audit-discoverability
Audit whether agents would find and pick an AI plugin or MCP server when a user asks: how its listing and MCP tool descriptions answer target prompts, with a labelled simulated pick against rivals. Use when asked to audit a plugin or MCP server, when agents ignore a plugin, to check prompts people should use it for against rivals, for AEO for plugins, to grade a pasted tool list or tools against a rival's, to check whether an app can be reached in a country, or to fix MCP tool descriptions and annotations such as readOnlyHint. Not for writing store copy.
How do I install this agent skill?
npx skills add https://github.com/theopenapps/plugin-stack --skill audit-discoverabilityIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill audits the discoverability and performance of AI plugins and MCP servers by analyzing their listings and tool descriptions. It utilizes official OpenApps tools (CLI and API) to fetch data and simulates how an AI agent would select tools based on specific user prompts. Security measures include sandboxing simulated agents to prevent access to the host environment and explicit instructions for the AI to treat third-party text as data rather than commands.
- Socketwarn
1 alert: gptSecurity
- Snykwarn
Risk: MEDIUM · 1 issue
What does this agent skill do?
Audit discoverability
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 |
| 1, 3 | references/listing.md |
| 2, 4 | references/tools.md |
| 5 | references/simulated-pick.md |
Steps
- Fix the scope. The plugin, 5-10 target prompts and 3-5 competitors. Done when each is named and at least half the prompts aren't drafted, or the report says coverage is circular.
- Can it be reached at all? Done when the listing, the server and the target country are each marked, with
checked_atprinted beside any stored status. A failed mark is fix #1, and every later step is labelledconditional on fixing reachability. - Audit the listing's words. Done when every target prompt is marked covered or missed, with the competitors that cover it.
- Audit the tools. Read them from
mcp_toolset_get, the repo's server code, ortools/listoutput the user pastes. Done when every tool has a verdict on saying what it does, when to use it, and its annotations. With none of the three, say so in the report and go to step 5. - Run the simulated pick. Done when each prompt has a pick, its reason and a run count, labelled as a simulation.
- Report. Ranked fixes. Done when every fix names a target prompt it should help and every number has its date and basis. If
.agents/plugin-stack.mdexists, addaudit-discoverability: <today>, top fix: <fix>under Runs without asking, in your own words.
Report order
- Any
Degraded:lines, thenThis simulation is not informative for this setif a control failed. Baseline:thebestchart place from the plugin'slistings_searchrow, withmeta.as_of, so the next run has something to compare.- Fixes, ranked: reachability, tool text that risks store review, prompts the plugin won and should have lost, then missed prompts, sourced ones before drafted ones. A tool fix gives the replacement text. A listing fix names the missing words and the field, and leaves the copy to
optimize-listing. With no listing yet, namesubmit-plugin. - Evidence: the coverage line, the tool verdicts, the picks with their label, the real-assistant line and what the simulation can't tell you.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/theopenapps/plugin-stack/audit-discoverability">View audit-discoverability on skillZs</a>