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

Blog Docs Log in Get started

manychat

ManyChat integration. Manage Organizations. Use when the user wants to interact with ManyChat 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/manychat/SKILL.md

Quality

Content

71%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 highly actionable, with executable commands and a clear connection-state feedback loop, but is mildly verbose in places and ships as a single monolithic file with no progressive disclosure to separate reference materials. A broken 'Step 2' cross-reference is the main workflow-clarity blemish.

Suggestions

Move the entity list, proxy flag table, and clientAction schema into one-level-deep reference files (e.g. ENTITIES.md, PROXY.md) and link to them from SKILL.md.

Fix the 'skip to Step 2' reference by either adding an explicit '## Step 2' heading or relabeling it to the actual target section.

Trim editorializing (the ManyChat marketing-automation intro, 'burn less tokens', 'focus on the integration logic') to keep the body lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient command-driven prose, but includes removable padding such as the opening paragraph explaining what ManyChat is and editorializing like 'so you can focus on the integration logic rather than auth plumbing' and 'This will burn less tokens'.	3 / 5
Actionability	It provides copy-paste-ready commands for every stage (install, login, connection ensure, action list/run, request) with concrete flags, a proxy flag table, and JSON-output examples covering the common cases.	5 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-until-ready → search → run sequence with a real feedback loop on connection state (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but 'skip to Step 2' references a Step 2 heading that does not exist, a minor validation/clarity gap.	4 / 5
Progressive Disclosure	The file has reasonable section headers, but at ~150 lines with no bundle files it keeps everything inline (full entity list, proxy flag table, clientAction schema) that could live in one-level-deep reference files; no external references are signaled.	3 / 5
	Total	15 / 20 Passed

Description

61%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 has a clear, distinct niche and an explicit 'Use when' clause, but its capability list is thin and generic ('Manage Organizations') rather than naming the concrete ManyChat entities the skill exposes. Trigger-term coverage relies on the single keyword 'ManyChat' with no synonyms or feature names.

Suggestions

Replace 'Manage Organizations' with concrete capabilities, e.g. 'Manage Flows, Broadcasts, Subscribers, Tags, and Custom Fields in ManyChat.'

Expand the 'Use when' clause with natural trigger phrases users would say, such as 'Use when the user wants to send a ManyChat broadcast, manage subscribers, or trigger a Flow.'

Add synonyms or feature-level keywords (e.g. 'chatbot', 'messaging automation', 'Flow', 'Subscriber') so the description matches varied user phrasings.

Dimension	Reasoning	Score
Specificity	The description names the domain ("ManyChat integration") but the only action offered ("Manage Organizations") is minimal and generic, and does not reflect the concrete entities the skill actually exposes (Flow, Broadcast, Subscriber, etc.).	2 / 5
Completeness	It states both a what ("ManyChat integration. Manage Organizations.") and an explicit when ("Use when the user wants to interact with ManyChat data."), but the what is generic and the when could name concrete triggers.	4 / 5
Trigger Term Quality	"ManyChat" is a specific natural keyword a user would say, but it is merely repeated ("ManyChat integration", "interact with ManyChat data") with no synonyms, feature names, or variations.	3 / 5
Distinctiveness Conflict Risk	ManyChat is a specific named platform, so the trigger ("interact with ManyChat data") carves a clear niche with minimal risk of firing for an unrelated skill.	5 / 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/manychat/SKILL.md
Commit: f484c82

Reviewed: 6 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.