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

junip

Junip integration. Manage Persons, Organizations, Deals, Activities, Notes, Files and more. Use when the user wants to interact with Junip 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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/junip/SKILL.md

Quality

Content

82%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 copy-paste CLI commands and a clear connection-state workflow including polling feedback loops. Its main weaknesses are minor marketing-flavored padding and a lack of explicit validation after action execution, plus a description/body mismatch on what entities the skill manages.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command reference with executable snippets and tables, with only minor padding such as the marketing-style intro ("helps e-commerce brands collect and showcase customer reviews... build trust and increase sales") and "so you can focus on the integration logic rather than auth plumbing", fitting the "efficient; minor instances of over-explanation" anchor.	4 / 5
Actionability	It provides copy-paste-ready commands throughout — install, login (including headless completion), `connection ensure`, polling with `--wait`, `action list`/`run` with `--input` JSON, and a proxy flags table — covering the common cases with fully executable guidance.	5 / 5
Workflow Clarity	The connection flow has an explicit state machine with checkpoints and a feedback loop (poll until READY, handle CLIENT_ACTION_REQUIRED by re-polling, check CONFIGURATION_ERROR), but the overall install→auth→connect→search→run sequence is conveyed via headers rather than a numbered sequence and lacks an explicit post-run verification step.	4 / 5
Progressive Disclosure	The single file is well-organized into clear sections (Overview, Working with Junip, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) with no nested references and no bundle files; it is slightly above the "good structure; most content appropriately placed" anchor, though the popular-actions and proxy-flag tables are inline reference material that could live separately.	4 / 5
	Total	17 / 20 Passed

Description

55%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 and is brand-distinctive, but its trigger language is generic and the listed entities (Persons, Organizations, Deals) do not match the skill's actual review-platform subject matter, suggesting a templated description. Tightening the trigger clause to mention reviews/ratings/products would materially improve it.

Suggestions

Replace the generic "interact with Junip data" trigger with concrete natural phrases users would say, e.g. "Use when the user wants to read, list, or analyze Junip reviews, product ratings, or store review statistics."

Align the "what" with the skill's real capabilities — reviews, review requests, products, and store overview — instead of the CRM-style Persons/Organizations/Deals entities that do not appear in the body.

Drop the vague "and more" filler and use specific verbs (List, Get, search) so the action coverage reads as comprehensive rather than generic.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Junip integration") and lists several concrete entity types ("Persons, Organizations, Deals, Activities, Notes, Files"), but the sole verb "Manage" is generic and "and more" is vague filler, so coverage of actual actions is not comprehensive.	3 / 5
Completeness	It states both a "what" (manage Persons, Organizations, Deals, Activities, Notes, Files) and an explicit "when" ("Use when the user wants to interact with Junip data"), but the "when" clause is generic rather than tied to concrete trigger phrases, fitting the anchor where "when" could be more specific.	4 / 5
Trigger Term Quality	Beyond the brand name "Junip", the only trigger phrase is the generic "interact with Junip data"; it omits the natural task terms users would actually say (reviews, ratings, store, products), matching the "one or two generic keywords; missing the natural phrases" anchor.	2 / 5
Distinctiveness Conflict Risk	The branded "Junip integration" phrasing gives it a clear niche with minimal conflict risk against unrelated skills, though the generic CRM-style entity list (Persons, Organizations, Deals) introduces minor overlap risk with sales/CRM skills.	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/junip/SKILL.md
Commit: f484c82

Reviewed: 5 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.