Name: customgpt
Rating: 56.8 (1 reviews)
Author: membranedev

customgpt

CustomGPT integration. Manage Projects, Users, Roles, Goals, Filters. Use when the user wants to interact with CustomGPT data.

Quality

64%

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/customgpt/SKILL.md

Quality

Content

63%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 content is a practical, executable guide to driving CustomGPT via the Membrane CLI with a clear connection workflow and feedback loops, but it is padded with marketing prose and inlines a large action reference that would benefit from a separate file. Trimming the intro and externalizing the actions table would improve both conciseness and progressive disclosure.

Suggestions

Remove the marketing-style intro paragraph ('CustomGPT allows users to create custom chatbots...') and the filler line 'Use action names and parameters as needed.' — Claude does not need CustomGPT's market positioning.

Move the 20-row Popular actions table into a references/actions.md file and link to it, keeping only a few representative examples inline to improve progressive disclosure.

Fix the dangling 'skip to Step 2' reference by labeling the searching/running sections as Step 2, or reword to 'proceed to Searching for actions'.

Dimension	Reasoning	Score
Conciseness	Mostly efficient CLI documentation, but it includes unnecessary padding such as the marketing-fluff intro ('CustomGPT allows users to create custom chatbots... used by businesses and individuals'), the verbose Knowledge Source tree, and filler like 'Use action names and parameters as needed.' — fitting 'mostly efficient but includes some unnecessary explanation' rather than the lean anchor 4.	3 / 5
Actionability	Concrete copy-paste commands are provided throughout (npm install, membrane login, connection ensure, action list/run, request), plus a Popular actions table — but the run examples use generic placeholders (<actionId>, '{"key": "value"}') with no worked end-to-end example using a real action, matching 'mostly executable; minor gaps' instead of the fully-worked anchor 5.	4 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-until-ready → search → run sequence with state-based branching (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR) and an explicit feedback loop ('poll again ... to check if the state moved to READY'), but the 'skip to Step 2' reference points to a Step 2 that is never labeled, a minor validation/sequencing gap matching anchor 4 rather than 5.	4 / 5
Progressive Disclosure	The body is well-sectioned with headers, but it is a single ~170-line monolith with no bundle files and no external references; large reference-like content (the 20-row Popular actions table and proxy-options table) is inlined rather than split into separate files, fitting 'some structure but content that should be separate is inline' rather than the well-split anchor 4.	3 / 5
	Total	14 / 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 cleanly states what and when and is highly distinct thanks to the named CustomGPT niche, but its action verbs are generic ('Manage') and its trigger phrase lacks concrete synonyms. Strengthening the trigger with product-specific terms like 'chatbots' or 'projects' would lift the weaker dimensions.

Suggestions

Replace the generic 'Manage Projects, Users, Roles, Goals, Filters' with varied concrete verbs (e.g. 'Create, update, and delete CustomGPT projects, conversations, and knowledge sources').

Expand the 'Use when' clause with concrete trigger terms users would say, e.g. 'Use when the user wants to manage CustomGPT chatbots, projects, agents, or conversations.'

Add common synonyms/file-format hints (e.g. 'custom GPT', 'CustomGPT projects') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'Manage Projects, Users, Roles, Goals, Filters' name several concrete resources in the CustomGPT domain, but the only action verb is the generic 'Manage', so coverage is concrete in scope yet minimal in distinct actions — matching the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Both 'what' ('CustomGPT integration. Manage Projects, Users, Roles, Goals, Filters.') and an explicit 'when' ('Use when the user wants to interact with CustomGPT data.') are present, but the 'when' is generic rather than concrete trigger phrases, matching 'has both what and when; when could be more explicit' instead of the concrete-trigger anchor 5.	4 / 5
Trigger Term Quality	The trigger 'Use when the user wants to interact with CustomGPT data' includes the product name but only one generic phrase ('interact with CustomGPT data'), missing common synonyms like 'chatbot', 'custom GPT', or 'projects' — fitting 'some relevant keywords but missing common variations' rather than the good-coverage anchor 4.	3 / 5
Distinctiveness Conflict Risk	'CustomGPT integration' targets a uniquely named product with a product-specific trigger ('interact with CustomGPT data'), giving it a clear niche with minimal overlap risk — matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 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/customgpt/SKILL.md
Commit: f484c82

Reviewed: ~15 hours 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.