Name: red-sift
Rating: 59.2 (1 reviews)
Author: membranedev

red-sift

Red Sift integration. Manage data, records, and automate workflows. Use when the user wants to interact with Red Sift 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/red-sift/SKILL.md

Quality

Content

68%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 — concrete, copy-paste-ready commands covering connect, search, run, and proxy flows, plus a genuine polling feedback loop for connection state. It loses points for a marketing-style intro and editorial padding, and for lacking any validation/verification step around potentially destructive action runs and proxy calls.

Suggestions

Trim the introductory product-marketing paragraph and editorializing sentences ('focus on the integration logic', 'burn less tokens') to pure operational guidance.

Add an explicit verify/dry-run step before running actions or proxy requests that may be destructive (e.g. global suppression changes, DELETE calls), with a confirm-and-recheck feedback loop.

Resolve the dangling 'Step 2' reference by either labeling the next section 'Step 2: Search and run actions' or removing the step labels so the sequence is unambiguous.

Dimension	Reasoning	Score
Conciseness	The bulk is an efficient command reference, but a marketing-style intro ('Red Sift is a cloud email security platform that helps organizations protect themselves from phishing...') and editorializing ('focus on the integration logic rather than auth plumbing', 'burn less tokens') are unnecessary explanation that could be tightened, matching anchor 3.	3 / 5
Actionability	The body is fully executable and copy-paste ready across the common cases — install, login (incl. headless), connection ensure/get with --wait, action list/run with --input, and a proxy request flag table — matching the anchor 5 example of specific commands covering common cases.	5 / 5
Workflow Clarity	The connection flow is well-sequenced with an explicit polling feedback loop (BUILDING -> READY/CLIENT_ACTION_REQUIRED -> re-poll), but the skill runs actions and proxy requests (incl. DELETE) against a security platform with no validation/verification step before or after; the destructive/batch cap holds this at 3.	3 / 5
Progressive Disclosure	The body is well-organized into clear sections (Overview, install, auth, connecting, searching, actions, proxy, best practices) with no nested references and no buried material; some inline reference content (proxy flag table, clientAction state machine) is appropriately kept in a single-page integration guide, placing it at anchor 4.	4 / 5
	Total	15 / 20 Passed

Description

68%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 names a distinct niche (Red Sift) with an explicit Use-when trigger and good brand-keyword coverage, but the 'what' relies on generic verbs (manage data, records, workflows) rather than concrete capabilities. Tightening the action list and adding domain-specific trigger terms like DMARC would raise specificity and trigger quality.

Suggestions

Replace generic verbs with concrete Red Sift capabilities, e.g. 'Configure DMARC, manage OnDMARC domains and reports, review alerts and global suppression'.

Add natural problem-area trigger terms — 'DMARC', 'OnDMARC', 'email security', 'phishing' — so users describing the problem match the skill.

Make the 'what' as specific as the 'when' so both halves of the description are concrete rather than the action half being generic.

Dimension	Reasoning	Score
Specificity	The domain is named ('Red Sift integration') but the action verbs are generic — 'Manage data, records, and automate workflows' mirrors anchor 2 ('Processes PDF files'), naming the domain with only minimal/generic actions rather than concrete capabilities.	2 / 5
Completeness	Both 'what' (manage data/records/automate workflows) and 'when' (Use when the user wants to interact with Red Sift data) are present and explicit; the 'when' is clear but generic, so it sits at anchor 4 rather than 5.	4 / 5
Trigger Term Quality	'Red Sift' appears as the natural brand keyword a user would say, reinforced by an explicit 'Use when the user wants to interact with Red Sift data' trigger; coverage is good but misses common problem-area variations like 'DMARC', 'OnDMARC', or 'email security'.	4 / 5
Distinctiveness Conflict Risk	The description is tied to a specific named product (Red Sift) with a product-scoped trigger clause, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	15 / 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/red-sift/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.