Name: drip
Rating: 55.2 (1 reviews)
Author: membranedev

drip

Drip integration. Manage Persons, Organizations, Deals, Activities, Notes, Files and more. Use when the user wants to interact with Drip data.

Quality

62%

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/drip/SKILL.md

Quality

Content

57%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 concrete Membrane CLI commands and a useful action catalog, and the connection workflow is well-sequenced with state checkpoints. Its weaknesses are mild marketing padding, missing validation for batch/destructive actions, and a monolithic structure with no file splitting.

Suggestions

Trim the promotional opening ('Drip is an e-commerce CRM designed to help businesses personalize marketing automation...') and the redundant 'Drip Overview' tree to tighten token efficiency.

Add an explicit verification/confirmation step before running batch or destructive actions (e.g., confirm count, review a dry-run, and check the response status), so the workflow can exceed the batch-cap of 3.

Move the full Popular actions table and the proxy request flag reference into a separate reference file (e.g. references/actions.md) and link to it from SKILL.md, keeping the main skill a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with dense command examples, but includes unnecessary marketing framing ('Drip is an e-commerce CRM designed to help businesses personalize marketing automation') and a redundant 'Drip Overview' tree that restates entities, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It provides concrete, executable CLI commands throughout (membrane connection ensure, action list, action run, request) with real flags and a 20-row action table, but uses unsubstituted placeholders (CONNECTION_ID, <actionId>, <id>) and gives no example input payloads, matching 'mostly executable guidance; concrete code with minor gaps' rather than fully copy-paste-ready 5.	4 / 5
Workflow Clarity	The connection flow has a clear state-driven sequence with checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and a poll-after-action feedback loop, but running actions — including batch and destructive ones (create-or-update-subscribers-batch, unsubscribe-subscribers-batch) — has no validation or verification step, which caps workflow clarity at 3 per the batch-operation rule.	3 / 5
Progressive Disclosure	The skill is well-organized with section headers but is a single ~190-line file with no bundle references, inlining the full Popular actions table and proxy flag reference that could live in separate files; since it exceeds the 50-line simple-skill exception, this fits 'some structure but content that should be separate is inline'.	3 / 5
	Total	13 / 20 Passed

Description

67%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 clearly identifies the Drip product and provides both a capability list and a use-trigger, but the 'when' clause is generic and the listed entities do not reflect Drip's actual data model (subscribers, campaigns, workflows). It is solid but imprecise, scoring mid-range across dimensions.

Suggestions

Replace the generic CRM entity list with Drip's real objects — e.g. 'Manage Subscribers, Campaigns, Workflows, Broadcasts, Tags, Events, and Forms' — so the description reflects what the skill actually does.

Make the trigger clause concrete: 'Use when the user wants to manage Drip subscribers, campaigns, workflows, or email automation, or interact with Drip data.'

Add natural synonyms users say (subscribers, email campaigns, workflows, automation) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete entities ('Persons, Organizations, Deals, Activities, Notes, Files') rather than vague language, but the trailing 'and more' leaves minor coverage gaps, fitting the 'lists several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Both 'what' (Manage Persons, Organizations, Deals, Activities, Notes, Files) and 'when' ('Use when the user wants to interact with Drip data') are explicitly present, but the trigger clause is generic rather than concrete, matching the 'has both what and when; when could be more explicit' anchor and not the fully concrete 5.	4 / 5
Trigger Term Quality	It includes the product name 'Drip' and the phrase 'interact with Drip data', but offers few natural synonyms users would actually say, and the entity terms (Persons, Organizations, Deals) do not match Drip's real subscriber/campaign vocabulary, so it sits at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'Drip integration' names a specific product giving it a clear niche and low conflict risk, but the generic CRM entity list (Persons, Organizations, Deals) overlaps with other CRM skills, so it is 'mostly distinct; minor overlap risk' rather than the minimal-risk 5.	4 / 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/drip/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.