Name: blink
Rating: 58.4 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

blink

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

Quality

67%

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/blink/SKILL.md

Quality

Content

72%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 across the whole Membrane lifecycle and good connection-state feedback loops. It loses points for lacking validation steps before destructive actions and for inlining bulk reference material that has no separate-file structure.

Suggestions

Add an explicit validation/confirmation step before running destructive actions (delete, archive) — e.g., confirm the target ID or run a GET first — to lift workflow clarity above the destructive-operation cap.

Move the 15-row popular-actions table into a references file (e.g. ACTIONS.md) and link to it from SKILL.md, keeping only a few representative examples inline.

Trim narrative sentences such as "so you can focus on the integration logic rather than auth plumbing" that restate what the commands already show.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable commands and tables with light prose; only minor sentences like "so you can focus on the integration logic rather than auth plumbing" are trimmable, fitting the efficient-with-minor-over-explanation anchor.	4 / 5
Actionability	It provides copy-paste-ready commands for the full lifecycle (install, login, connection ensure, polling, action list/run, request proxy) with documented flags and a concrete action-key table, matching the fully-executable anchor covering common cases.	5 / 5
Workflow Clarity	The connection workflow is well sequenced with state-polling feedback loops, but destructive actions (e.g. "Delete User Linked Account", "Archive Feed Event") are run with no validation/verification step, triggering the destructive-operation cap at 3.	3 / 5
Progressive Disclosure	Sections are clearly headed, but with no bundle files the entire 15-row action table and full CLI reference are inlined in SKILL.md rather than split into referenced files, matching the some-structure-but-inline-content anchor.	3 / 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 answers both what and when in third person, but the capabilities are described in generic verbs ("manage data, records") rather than concrete Blink-specific actions. Trigger guidance is present yet lacks natural synonym coverage.

Suggestions

Replace generic verbs with concrete Blink capabilities (e.g., send feed events, manage linked accounts, fetch users) to raise specificity.

Add natural trigger synonyms users would say, such as "on-call alerts", "incident automation", or "Blink workflows", beyond just "interact with Blink data".

Tie the "Use when" clause to the concrete actions listed so the trigger feels specific rather than boilerplate.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the Blink domain and a couple of actions, but the actions are generic ("manage data") rather than concrete capabilities, matching the anchor for domain + 1-2 actions that are not comprehensive.	3 / 5
Completeness	It states both what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with Blink data"), but the trigger is somewhat generic and could be more specific, matching the anchor for both present with an improvable "when".	4 / 5
Trigger Term Quality	The trigger "Use when the user wants to interact with Blink data" surfaces the relevant keyword "Blink data" but lacks natural synonyms or variations a user might say, fitting the anchor for some relevant keywords with missing variations.	3 / 5
Distinctiveness Conflict Risk	Naming a specific app ("Blink integration") plus a Blink-specific trigger creates a mostly-distinct niche with only minor overlap risk from generic verbs, fitting the anchor for mostly distinct with minor overlap.	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/blink/SKILL.md
Commit: f484c82

Reviewed: 3 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.