Name: bunnyshell
Rating: 56.8 (1 reviews)
Author: membranedev

bunnyshell

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

Quality

65%

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/bunnyshell/SKILL.md

Quality

Content

68%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 an actionable, well-structured guide with strong connection-state feedback loops. Its main weakness is the absence of verification steps before destructive action runs or proxy calls, which caps workflow clarity.

Suggestions

Add an explicit verification step before running mutating actions or proxy DELETE/PUT requests, e.g. listing the target resource and confirming with the user before destructive operations.

Provide one end-to-end worked example with realistic values (connection id, action id, input JSON) to close the placeholder gap in actionability.

Trim the best-practices section and the auth-plumbing aside to recover tokens without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — install, auth, connection, and action commands appear with minimal preamble — but a few lines pad ('so you can focus on the integration logic rather than auth plumbing') and the best-practices section restates points, keeping it just below fully efficient.	4 / 5
Actionability	It provides concrete, executable commands throughout (npm install, membrane login, connection ensure, action run, request) with a flag table for proxying, but relies on placeholders (CONNECTION_ID, actionId) and lacks an end-to-end worked example, leaving minor gaps.	4 / 5
Workflow Clarity	The connection flow has a strong polling/feedback loop (BUILDING -> READY, CLIENT_ACTION_REQUIRED -> re-poll, CONFIGURATION_ERROR), but running actions and proxying requests (including DELETE) has no verification checkpoint, so the destructive-operations cap limits this to the validation-gaps anchor.	3 / 5
Progressive Disclosure	Content is well organized into clearly headed sections with no nested references, and inline material (proxy flag table, state machine) is reasonably placed; minor gaps are that some reference-worthy material is inlined and there are no separate reference files for deeper detail.	4 / 5
	Total	15 / 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 is product-anchored and includes an explicit 'Use when' clause, which gives it solid completeness and distinctiveness. Weaknesses are generic action verbs and limited trigger-term variety, which keep specificity and trigger quality at mid-range.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Bunnyshell operations like 'provision environments, deploy components, and manage deployments'.

Add natural trigger synonyms such as 'environments', 'deployments', or 'cloud environments' so users phrase requests in their own words.

Tighten the 'when' clause to name specific intents, e.g. 'Use when the user wants to provision, deploy, or manage Bunnyshell environments.'

Dimension	Reasoning	Score
Specificity	The description names the domain (Bunnyshell) and a couple of actions ('Manage data, records, and automate workflows'), but those actions are generic rather than concrete platform-specific operations, so it sits at the 'domain plus 1-2 actions, not comprehensive' anchor.	3 / 5
Completeness	It states both what it does ('Manage data, records, and automate workflows') and when to use it ('Use when the user wants to interact with Bunnyshell data'); the 'when' is explicit but could be more specific, so it is above the missing-when anchor but short of fully concrete triggers.	4 / 5
Trigger Term Quality	It surfaces the product keyword 'Bunnyshell' and the natural phrase 'interact with Bunnyshell data', but lacks common synonyms or variations users might say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Bunnyshell product name gives it a clear niche and the trigger names the product explicitly, minimizing wrong-skill activation, though the generic verbs ('manage data, records') leave minor overlap risk with adjacent data skills.	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/bunnyshell/SKILL.md
Commit: f484c82

Reviewed: 4 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.