From skill-forge
Converts Claude Code skills to OpenAI Codex, Google Gemini CLI, Antigravity, and Cursor. Generates platform-specific files like openai.yaml, AGENTS.md and compatibility reports.
npx claudepluginhub agricidaniel/skill-forgeThis skill uses the workspace's default tool permissions.
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google
Installs 1,265+ agentic SKILL.md files for Claude Code, Gemini CLI, Cursor, Codex CLI, Kiro, and other AI coding assistants via npx, git clone, or plugins. Use to extend AI tools with task-specific skills.
Guides creation of new Claude Code skills from scratch, listing existing user/project skills, samples, current directory, and providing metadata templates for descriptions/tags.
Share bugs, ideas, or general feedback.
Convert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor while maintaining quality and following each platform's best practices.
SKILL.md and parse frontmatter.mcp.json) if presentRun dry-run analysis first:
python scripts/convert_skill.py <path> --dry-run --target all
Review the compatibility report:
Run the conversion:
python scripts/convert_skill.py <path> --target codex,gemini,antigravity,cursor --output dist/
For MCP config conversion:
python scripts/convert_skill.py <path> --target all --output dist/ --include-mcp
Features that need manual adaptation per platform:
| Claude Feature | Codex | Gemini/Antigravity | Cursor |
|---|---|---|---|
allowed-tools | Supported | Remove; all tools available | Remove; no equivalent |
context: fork | No equivalent | No equivalent | No equivalent |
hooks | 1 event (notify) | Partial (CLI) | 6 events (beta) |
model selection | No equivalent | No equivalent | No equivalent |
Task delegation | Break into separate skills | Break into separate skills | Background Agents (Ultra plan) |
/slash commands | $mention syntax | Description-based activation | Description-based + @rule |
| Sub-skill routing | Separate skills with $mention | Separate skills, LLM-routed | Separate skills, LLM-routed |
Run validation on each generated output:
python scripts/validate_skill.py dist/codex/<skill-name>/
python scripts/validate_skill.py dist/gemini/<skill-name>/
python scripts/validate_skill.py dist/antigravity/<skill-name>/
python scripts/validate_skill.py dist/cursor/<skill-name>/
Fix any critical or high-priority issues before proceeding.
Present the user with a summary:
## Conversion Report: {skill-name}
| Platform | Score | Files | Warnings | Manual Steps |
|----------|-------|-------|----------|-------------|
| Codex | 92% | 4 | 2 | 1 |
| Gemini | 88% | 3 | 3 | 1 |
| Antigravity | 88% | 3 | 3 | 1 |
| Cursor | 88% | 3 | 3 | 1 |
### Generated Files
[list per platform]
### Warnings
[list per platform]
### Manual Steps Required
[list per platform]
When converting for all platforms (--target all), the script auto-generates
install-multiplatform.sh that:
--platform flag for explicit selection| Platform | Skill Path | Instruction File | Config Format |
|---|---|---|---|
| Claude Code | .claude/skills/ | CLAUDE.md | JSON (.mcp.json) |
| OpenAI Codex | .agents/skills/ | AGENTS.md | TOML (config.toml) |
| Gemini CLI | .gemini/skills/ | GEMINI.md | JSON (settings.json) |
| Antigravity | .agent/skills/ | GEMINI.md | JSON (mcp_config.json) |
| Cursor | .cursor/skills/ | .cursor/rules/*.mdc | JSON (mcp.json) |
For full platform specs, load references/platforms.md.