AugmentClaude
DocsDevOps

Agent Workspace Migration

By dontbesilent2025· dontbesilent2025/dbskill· 0

Organize multi-platform agent projects with consistent naming, bridging, and structure.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.
    Install
    Sign up to copy
    Sign up free to reveal

    This copies the whole skill folder into ~/.claude/skills/dbs-agent-migration-dontbesilent2025/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
    Sign up free to reveal
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Agent Claude Code / Codex / Grok / Agents~.agents/skills Agent bridge /dbs-agent-migration/agent Codex Claude Code Grok AGENTS.md skill bridge Agent Claude Codex Grok Agent workspace migration. Turn any project into a maintainable Claude Code / Codex / Grok / generic Agents (~.agents/skills) workspace by auditing rule files, establishing source-of-truth skills, normalizing names, and generating bridges. Trigger: /dbs-agent-migration/agent-migration, "migrate to Codex", "migrate to Claude Code", "migrate to Grok", "migrate to Doubao", "fix AGENTS.md", "organize skill bridges"

What this skill does

This skill organizes multi-platform agent projects by establishing consistent naming, bridging structures, and unified rules across Claude Code, Codex, Grok, and generic Agents workspaces. It transforms chaotic or partially migrated projects into maintainable systems through structured audits, source-of-truth identification, frontmatter normalization, and multi-platform bridge generation.

What it does

  • Audits existing configurations — examines CLAUDE.md, AGENTS.md, SOURCE_OF_TRUTH.md, and scattered skill candidates to classify projects into four maturity levels (A–D) and identify missing layers
  • Establishes rule-file hierarchy — separates platform-agnostic rules into AGENTS.md, preserves platform-specific rules in CLAUDE.md or Codex/Grok equivalents, and removes redundant or outdated content
  • Identifies skill source-of-truth — locates or creates a central skills/ directory, discovers candidate skills, and curates them into a coherent skill system
  • Unifies naming and metadata — standardizes frontmatter, skill names, and descriptions across all platforms while respecting existing long-term naming conventions
  • Generates multi-platform bridges — creates thin, passthrough bridges for Claude Code, Codex, Grok (with mandatory user_invocable: true), and generic Agents (~/.agents/skills), all pointing to the same source-of-truth files
  • Verifies structural completeness — validates rule layers, bridge consistency, Grok requirements, and resolves symlink conflicts or dangling references

How to use it

Invoke this skill when you need to migrate or reorganize an agent project across multiple platforms. Hand it your current project structure—including any existing CLAUDE.md, AGENTS.md, skills/ directory, and ~/.agents/skills or platform-specific skill locations. The skill will step through each phase: audit, rule-file alignment, true-source discovery, naming unification, bridge generation, and final verification. At each step it reports findings, explains decisions, and asks for confirmation before proceeding.

Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.

Related skills

C

Claude API Helper

anthropics

Build, debug, and optimize Claude API applications with caching and model migration support.

OfficialComplete terms in LICENSE.txt
D

Documentation Co-Authoring

anthropics

Guide structured workflows for writing docs, proposals, and technical specs collaboratively.

Official
P

PPTX Text Extractor

axoviq-ai

Extract text and speaker notes from PowerPoint presentations.

AGPL-3.0-or-later
M

Memory Search

davila7

Search conversation history and recall previous discussions, decisions, and context.