated rather than only weakly implied.	4 / 5
Trigger Term Quality	"Rasa", "Assistants", and "interact with Rasa data" provide some relevant natural keywords but miss common synonyms or file/extension variations. It is not a 4 because keyword coverage is narrow, and not a 2 because more than one or two generic keywords are present.	3 / 5
Distinctiveness Conflict Risk	"Rasa" anchors a clear niche with mostly distinct triggers, though "Assistants" overlaps with adjacent skill terms. It is not a 5 because the trigger phrasing is somewhat generic, and not a 3 because Rasa is a clearly identifiable niche.	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/rasa/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.