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

tiledesk

Tiledesk integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tiledesk 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/tiledesk/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 content is actionable and well-structured with concrete commands and a solid connection state-machine, but suffers from inconsistent step labeling and missing validation for action/proxy execution. Adding explicit step headers and result-validation guidance would push it into the top tier.

Suggestions

Add explicit numbered step headers (e.g., 'Step 1: Connect', 'Step 2: Discover actions') and remove the orphaned '1b' / 'Step 2' references to fix the sequencing labels.

Insert validation checkpoints before destructive proxy calls (e.g., confirm the method and target before running DELETE/PATCH) and after action runs (check the output/error fields).

Trim padding like 'so you can focus on the integration logic rather than auth plumbing' and complete the truncated 'It's used by businesses' sentence to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command snippets with brief framing, but contains minor padding such as "so you can focus on the integration logic rather than auth plumbing" and an unfinished "It's used by businesses" sentence, fitting the efficient-with-minor-trim anchor.	4 / 5
Actionability	It provides concrete, copy-paste-ready membrane commands with a flags table, but relies on placeholder IDs (CONNECTION_ID, <actionId>) and dynamic action discovery rather than naming specific Tiledesk actions, leaving minor gaps versus fully-specified examples.	4 / 5
Workflow Clarity	The connection flow has a clear state-machine with polling checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED), but the action-running and proxy paths lack validation checkpoints and the step labeling is inconsistent (a referenced 'Step 2' and '1b' with no matching 'Step 1a'/'Step 2' headers); the destructive-capable proxy (DELETE) without validation caps this at 3.	3 / 5
Progressive Disclosure	The single-file body is well organized into clearly headed sections (Overview, Install, Auth, Connecting, Searching, Proxy, Best practices) with no nested references; the detailed clientAction state machine and flags table could arguably live in a reference file, but placement is reasonable, matching the good-structure anchor.	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 cleanly covers what and when with a distinct proper-noun trigger, but its action language is generic and it lacks trigger synonyms. Tightening the action list and adding concrete trigger phrases would raise it toward the top anchors.

Suggestions

Replace generic verbs with concrete Tiledesk actions (e.g., 'manage live chat, chatbots, and support tickets') to lift specificity.

Add natural trigger variations users would say, such as 'live chat', 'support tickets', or 'chatbot intents', to improve trigger term coverage.

Make the 'Use when...' clause enumerate concrete scenarios (e.g., 'Use when the user wants to manage Tiledesk conversations, bots, or knowledge base') to reach explicit completeness.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Tiledesk domain plus a couple of action categories, but the actions are generic rather than concrete, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It states both what ("Tiledesk integration. Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Tiledesk data"), but the 'when' clause is generic rather than listing concrete trigger phrases, so it does not reach a 5.	4 / 5
Trigger Term Quality	The description includes the key proper-noun trigger "Tiledesk" plus "data", "records", and "workflows", but lacks common synonyms or variations users might naturally say, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The proper noun "Tiledesk" gives the skill a clear niche with minimal conflict risk, though the generic "manage data, records" wording leaves minor overlap with other data-management skills, placing it just below the clearly-distinct anchor.	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/tiledesk/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.