Name: cohere
Rating: 59.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

cohere

Cohere integration. Manage Documents, Models, Datasets, Jobs. Use when the user wants to interact with Cohere data.

Quality

68%

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/cohere/SKILL.md

Quality

Content

75%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 highly actionable with executable commands and a clear connection-state workflow, but it includes some unnecessary Cohere background and keeps reference-like catalogs inline rather than splitting them into bundled files.

Suggestions

Trim the intro paragraph and 'Cohere Overview' bullets, which restate product capabilities Claude already knows; keep only the operational details unique to the Membrane integration.

Fix the broken 'skip to Step 2' cross-reference by labeling the post-connection steps as Step 2 (search actions) and Step 3 (run/proxy), or remove the dangling reference.

Add an explicit verification checkpoint after running an action (e.g., check the `output` field and handle error states) to close the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The bulk is an efficient command reference, but the intro paragraph ('Cohere provides access to advanced language models...') and the 'Cohere Overview' bullets re-explain Cohere capabilities Claude largely already knows, so it could be tightened.	3 / 5
Actionability	It provides fully executable, copy-paste-ready commands across the common cases (install, login, connection ensure, action list/run, proxy) with a flags table and concrete JSON-input examples.	5 / 5
Workflow Clarity	The install→login→connect→poll→search→run sequence is clear with state-machine feedback loops (READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR with re-poll), but the 'skip to Step 2' reference is broken and there is no post-run verification checkpoint.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with no nested references, but in a >150-line single-file skill the inline 'Popular actions' catalog and proxy flag table are reference material that could be split into separate files.	4 / 5
	Total	16 / 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 covers both what and when with a clear Cohere-specific trigger, but relies on a single generic verb and lacks the natural task-level keywords (e.g., generate text, embed, rerank) that would sharpen trigger matching.

Suggestions

Replace the generic 'Manage' with distinct concrete verbs reflecting actual Cohere tasks, e.g., 'Generate text and chat responses, classify and embed text, rerank documents'.

Add concrete trigger phrases to the 'Use when...' clause, e.g., 'Use when the user wants to generate text, embed or rerank documents, or classify content with Cohere'.

Include common synonyms and API surface terms users say (chat, embeddings, rerank, classify) to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the Cohere domain and lists four resource types ('Manage Documents, Models, Datasets, Jobs'), but the only action verb is the generic 'Manage' applied uniformly rather than multiple distinct concrete actions.	3 / 5
Completeness	Both 'what' ('Manage Documents, Models, Datasets, Jobs') and 'when' ('Use when the user wants to interact with Cohere data') are explicitly present, though the trigger clause is somewhat generic rather than listing concrete task triggers.	4 / 5
Trigger Term Quality	The brand keyword 'Cohere' appears in 'Cohere integration' and 'interact with Cohere data', but the resource words are generic and common synonyms or natural phrasings a user would say are largely missing.	3 / 5
Distinctiveness Conflict Risk	'Cohere integration' establishes a clear branded niche with minimal conflict risk, but the generic resource list ('Documents, Models, Datasets, Jobs') creates minor overlap risk with adjacent ML/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/cohere/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.