Name: phantombuster
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

phantombuster

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

Quality

66%

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/phantombuster/SKILL.md

Quality

Content

75%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 executable commands and a well-structured connection workflow, weakened only by a marketing-flavored intro and the absence of result verification after running actions.

Suggestions

Trim the marketing intro and filler phrases ('so you can focus on…', 'Use action names and parameters as needed.') to recover tokens.

Add an explicit verification step after 'membrane action run', e.g. check the output field and handle empty/error results before reporting success.

Consider moving the Popular actions table into a references file to keep SKILL.md a lean overview with a one-level pointer.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean command reference, but the marketing intro ('used by marketers, sales teams, and growth hackers') and filler like 'so you can focus on the integration logic rather than auth plumbing' add unnecessary tokens.	3 / 5
Actionability	It provides copy-paste ready commands for install, login, connection ensure, action list/run, and proxy requests, plus a Popular actions table with concrete action keys covering the common cases.	5 / 5
Workflow Clarity	The connection setup is a clear sequenced state machine with polling feedback loops and explicit handling of READY/BUILDING/CLIENT_ACTION_REQUIRED/error states, though running actions lacks an explicit output-validation checkpoint.	4 / 5
Progressive Disclosure	No bundle files exist; the single SKILL.md is organized with clear section headers and no nested references, though the Popular actions reference table is inlined rather than split out.	4 / 5
	Total	16 / 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 identifies the platform and provides an explicit use-when trigger, but its action language is vague and it lacks natural trigger synonyms beyond the brand name.

Suggestions

Replace generic verbs with concrete Phantombuster capabilities, e.g. 'Extract leads, scrape social profiles, and launch automation agents'.

Expand the trigger clause with natural phrases users say, e.g. 'Use when the user mentions lead generation, social media scraping, or Phantombuster agents'.

Avoid circular phrasing like 'interact with Phantombuster data' in favor of specific tasks that signal when to load the skill.

Dimension	Reasoning	Score
Specificity	The description names the domain (Phantombuster) but the actions ('Manage data, records, and automate workflows') are generic and abstract rather than concrete capabilities like lead extraction or social scraping.	2 / 5
Completeness	It states both what it does and includes an explicit 'Use when the user wants to interact with Phantombuster data' trigger, though the when clause is generic and could be more specific.	4 / 5
Trigger Term Quality	It relies on the single brand keyword 'Phantombuster' with no natural synonyms, task phrases, or variations a user might say beyond the brand name.	3 / 5
Distinctiveness Conflict Risk	Tying the trigger to the specific Phantombuster platform gives it a clear niche with minimal conflict risk, though generic terms like 'data' and 'workflows' leave minor overlap with other automation 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/phantombuster/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.