Name: campaign-cleaner
Rating: 60 (1 reviews)
Author: membranedev

campaign-cleaner

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

Quality

70%

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/campaign-cleaner/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 a strong, actionable integration guide built around copy-paste-ready Membrane CLI commands, a useful actions table, and a well-sequenced connection workflow with real state-handling checkpoints. Its main weaknesses are minor conciseness trims, an unlabeled "Step 2" in the workflow, and the absence of validation guidance or caution around destructive actions like delete-campaign.

Suggestions

Add an explicit "Step 2" header (e.g. over "Searching for actions") so the "skip to Step 2" references resolve, and label 1a/1b consistently.

Add a brief validation/caution note around running actions — especially destructive ones like delete-campaign — e.g. confirm the target campaign id and check the action's output/error field before proceeding.

Trim marketing prose ("This helps improve campaign performance and reduce wasted ad spend") and the "so you can focus on the integration logic rather than auth plumbing" aside to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is predominantly lean commands, tables, and operational state-handling detail, with only minor over-explanation that could be trimmed (e.g. the marketing line "This helps improve campaign performance and reduce wasted ad spend" and "so you can focus on the integration logic rather than auth plumbing"), matching the efficient-with-minor-trims anchor.	4 / 5
Actionability	It provides copy-paste-ready, executable commands for every common case — install, login (incl. headless completion), connection ensure, polling, action list/run with JSON input, and proxy requests — plus a concrete popular-actions table with keys and descriptions, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The connect-to-ready flow is a clearly sequenced multi-step process with explicit validation checkpoints and a feedback loop (poll with --wait, branch on READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR, re-poll after user action), but it references an unlabeled "Step 2" and offers no result-validation or caution for destructive actions like delete-campaign, leaving minor validation gaps that keep it below 5.	4 / 5
Progressive Disclosure	The content is well-organized into clear sections (Overview, Working with, Install, Authentication, Connecting, Searching, Popular actions, Running actions, Proxy, Best practices) with reference material appropriately inline; no bundle files exist and only external URLs are linked, so structure is good with minor organization gaps (the thin Overview and the dangling "Step 2" reference).	4 / 5
	Total	17 / 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 pairs a "what" with an explicit "Use when" trigger and leverages a distinctive app name, but its capability language is generic boilerplate ("manage data, records, and automate workflows") rather than concrete operations, and it lacks the natural trigger phrases a real user would say.

Suggestions

Replace the generic "Manage data, records, and automate workflows" with concrete actions the integration performs, e.g. "Submit campaigns for spam/click-fraud analysis, retrieve PDF analysis reports, check campaign status, and list saved campaigns."

Add natural trigger terms users actually say — "click fraud", "bot traffic", "ad spend", "campaign analysis" — alongside "Campaign Cleaner" so the skill activates on real user phrasing.

Tighten the "Use when" clause to name concrete intents (e.g. "Use when the user wants to analyze or manage Campaign Cleaner campaigns, check processing status, or pull analysis reports") rather than the vague "interact with Campaign Cleaner data".

Dimension	Reasoning	Score
Specificity	The description lists "Manage data, records, and automate workflows" — these are generic, abstract action phrases rather than concrete operations (no equivalents to "extract text" or "fill forms"), matching the anchor that names the domain but uses minimal/generic actions.	2 / 5
Completeness	Both halves are present — a "what" ("Manage data, records, and automate workflows") and an explicit "Use when the user wants to interact with Campaign Cleaner data" trigger — but the "what" is generic boilerplate rather than concrete, so it sits at the anchor where both exist yet could be more specific, below the concrete-trigger level of 5.	4 / 5
Trigger Term Quality	It anchors on the distinctive app name "Campaign Cleaner" and terms like "data" and "records", but misses the natural phrases a marketer would actually say (click fraud, bot traffic, campaign performance) and includes no synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	The specific app name "Campaign Cleaner" in the trigger gives it a clear, distinct niche with low conflict risk, but the generic "Manage data, records, and automate workflows" framing leaves minor overlap risk with broad data-management 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/campaign-cleaner/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.