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

Blog Docs Log in Get started

deepseek

DeepSeek integration. Manage Organizations. Use when the user wants to interact with DeepSeek 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/deepseek/SKILL.md

Quality

Content

67%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 strong, actionable integration guide with concrete commands and a well-handled connection-state feedback loop. Its main weaknesses are templated filler in the Overview/intro and a broken Step 2 cross-reference that slightly muddy the workflow.

Suggestions

Remove the introductory paragraph explaining what DeepSeek is and the empty "DeepSeek Overview" bullet list ("Files / Folders"), which read as templated filler Claude does not need.

Fix the dangling "Step 2" reference by either labeling the post-connection section "Step 2" or rewording to "skip to Searching for actions" so the workflow sequence is unambiguous.

Tighten "When to use which actions: Use action names and parameters as needed." into concrete guidance, or delete it, since it currently adds tokens without instruction.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient concrete commands and tables, but the intro paragraph explaining what DeepSeek is and the templated "DeepSeek Overview" section ("Files / Folders", "Use action names and parameters as needed.") are unnecessary padding.	3 / 5
Actionability	Copy-paste-ready commands appear throughout (install, login, connection ensure, action list/run, request) with a popular-actions table and proxy-flag table, leaving only minor gaps around placeholders and the vague overview.	4 / 5
Workflow Clarity	The install-auth-connect-search-run sequence is clear with a real feedback loop in the connection state handling (poll --wait, re-poll after clientAction, handle error states), but "skip to Step 2" references a non-existent Step 2 and there is no post-run verification.	4 / 5
Progressive Disclosure	Content is organized into clear ## / ### sections in a single file with no bundle files, but at over 50 lines with a vague Overview section and inconsistent step numbering (1b, Step 2) it has minor organization gaps rather than fully clean navigation.	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 correctly pairs a what statement with an explicit Use-when trigger and is anchored to a specific product, but it is thin on concrete actions and natural trigger terms. Expanding the action list and trigger synonyms would lift it from adequate to strong.

Suggestions

Replace the generic "interact with DeepSeek data" with the concrete actions the skill actually supports (e.g. create chat/FIM completions, list models, check user balance), since "Manage Organizations" does not match the skill's real capabilities.

Add natural trigger terms users would say, such as "chat completion", "DeepSeek models", or "DeepSeek API", to improve trigger-term coverage beyond the single brand keyword.

Sharpen the Use-when clause to name specific intents (e.g. "Use when generating code completions or querying DeepSeek models") instead of the vague "interact with DeepSeek data".

Dimension	Reasoning	Score
Specificity	Names the DeepSeek domain plus one concrete action ("Manage Organizations"), while the rest ("interact with DeepSeek data") stays generic, matching the 1-2 concrete actions anchor without being comprehensive.	3 / 5
Completeness	It states both what ("DeepSeek integration. Manage Organizations.") and when ("Use when the user wants to interact with DeepSeek data."), but the when clause is generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	"DeepSeek" is the single strong natural keyword a user would say, but there are no synonyms or variations (e.g. chat completion, models, API), so coverage is relevant yet incomplete.	3 / 5
Distinctiveness Conflict Risk	The "DeepSeek" product name makes it mostly distinct with minimal conflict risk, though "Manage Organizations" and "interact with data" are generic enough to invite minor overlap with related 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/deepseek/SKILL.md
Commit: f484c82

Reviewed: ~17 hours 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.