submit-plugin
Skill4 starsChanged 10 days agoMITView on GitHub
Submit an AI plugin to the ChatGPT, Claude or Cursor stores: a store-ready kit with first-listing copy, assets, reviewer answers and the choices that can't change later, such as MCP origin, slug and countries. Use when preparing a plugin for submission, checking a repo is ready before uploading a plugin zip, asking how to get a plugin or MCP server listed in a store or connectors directory, or after a rejection.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- github/plugin-marketplace-startertheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- github/plugin-marketplace-starter★ 7same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- audit-discoverabilitySkill
- design-widgetsSkill
- find-openingSkill
- optimize-listingSkill
- plugin-stackSkill
- track-launchSkill
- watch-competitorsSkill
The file
Files
Submit plugin
A question such as "how do I figure out what's wrong?" or "what do I need?" is a request to run these steps on this repo, so run them instead of explaining them.
Read at each step
| Step | Read |
| 1 | .agents/plugin-stack.md if present, references/data.md |
| 2-4 | references/stores/<store>.md for each store in scope |
| 4 | references/kit.md |
A store with no file here: work from its own docs and say the report has no checked notes for it.
Steps
Fix the scope. List the working directory first, then read its README and manifests:
.codex-plugin/plugin.json,.claude-plugin/plugin.json,.cursor-plugin/plugin.json,.mcp.json, and any server code they name. Say what you found before asking anything, and ask only what they don't answer. The plugin, the stores, and whether this is a first submission or a rejection. Done when each is named, or the folder is confirmed empty and the user has said where the plugin is.Rejection or a stuck review: read the reviewer's reasons, keep the choices already made, skip steps 2 and 4, and run step 3 from the store file's "Rejected or stuck" section. Step 3 is then done when each reason maps to a requirement and a change, or the cause is marked unknown where the store gives none, and one next action is stated.
- Lock the permanent choices. Done when the user has confirmed each choice the store won't let them change later.
- Check readiness. Mark each requirement in the store file pass, fail or can't-tell, and name the evidence.
passneeds something run or opened: the manifest's actual value, atools/listcall against the exact origin being locked from a client with no stored credentials, the sign-in flow in a clean browser session, the listed URLs loading. Reading the code earns only can't-tell. Done when every requirement has a mark and its evidence. - Build the kit. Copy drawn from the plugin's closest live listings, even when a kit already exists. Done when every kit item has content or a named owner, and the hand-off names the listings you read.
- Hand off. Done when every fail, every can't-tell and every manual store step is one numbered action, in order. The user submits; you prepare. Once submitted,
track-launchcompares the wait with apps that went live. If.agents/plugin-stack.mdexists, addsubmit-plugin: <today>, stores: <stores>under Runs without asking, in your own words.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.