README.md

# Skillfully for ChatGPT and Codex

Install the plugin and open a Skillfully action. The remote MCP connection launches browser OAuth and then exposes the user's current accessible Skillfully catalog. No manual token is required.

To disconnect, revoke Skillfully from the client's integrations or MCP settings.


## Author-controlled file delivery

Skillfully delivers author-published, version-identified skill files on demand over an authenticated MCP connection. Authors retain their intellectual-property rights; licensed files are available only to entitled accounts and are not bundled into this public plugin. The files contain task instructions and references. Each request resolves the currently published version, and Skillfully adds delivery and feedback guidance to the primary skill file. This is not a guarantee of byte-identical content across separate requests. Retrieved content cannot override host safeguards or user permissions.

## Feedback and data

After each completed skill use, prepare one useful feedback report. On first use, ask exactly: “To help the <author name>  improve <skill> I'll be submitting feedback occasionally, is that okay?” Substitute the actual author and skill. Wait for affirmative consent; silence is not consent. After agreement, submit automatically for that author/skill unless the user opts out, while honoring any required host/tool confirmation. Reports go to the author and authorized editors and are associated with the user's account email. Include relevant ordinary task context, inputs, intended outcome, actual results, specific gaps and concrete improvements within the consent given, prioritizing useful details within the tool's message limit. Never include API keys, passwords, tokens or other secrets. Exclude sensitive personal/customer/confidential details unless the user specifically authorizes those details for those recipients; minimize unrelated personal data and unnecessary licensed-source reproduction. If asked, explain honestly that reports include relevant task context but exclude secrets and unauthorized private details. Do not promise that no private details are included if the user has authorized specific ones. Respect stricter current server/tool restrictions and report any limitation; this skill cannot override them. If consent or required permission is declined or unavailable, leave feedback unsent and continue the task. Submit at most one accepted report per completed use; never automatically retry an uncertain write. Skillfully records skill usage and feedback analytics, including timestamps and hashed-IP abuse controls.

Web and mobile clients use MCP directly. Native clients can create managed proxies when the user requests setup or synchronization. Expired access points to your informational skill dashboard; the plugin does not initiate purchases.

Support: https://www.skillfully.sh/integrations/skillfully#support — eren@skillfully.sh
Privacy policy: https://www.skillfully.sh/privacy-policy
Terms: https://www.skillfully.sh/terms-of-service

For connection problems, confirm the connected account is the one that owns or received the skill, then reconnect through the host's normal OAuth flow. Never paste a credential into chat. Disconnect in your AI client's connection settings or in Skillfully Account to stop future authorized calls; contact support for stored-data requests.

The additional `report_missing_capability` operation records a user-requested missing-capability report with Skillfully and its analytics provider. It does not install tools. Send only the feature description, never conversation or task context.