菜单
Converts agent definitions between Markdown (with YAML frontmatter) and TOML formats. Use when transforming agent configurations for different agent systems — MD format for rich tool restrictions, TOML format for Codex-style agents with sandbox modes.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Execute batched or parallel RLM work using Daytona sandboxes. Use when running multiple sub-tasks, parameter sweeps, or batch recursive RLM calls in the daytona_pilot runtime.
Debug fleet-rlm runtime issues from Claude Code. Use when diagnosing daytona_pilot failures, API and websocket contract problems, sandbox persistence bugs, or runtime readiness drift.
Execute Python code in Daytona sandboxes with durable volume persistence. Use when running code in a Daytona sandbox, processing data with stateful execution, or persisting results across sessions.
(EXPERIMENTAL) Research implementation for RLM long-context processing using standalone Python scripts. For production use, prefer the rlm skill which uses the fleet-rlm package with Daytona sandboxes. This skill is for experimentation, evaluation, and alternative implementation patterns.
Long-term memory persistence for RLM using Daytona durable volume storage. Use when storing, recalling, listing, or searching data that persists across sandbox sessions in the daytona_pilot runtime.
Run fleet-rlm through its current public entrypoints. Use when you need the right command for the Web UI, API server, MCP server, terminal chat, or Daytona smoke validation from a Claude Code workflow.
| name | agent-converter |
| description | Converts agent definitions between Markdown (with YAML frontmatter) and TOML formats. Use when transforming agent configurations for different agent systems — MD format for rich tool restrictions, TOML format for Codex-style agents with sandbox modes. |
Convert agent definitions between two formats:
.md with YAML frontmatter) — Rich format with explicit tool restrictions.toml) — Simple format for Codex agents with sandbox modes.md file (or directory of agents)toml (default) or mdpython3 skills/agent-converter/scripts/convert_agent.py <input.md> [--output <dir>]
python3 skills/agent-converter/scripts/convert_agent.py --batch <input_dir> [--output <dir>]
python3 skills/agent-converter/scripts/convert_agent.py <input.toml> --to-md [--output <dir>]
| MD Frontmatter | TOML Field |
|---|---|
name | (derived from filename) |
description | Included in developer_instructions |
tools | Mapped to sandbox_mode |
| Markdown body | developer_instructions |
| Tools | Sandbox Mode |
|---|---|
Read, Grep, Glob only | read-only |
| Any Write/Edit tools | allow-edits |
| No tools specified | allow-edits (default) |
| Sandbox Mode | Tools |
|---|---|
read-only | Read, Grep, Glob |
allow-edits | Read, Write, Edit, Bash, Glob, Grep |
explorer.md---
name: explorer
description: >
Read-only codebase explorer.
tools:
- Read
- Grep
- Glob
---
# Explorer — Read-Only Codebase Navigator
You are a read-only explorer agent...
explorer.tomlsandbox_mode = "read-only"
developer_instructions = """
Role: Read-only codebase explorer.
Tools: Read, Grep, Glob
---
# Explorer — Read-Only Codebase Navigator
You are a read-only explorer agent...
"""
| Error | Resolution |
|---|---|
| Missing frontmatter | Treat as plain markdown, use defaults |
| Invalid TOML | Report parse error with line number |
| Unknown tools | Warn and include in output as-is |
| File exists | Prompt user or use --force to overwrite |
skills/agent-converter/references/format-spec.md.agents/sub-agents/