Name: sifter
Rating: 61.6 (1 reviews)
Author: membranedev

sifter

Sifter integration. Manage Persons, Organizations, Deals, Leads, Projects, Activities and more. Use when the user wants to interact with Sifter data.

Quality

73%

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/sifter/SKILL.md

Quality

Content

67%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.

An actionable, well-structured integration guide with executable commands and a solid connection-readiness workflow. Its weaknesses are explanatory padding about Membrane internals and a couple of structural clarity issues (dangling step reference, invocation inconsistency).

Suggestions

Trim the prose explaining Membrane's internal behavior (URL normalization, auto-built connectors) to lift conciseness — keep only what affects the command outcome.

Resolve the dangling "skip to Step 2" reference by labeling the steps explicitly, and pick one canonical invocation (either `membrane` or `npx @membranehq/cli@latest`) and use it consistently.

Dimension	Reasoning	Score
Conciseness	Mostly command-driven and efficient, but several passages explain Membrane internals (e.g., "The URL is normalized to a domain and matched against known apps... a connector is built automatically") that Claude does not need to act.	3 / 5
Actionability	Concrete copy-paste commands cover login, connection, action search/run, and proxying, plus a flags table; minor gaps are placeholder values and an inconsistent `membrane` vs `npx @membranehq/cli` invocation style.	4 / 5
Workflow Clarity	The install → login → connect → search → run sequence is clear with an explicit connection state-machine and re-poll feedback loop, but the dangling "skip to Step 2" reference introduces a minor navigation gap.	4 / 5
Progressive Disclosure	A single well-sectioned SKILL.md with no bundle files and clear headers; being over 50 lines with the flags table and state detail inlined keeps it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

78%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.

A solid description that names concrete Sifter entities and gives an explicit trigger clause tied to a specific product, minimizing conflict risk. The main gap is that the "when" clause is somewhat generic and the action verbs are limited to "Manage".

Suggestions

Replace "Manage ... and more" with a few distinct verbs (e.g., create, update, search) to raise specificity toward the anchor-5 example.

Make the "Use when" clause task-specific (e.g., "Use when the user wants to create or search Sifter issues, milestones, or projects") to sharpen the trigger.

Dimension	Reasoning	Score
Specificity	"Manage Persons, Organizations, Deals, Leads, Projects, Activities and more" lists several concrete managed entities, but relies on a single verb so coverage is not fully comprehensive like the anchor-5 example.	4 / 5
Completeness	It states both a clear "what" (manage named Sifter entities) and an explicit "when" ("Use when the user wants to interact with Sifter data"), but the trigger could be more task-specific.	4 / 5
Trigger Term Quality	"Sifter" and "interact with Sifter data" give good keyword coverage of the natural product term users would say, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	The named product "Sifter" with a distinct, product-specific trigger creates a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 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/sifter/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.