check-agent-compatibility
An agent skill by cursor, from cursor/plugins. Tags: compatibility, configuration, developer-tools, validation.
What it does
Its SKILL.md has no description.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill check-agent-compatibilityOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/agent-compatibility/skills/check-agent-compatibility ~/.claude/skills/check-agent-compatibilitySafety box score
Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a thin orchestration prompt for running repository compatibility checks and summarizing the results. It does not contain scripts, network calls, or file-editing logic, so the main risk is just the agent spending time on four subordinate reviews rather than changing anything on disk.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | `SKILL.md` only describes a workflow; it does not ship shell commands, scripts, or code evaluation. |
| Network access | 0 (none) | No URL fetches, uploads, or remote API calls are defined in the skill text. |
| Filesystem reach | 0 (none) | The skill does not instruct reading or writing outside the repo, and it contains no file-manipulation steps. |
| Secrets & credentials | 0 (none) | It does not ask for tokens, passwords, key files, or `.env` contents. |
| Privilege & persistence | 0 (none) | There is no sudo, install, service registration, or OS/git configuration change in the workflow. |
| Instruction hijack surface | 0 (none) | The text gives workflow instructions like `Use one subagent per task`, but nothing that tries to bypass safeguards, hide behavior, or follow external instructions. |
| Irreversible actions | 0 (none) | The skill only asks for analysis and reporting; it does not push, deploy, send messages, pay, book, or delete anything. |
| Transparency | 0 (none) | All shipped content is readable plain text; there are no binaries, blobs, or decoded-at-runtime payloads. |
Before installing
- Read the referenced subskills (`compatibility-scan-review`, `startup-review`, `validation-review`, `docs-reliability-review`) to confirm they are also read-only.
- Verify that no dependent skill shells out to the network or mutates files outside the repository.
- If you want to gauge overhead, try it once in a scratch repository first.
Rated 2026-10-20 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- agent-compatibility/skills/check-agent-compatibility/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- principle-encode-lessons-in-structure — Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
- cli-for-agents — Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors.
- create-verification-skill — Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
- review-plugin-submission — Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.
- setup-pstack — Configure which models pstack uses per role and at what reasoning budget.
- find-docs — Retrieves up-to-date documentation, API references, and code examples for any developer technology.