# Manage skills across Claude Code, Codex, and Cursor

> Use one source of truth to manage SKILL.md workflows across Claude Code, Codex, and Cursor without confusing portability with automatic synchronization.

- Canonical URL: https://www.skillsboard.sh/guides/manage-skills-across-claude-codex-cursor
- Markdown URL: https://www.skillsboard.sh/guides/manage-skills-across-claude-codex-cursor.md
- Publisher: Skills Board (https://www.skillsboard.sh)
- Published: 2026-07-22
- Last updated: 2026-08-16
- Topics: team operations, skill sharing, compatibility, mixed-agent teams

Claude Code, Codex, and Cursor can all work with reusable skills, but “supported” does not mean “kept in sync.” A durable team setup separates the shared skill source from each agent’s installation and discovery rules.

## In short

To share skills across Claude Code, Codex, and Cursor, keep one canonical SKILL.md source and document how each agent installs, discovers, and invokes it. Test every agent path with the same fixture, then share the compatibility record. Do not maintain separate canonical copies or assume updates sync automatically.

## Core principle

One canonical source. One visible team entry. Explicit setup for every agent path.

## Problem

Mixed-agent teams usually fail in one of two ways: they maintain three unrelated skill collections, or they assume one folder will behave identically everywhere. The safer model is one canonical artifact, one team library record, and a thin, tested adapter for each agent surface.

## Standardize the layers, not every implementation detail

The common layer is the skill’s purpose, source, owner, and SKILL.md workflow. Agent-specific installation, discovery, invocation, and administrative controls remain explicit adapters that your team verifies against current vendor documentation.

## Comparison

| Layer | Team standard | Agent-specific adapter |
| --- | --- | --- |
| Skill artifact | One canonical SKILL.md plus versioned scripts, templates, and references. | Confirm which bundled resources and extensions each agent supports before rollout. |
| Discovery | One shared library record explains when the skill should be used. | Claude Code, Codex, and Cursor can expose skills differently by product, version, workspace, or project. |
| Installation | Keep the reviewed source and intended version stable. | Document the current supported install or access path for each agent instead of inventing a universal command. |
| Invocation | Use the same task fixture and expected output in compatibility tests. | Record whether the skill is selected automatically, invoked explicitly, or constrained by local settings. |
| Updates | Review changes at the canonical source and publish one new library state. | Refresh or reinstall through each tested agent path; portability alone does not perform this step. |

## A cross-agent rollout that stays understandable

Pilot one skill across the three agents before generalizing the process. The goal is to expose differences early and keep them in a small compatibility record.

### Choose one representative workflow

Pick a skill with a clear input and reviewable output, such as release-note drafting or a code-review checklist. Avoid a first pilot that depends on many private tools or broad write permissions.

**Output:** One narrow workflow and one reusable test fixture.

### Normalize the portable core

Keep purpose, trigger, inputs, procedure, output format, and final checks in SKILL.md. Put templates, examples, and scripts beside it so the source remains inspectable and versioned.

**Output:** A canonical skill directory with a stable source URL.

### Create three small setup notes

For Claude Code, Codex, and Cursor, link the current official instructions and record only the settings or locations your team actually uses. Do not duplicate the full skill to create the notes.

**Output:** One concise adapter note per agent and environment.

### Run the same fixture in every agent

Use the same input, expected sections, and pass/fail checks. Record meaningful differences in discovery, permissions, tool access, output, and invocation behavior.

**Output:** A compatibility matrix based on observed results.

### Publish the team entry

Point teammates to the canonical source, explain the use case it is for, and expose only the agent paths that passed. A team library makes this discoverable without pretending to be a universal installer.

**Output:** One searchable entry with tested use paths.

### Update source first, adapters second

Review changes at the canonical source, repeat the fixture, then refresh each agent path. If one agent fails, mark that path needs-review rather than forking the skill silently.

**Output:** One version history and explicit per-agent lifecycle states.

The Claude Code adapter note is the one most teams write first, and the documented directories, precedence rules, and verification commands behind it are in [how to install Claude skills in Claude Code](https://www.skillsboard.sh/guides/install-claude-skills-in-claude-code).

## The compatibility record

Keep this beside the saved entry. It records evidence, not a timeless promise: agent behavior and supported setup paths can change.

- **Canonical version:** Commit, tag, or reviewed source state used in the test.
- **Agent and environment:** Claude Code, Codex, or Cursor plus the relevant workspace, CLI, editor, or project context.
- **Setup path:** The official installation or access instructions the tester followed.
- **Invocation:** Automatic selection, explicit invocation, or another observed trigger.
- **Fixture result:** Pass, partial, or fail against the same expected output and checks.
- **Reviewed at:** Date, owner, and reason to retest after a source or agent change.

## Cross-agent skill discovery and instruction-transport fixture

**Summary:** Use this public fixture to test whether one documented agent path can discover a named SKILL.md and transport a nonce-bearing instruction into a fresh session. The protocol publishes the method and blank record only; Skills Board is not claiming a result for Claude Code, Codex, Cursor, or any other agent.

**Version:** 1.0

**Status:** Protocol only — no results claimed

### Scope

- Pins the product version, environment, setup documentation, fixture hash, and test date for one path.
- Uses two fresh sessions and two private run nonces to check named-skill discovery and literal instruction transport.
- Publishes fixed pass, partial, fail, and not-run criteria plus a blank evidence record.

### Methodology

#### Pin the path

Record the exact product version, interface, operating system, workspace scope, vendor setup URL, and access date.

#### Prepare the fixture

Copy the published SKILL.md, replace its placeholder with a new 128-bit-or-longer nonce, and hash the installed file.

#### Keep the nonce out of context

Expose the fixture only through the documented setup path. Do not paste the receipt or nonce into the conversation.

#### Run a fresh session

Send the protocol's exact invocation prompt and retain the full response plus any observable discovery or invocation signal.

#### Repeat independently

Start another fresh session with a different nonce, the same setup path, and a new fixture hash.

#### Apply fixed criteria

Mark pass only when both runs return their exact one-line receipts. Preserve partial, fail, and not-run outcomes.

### Limitations

- It does not test automatic selection, scripts, tools, commands, file access, network access, or side effects.
- It does not evaluate permissions, sandboxing, secret handling, open-ended output quality, or bundled resources.
- If the product does not expose provenance, the nonce proves that the payload reached the session—not which internal discovery mechanism loaded it.
- A result applies only to the recorded product version, environment, and setup path—not every client or future release.
- A pass for this fixture cannot certify another skill as safe, correct, portable, or team-approved.

[Open the complete fixture](https://www.skillsboard.sh/cross-agent-skill-compatibility-fixture.md)

## Cross-agent shortcuts to avoid

### Assuming format means synchronization

A shared SKILL.md reduces duplication, but it does not automatically install, update, or enable the skill in every agent environment.

### Maintaining three canonical copies

Agent folders should consume or reference the reviewed source. If each copy evolves independently, the team no longer knows which behavior it approved.

### Publishing untested compatibility badges

Support claims should name the tested environment and date. A vendor announcing skill support is not evidence that your specific scripts and permissions work there.

### Hiding agent-specific differences

Different discovery and invocation rules are normal. Small adapter notes are cheaper and clearer than forcing a misleading universal setup.

## Checklist

- One canonical skill source is shared across all three agent paths.
- The portable workflow is separated from agent-specific setup notes.
- Every compatibility claim names an observed environment and review date.
- The same fixture and pass/fail checks were used for each agent.
- A failed agent path can be paused without forking the canonical skill.
- The team can discover the skill without knowing its install location in advance.

## Sources

- [OpenAI: Skills in ChatGPT](https://help.openai.com/en/articles/20001066): Explains the reusable and shareable skill model, the open standard, and support across OpenAI products including Codex.
- [Anthropic: Extend Claude with skills](https://code.claude.com/docs/en/slash-commands): Documents Claude Code skill files, project and personal discovery, invocation controls, and sharing patterns.
- [Cursor 2.4: Skills support](https://cursor.com/changelog/2-4): Announces Agent Skills in Cursor editor and CLI, using SKILL.md files with instructions, scripts, and commands.
- [GitHub: About agent skills](https://docs.github.com/en/copilot/concepts/agents/about-agent-skills): Confirms Agent Skills as an open standard used across multiple AI systems and documents shared repository locations.
- [Skills Board: Cross-agent skill compatibility fixture](https://www.skillsboard.sh/cross-agent-skill-compatibility-fixture.md): Version 1.0 of the dated, reproducible discovery and instruction-transport protocol. It publishes fixed criteria and a blank record, with no agent results claimed.