Name: talkdesk
Rating: 63.2 (1 reviews)
Author: membranedev

talkdesk

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

Quality

75%

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/talkdesk/SKILL.md

Quality

Content

76%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 highly actionable with executable commands and a well-structured connection workflow, but it caps on workflow clarity because destructive proxy/action operations have no validation checkpoints and a 'Step 2' reference is dangling. Adding a verify-before-destructive-call step and labeling Step 2 would raise it.

Suggestions

Add a validation/verification checkpoint before destructive proxy requests (POST/PUT/PATCH/DELETE) and batch action runs, e.g. confirm the target and dry-run where possible, to satisfy the workflow-clarity feedback-loop requirement.

Label or remove the dangling 'skip to Step 2' reference so the connection workflow's sections are consistently numbered and navigable.

Trim the introductory definition of what Talkdesk is and marketing-style phrases ('rather than auth plumbing', 'burn less tokens') to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and command-driven, with only minor padding such as the introductory definition of what Talkdesk is and phrases like 'rather than auth plumbing' and 'burn less tokens', matching 'efficient, minor over-explanation to trim' rather than fully lean.	4 / 5
Actionability	It provides copy-paste ready executable commands across install, auth, connection, action discovery, action execution, and proxying (plus a flags table), covering the common cases fully.	5 / 5
Workflow Clarity	The connection flow has a clear state-based sequence with poll checkpoints, but 'skip to Step 2' references an unlabeled section and destructive operations (proxy POST/PUT/DELETE, action runs) lack any validation/verification step, triggering the destructive-op cap at 3.	3 / 5
Progressive Disclosure	The single-file skill is well-organized into clear sections with no nested references, though some reference-like material (clientAction fields, proxy flags table) is inlined, matching 'good structure, minor organization gaps'.	4 / 5
	Total	16 / 20 Passed

Description

73%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 answers both what and when with an explicit 'Use when' clause and a distinctive brand trigger, but its action list is generic and lacks concrete Talkdesk entity terms. Tightening the trigger phrases to mention calls, contacts, or records would lift completeness and trigger quality.

Dimension	Reasoning	Score
Specificity	It names the domain plus a few actions ('Manage data, records, and automate workflows') but these are generic rather than concrete Talkdesk operations, matching the 'domain + 1-2 actions, not comprehensive' anchor rather than the specific-action anchors above or the purely minimal anchor below.	3 / 5
Completeness	Both 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with Talkdesk data') are explicit, but the trigger is single-phrased rather than a set of concrete triggers, matching 'both present, when could be more specific'.	4 / 5
Trigger Term Quality	'Talkdesk' appears twice ('Talkdesk integration', 'interact with Talkdesk data') giving good natural keyword coverage, but specific entity terms (calls, contacts, agents) that users would mention are absent, so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	'Talkdesk' is a specific SaaS brand establishing a clear niche with distinct triggers and minimal conflict risk, matching the 'clear niche, minimal conflict' anchor.	5 / 5
	Total	16 / 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/talkdesk/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.