Name: giantcampaign
Rating: 60 (1 reviews)
Author: membranedev

giantcampaign

GiantCampaign integration. Manage Leads, Persons, Organizations, Deals, Projects, Activities and more. Use when the user wants to interact with GiantCampaign 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/giantcampaign/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 a strong, executable integration guide with a clear install-to-action workflow and excellent command coverage. Its main weaknesses are mild verbosity in the intro/explainer and the absence of an explicit result-validation or error-recovery feedback loop after running actions.

Suggestions

Trim the opening marketing-platform explainer and the generic 'Use action names and parameters as needed' line; assume Claude knows what a marketing automation tool is.

Add an explicit validation/feedback step after running actions (e.g. 'Check the output field; on error, inspect the error object and retry or surface clientAction to the user') to close the loop on the action-run workflow.

Consider moving the full Popular-actions table into a references file and keeping only a few representative examples inline, to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable CLI snippets, but the marketing-platform explainer ('GiantCampaign is a marketing automation platform that helps businesses...'), the generic 'Use action names and parameters as needed', and some lightly padded prose could be trimmed.	3 / 5
Actionability	Fully executable copy-paste commands cover the common cases — install, login (incl. headless completion), connection ensure, polling with --wait, action list/run with --input JSON, and the proxy request — each with concrete flags and expected output fields.	5 / 5
Workflow Clarity	Clear sequenced flow (install → login → connection ensure → poll until READY → list/run actions) with polling checkpoints and a state-by-state branching guide; short of 5 because there is no explicit validation of action results or error-recovery feedback loop after a run.	4 / 5
Progressive Disclosure	Well-organized sections (Overview, Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) with a useful inline action table; no bundle files exist, and the bulk is appropriately inline, though the full Popular-actions table could live in a reference file.	4 / 5
	Total	16 / 20 Passed

Description

66%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 app and lists concrete data entities plus a 'Use when' clause, but relies on the generic verb 'Manage' throughout and a broad trigger rather than sharp, varied trigger phrases. It is competent but not exemplary.

Suggestions

Replace the repeated generic verb 'Manage' with several distinct concrete actions (e.g. 'Create and update subscribers, launch and pause campaigns, build mailing lists') so capabilities read as specific actions.

Expand the 'Use when' clause with concrete natural triggers and synonyms users actually say, e.g. 'Use when the user wants to manage GiantCampaign subscribers, campaigns, mailing lists, leads, or deals.'

Add the file/identifier extensions or common synonyms (e.g. 'subscribers', 'campaigns', 'mailing lists') to improve keyword coverage and reduce overlap with generic CRM skills.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete entity types ('Manage Leads, Persons, Organizations, Deals, Projects, Activities and more'), but each action is the single generic verb 'Manage' with no breakdown, leaving coverage non-comprehensive.	3 / 5
Completeness	Has a clear 'what' ('Manage Leads, Persons, Organizations...') and an explicit 'when' ('Use when the user wants to interact with GiantCampaign data'); the 'when' is present but generic rather than tied to concrete trigger phrases.	4 / 5
Trigger Term Quality	'GiantCampaign data' is a strong natural trigger and entity terms like Leads, Deals, Projects are plausible user language; missing common synonyms or file extensions, so not a full 5.	4 / 5
Distinctiveness Conflict Risk	The named app 'GiantCampaign' makes it fairly distinct, but the broad entity list and generic 'Manage... data' framing overlap with general CRM/marketing skills, so conflict risk remains moderate.	3 / 5
	Total	14 / 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/giantcampaign/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.