🇺🇸English

/converter -- Cross-Platform Skill Converter

Parse AgentOps skills into a universal SkillBundle format, then convert to target agent platforms.

Quick Start

/converter skills/council codex     # Convert council skill to Codex format
/converter skills/vibe cursor       # Convert vibe skill to Cursor format
/converter --all codex              # Convert all skills to Codex

Pipeline

The converter runs a three-stage pipeline:

parse --> convert --> write

Stage 1: Parse

Read the source skill directory and produce a SkillBundle:

• Extract YAML frontmatter from SKILL.md (between --- markers)
• Collect the markdown body (everything after the closing ---)
• Enumerate all files in references/ and scripts/
• Assemble into a SkillBundle (see references/skill-bundle-schema.md)

Stage 2: Convert

Transform the SkillBundle into the target platform's format:

The Codex adapter produces a SKILL.md with YAML frontmatter (name, description) plus rewritten body content and a prompt.md (Codex prompt referencing the skill). Default mode is modular : reference docs, scripts, and resources are copied as files and SKILL.md includes a local resource index instead of inlining everything. Optional inline mode preserves the older behavior by appending inlined references and script code blocks. Codex output rewrites known slash-skill references (for example /plan) to dollar-skill syntax ($plan), replaces Claude-specific paths/labels (including ~/.claude/, $HOME/.claude/, and /.claude/ path variants), normalizes common mixed-runtime terms (for example , , and ) to Codex-native phrasing, and rewrites Claude-only primitive labels to runtime-neutral wording. It preserves current flat CLI commands from the source skill rather than reintroducing deprecated namespace forms. It also deduplicates repeated "In Codex" runtime headings after rewrite while preserving section content. It preserves non-generated resource files/directories from the source skill (for example , , , , ) and enforces passthrough parity (missing copied resources fail conversion). Descriptions are truncated to 1024 chars at a word boundary if needed.

The Cursor adapter produces a <name>.mdc rule file with YAML frontmatter (description, globs, alwaysApply: false) and body content. References are inlined into the body, scripts are included as code blocks. Output is budget-fitted to 100KB max -- references are omitted largest-first if the total exceeds the limit. If the skill references MCP servers, a mcp.json stub is also generated.

Stage 3: Write

Write the converted output to disk.

• Default output directory: .agents/converter/<target>/<skill-name>/
• Write semantics: Clean-write. The target directory is deleted before writing. No merge with existing content.

CLI Usage

# Convert a single skill
bash skills/converter/scripts/convert.sh <skill-dir> <target> [output-dir]
bash skills/converter/scripts/convert.sh --codex-layout inline <skill-dir> codex [output-dir]

# Convert all skills
bash skills/converter/scripts/convert.sh --all <target> [output-dir]

Arguments

Supported Targets

• codex -- Convert to OpenAI Codex format (SKILL.md + prompt.md) with codex-native rewrites (slash-to-dollar skills, .claude path variants to .codex, mixed-runtime term normalization to Codex phrasing, Claude primitive label neutralization, duplicate runtime-heading cleanup, and flat ao CLI preservation). Default is modular output with copied resources and a SKILL.md local-resource index; pass --codex-layout inline for legacy inlined refs/scripts. Converter enforces passthrough parity so missing copied resources fail fast. Output: <dir>/SKILL.md, <dir>/prompt.md, and copied resources.
• cursor -- Convert to Cursor rules format ( rule file + optional ). Output: and optionally .

Extending

To add a new target platform:

1. Add a conversion function to scripts/convert.sh (pattern: convert_<target>)
2. Update the target table above
3. Add reference docs to references/ if the target format needs documentation

Examples

Converting a single skill to Codex format

User says: /converter skills/council codex

What happens:

1. The converter parses skills/council/SKILL.md frontmatter, markdown body, and any references/ and scripts/ files into a SkillBundle.
2. The Codex adapter transforms the bundle into a SKILL.md (body + inlined references + scripts as code blocks) and a prompt.md (Codex prompt referencing the skill).
3. Output is written to .agents/converter/codex/council/.

Result: A Codex-compatible skill package ready to use with OpenAI Codex CLI.

Batch-converting all skills to Cursor rules

User says: /converter --all cursor

What happens:

1. The converter scans every directory under skills/ and parses each into a SkillBundle.
2. The Cursor adapter transforms each bundle into a .mdc rule file with YAML frontmatter and body content, budget-fitted to 100KB max. Skills referencing MCP servers also get a mcp.json stub.
3. Each skill's output is written to .agents/converter/cursor/<skill-name>/.

Result: All skills are available as Cursor rules, ready to drop into a .cursor/rules/ directory.

Troubleshooting

References

• references/skill-bundle-schema.md -- SkillBundle interchange format specification

Reference Documents

• references/skill-bundle-schema.md

Weekly Installs

156

Repository

boshu2/agentops

GitHub Stars

197

First Seen

Feb 17, 2026

Security Audits

Gen Agent Trust HubWarnSocketFailSnykFail

Installed on

opencode155

codex152

github-copilot151

kimi-cli151

gemini-cli151

amp151