Name: dandelion
Rating: 53.6 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

dandelion

Dandelion integration. Manage Organizations. Use when the user wants to interact with Dandelion data.

Quality

60%

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/dandelion/SKILL.md

Quality

Content

63%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 solid, command-driven integration guide with a clear connection workflow and explicit state checkpoints, but it is somewhat padded and keeps all detail inline rather than progressively disclosing it to reference files.

Suggestions

Trim the marketing-style intro and remove the empty 'Dandelion Overview' bullet list plus the filler line 'Use action names and parameters as needed.'

Move the full popular-actions catalog and proxy flag reference into separate reference files, keeping only key examples inline with clear links.

Fix the dangling 'Step 2' references by labeling the downstream sections (e.g. 'Step 2: Search and run actions') so the workflow sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but includes some unnecessary padding (the marketing-style intro paragraph, the cryptic 'Dandelion Overview' bullet list, and filler like 'Use action names and parameters as needed') that could be tightened.	3 / 5
Actionability	It provides copy-paste-ready CLI commands (login, connection ensure, action list/run, request) plus a popular-actions table and flag reference, but the generic placeholders and the vague 'Dandelion Overview' section leave minor gaps versus fully executable coverage.	4 / 5
Workflow Clarity	The connection flow is a clear sequence with explicit state-based checkpoints and a poll-after-user-action feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), though references to an unlabeled 'Step 2' and slightly loose ordering keep it from level 5.	4 / 5
Progressive Disclosure	Sections are well-organized and the only external pointer is the official docs URL, but the doc is a single ~120-line file with no one-level-deep references splitting out the action catalog or proxy details, so content that could live in separate files is inlined.	3 / 5
	Total	14 / 20 Passed

Description

57%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 includes an explicit 'Use when' trigger and names a specific platform, but its capability statement is thin and generic ('Manage Organizations') rather than reflecting Dandelion's actual text-analytics functions.

Suggestions

Replace 'Manage Organizations' with the real concrete capabilities, e.g. 'Analyze sentiment, detect language, compare text similarity, and extract entities from text'.

Broaden the trigger phrase to natural user terms, e.g. 'Use when the user wants sentiment analysis, language detection, or entity extraction from text'.

Make the 'when' clause more specific by naming the text-analytics tasks rather than the generic 'interact with Dandelion data'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Dandelion integration') and a single minimal action ('Manage Organizations') but gives no concrete text-analytics capabilities; not the level-3 '1-2 concrete actions' because 'Manage Organizations' is generic and arguably misrepresents the platform's actual sentiment/entity features.	2 / 5
Completeness	Both a 'what' ('Dandelion integration. Manage Organizations.') and an explicit 'when' ('Use when the user wants to interact with Dandelion data') are present, satisfying the level-4 anchor, though the 'what' is vague and the 'when' is not very specific so it does not reach level 5.	4 / 5
Trigger Term Quality	'Use when the user wants to interact with Dandelion data' surfaces the relevant keyword 'Dandelion' / 'Dandelion data', but offers no natural synonyms or task phrases (sentiment, entities, language detection) that users would actually say.	3 / 5
Distinctiveness Conflict Risk	'Dandelion' is a named external platform giving a clear niche with minimal conflict risk, but the trigger 'interact with Dandelion data' is somewhat broad so it is mostly distinct rather than fully so.	4 / 5
	Total	13 / 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/dandelion/SKILL.md
Commit: f484c82

Reviewed: ~16 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.