migrate-aiboarding
Use when a repo has a legacy AIBOARDING.md (v1 layout) and should move to the standard AGENTS.md + CLAUDE.md layout with the .aiboarding/state.json sidecar. One-shot, preview-first migration that preserves the existing onboarding content and rewires the hooks.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- migrate-aiboarding
- description
- Use when a repo has a legacy AIBOARDING.md (v1 layout) and should move to the standard AGENTS.md + CLAUDE.md layout with the .aiboarding/state.json sidecar. One-shot, preview-first migration that preserves the existing onboarding content and rewires the hooks.
03 SKILL.md 正文
Migrating AIBOARDING.md → AGENTS.md + CLAUDE.md
One-shot migration from the v1 custom-injection layout to the standard-files
layout. The onboarding knowledge in AIBOARDING.md is an investment - carry it
over; never regenerate from scratch and never delete anything without approval.
Announce at start: "Using migrate-aiboarding to move this repo to the AGENTS.md layout."
Precondition: AIBOARDING.md exists at the repo root. If it does not, stop and
suggest create-agent-onboarding. If AGENTS.md also already exists, stop and ask
the user which file is authoritative before writing anything.
Step 1: Carry over state
Read the AIBOARDING.md frontmatter (aiboarding_version, generated,
last_synced_commit). These seed .aiboarding/state.json:
aiboarding_version: 2generated: today's datelast_synced_commit: carried over verbatim (empty stays empty - the repair semantics of an empty pointer are preserved).
Step 2: Map the body
Map the three v1 H1 sections onto the v2 schema (see create-agent-onboarding's Shared contracts for the exact section list and order):
| v1 source | v2 target sections |
|---|---|
# 1. Engineering Basics |
Stack and Runtime, Build, Test, Run, Architecture Map |
# 2. Domain & Business Logic |
Project Purpose, Domain Model |
# 3. AI-Specific Context |
Agent Guardrails, Known Failure Modes |
Preserve the compressed density of the source text; split it, don't rewrite it. Backtick-quote any command, identifier, path, or error string that isn't already.
Two v2 sections have no v1 source: Verification Before Completion and
Escalation - Ask the User When. Run a short, scoped grilling pass (the
one-question-at-a-time style from create-agent-onboarding) ONLY for these gaps.
Step 3: Generate the wrapper and lifecycle files
Follow create-agent-onboarding Phase 6: CLAUDE.md (@AGENTS.md + fenced
Claude-notes block), state.json, config.json, .aiboarding/.gitignore, the six
hook files, and its complete current tool set including write-evidence.
Repo-local hook/settings steps are Claude Code-only. Codex plugin hooks are native,
optional, and require /hooks trust review; standalone skills use manual
update-agent-onboarding after meaningful commits.
Step 4: Rewire hooks and settings (Claude Code runtimes)
In <repo>/.claude/settings.json:
- Replace the
SessionStartfull-injection entry with the current template's entry (the modernsession-startis a fallback warner, not an injector). - Delete the
PreToolUse[Task]entry (pre-taskis retired -SubagentStartis native now). - Replace the
PostToolUseentry so it dispatchesdrift-check(notpost-commit). - Add the
SubagentStartandInstructionsLoadedentries from the template. Delete<repo>/.aiboarding/hooks/pre-taskand<repo>/.aiboarding/hooks/post-commit. All edits idempotent: match aiboarding entries bycommandcontaining.aiboarding/hooks/run-hook.cmd; never duplicate; leave non-aiboarding hooks alone.
Step 5: Retire the legacy document
Ask the user to choose (default: archive):
- Archive (default): move
AIBOARDING.mdtodocs/archive/AIBOARDING.mdunchanged. Git history preserves it either way; nothing at the root keeps stale onboarding discoverable by tools. - Keep as legacy: leave
AIBOARDING.mdin place and prepend a deprecation banner viainject-fenced AIBOARDING.md deprecation <banner-file>pointing toAGENTS.md. The drift hook keeps honoring the legacy layout only whenstate.jsonis absent, so with both present the sidecar wins. Never deleteAIBOARDING.mdoutright unless the user explicitly asks.
Step 6: Single approval gate, then write
Before writing ANYTHING, present the full migration plan in one preview: every file to be created, modified (with the settings diff), moved, or deleted. One approval covers the whole batch; a rejection means nothing was touched.
Step 7: Exit check
Run create-agent-onboarding's Phase 7 validation gate, then audit-agent-onboarding
if available. Report the file-by-file outcome, and remind the user to commit the new
layout (the drift hook stays silent for onboarding-only commit ranges).
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.