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

chaindesk

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/chaindesk/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 a well-structured, mostly executable guide to driving Chaindesk through the Membrane CLI, with a strong connection workflow. Its main gaps are the lack of validation guidance around destructive delete actions and the absence of a fully-worked action example.

Suggestions

Add a validation checkpoint before destructive actions, e.g. 'Before running delete-datasource/delete-datastore/delete-agent, confirm the target ID with the user and consider a get-* call to verify'.

Include one fully-worked popular-action example with real parameter values (e.g. `membrane action run query-datastore --input '{"query": "..."}'`).

Trim the mildly padded explanatory prose around auth plumbing to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with copy-paste bash commands and tight tables, but includes some mild explanatory prose (e.g. 'so you can focus on the integration logic rather than auth plumbing') that could be trimmed.	4 / 5
Actionability	Provides concrete, executable commands for every phase (login, connection ensure, action list/run, request proxy), but stops short of a fully-worked action invocation with real parameter values for the listed popular actions.	4 / 5
Workflow Clarity	The connection flow is well-sequenced with explicit state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-again feedback loop, but destructive actions (delete-datasource, delete-datastore, delete-agent) appear with no validation or confirmation guidance, capping the score at 3.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections (install, auth, connecting, searching, popular actions, proxy, best practices) with no nested references and no bundle files present; the inline popular-actions and proxy-flag tables are minor bulk that could optionally be split out.	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 clear and includes an explicit 'Use when' trigger tied to a named platform, but its action verbs are generic and it lacks richer natural-language trigger terms. It is distinguishable but could be more specific and comprehensive.

Suggestions

Replace generic verbs with concrete Chaindesk actions, e.g. 'Retrieve conversations, query datastores, and manage datasources and agents'.

Add natural trigger phrases users would say, such as 'Use when the user mentions Chaindesk conversations, datasources, datastore queries, or AI agents'.

Mention the supported channels (Discord, Telegram, email) in the description to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (Chaindesk) and a couple of actions ('Manage data, records, and automate workflows'), but the actions are generic rather than concrete, so coverage is not comprehensive.	3 / 5
Completeness	Both the 'what' ('Manage data, records, and automate workflows') and an explicit 'when' ('Use when the user wants to interact with Chaindesk data') are present, but the trigger could be more specific with concrete phrases.	4 / 5
Trigger Term Quality	Includes relevant keywords ('Chaindesk', 'data', 'records', 'workflows') but misses common variations and synonyms a user might naturally say (e.g. conversations, datasource, chatbot, datastore).	3 / 5
Distinctiveness Conflict Risk	The named platform ('Chaindesk integration') gives a clear niche with low conflict risk, though the generic action verbs ('manage data', 'automate workflows') leave minor overlap with broader 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/chaindesk/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.