project-directory-migration
Migrate Claude Code project sessions when renaming directories. TRIGGERS - directory rename, move project, migrate sessions
What this skill does
# Project Directory Migration
> Safely migrate Claude Code project context (sessions, memory, history) when renaming a project directory.
> **Self-Evolving Skill**: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
## When to Use This Skill
Use this skill when:
- Renaming a project directory (e.g., `my-old-name/` to `my-new-name/`)
- Moving a project to a different path
- User says "No conversations found" after a directory rename
- Reorganizing workspace directories
- Package rename requires matching directory name to GitHub repo name
- Recovering sessions that became orphaned after a directory move
## Interactive Workflow
### Phase 1: Gather Facts
Use AskUserQuestion to collect source and target paths.
```
Question 1 (header: "Source"): "What is the current project directory path?"
Options:
- "Use current directory: $PWD" (Recommended)
- "Specify a different path"
Question 2 (header: "Target"): "What should the new directory path be?"
Options:
- (User provides via "Other" free text)
```
### Phase 2: Dry-Run Audit
Run the migration script in `--dry-run` mode to discover what needs migrating:
```bash
bash "<skill-scripts>/claude-code-migrate.sh" --dry-run "$OLD_PATH" "$NEW_PATH"
```
Present findings to user:
- Number of session files found
- Number of history.jsonl entries to rewrite
- Whether auto-memory (MEMORY.md) exists
- Environment tooling detected (mise, uv, direnv, asdf)
### Phase 3: Scope and Confirm
```
Question 3 (header: "Scope", multiSelect: true):
"What should be included in migration?"
Options:
- "Claude Code sessions + history (Recommended)"
- "Auto-memory (MEMORY.md) (Recommended)"
- "Backward-compatibility symlink (Recommended)"
- "Auto-fix environment: mise trust, venv recreate (Recommended)"
Question 4 (header: "Execute"):
"Ready to migrate? The script creates a timestamped backup first."
Options:
- "Execute migration now (Recommended)"
- "Export copy-paste commands for manual execution"
- "Cancel"
```
**If user chooses "Export copy-paste commands"**: Generate the exact commands they can paste into their terminal after closing Claude Code. This is the safest option since Claude Code won't be accessing the project files during migration.
### Phase 4: Post-Migration Report
After migration completes, report:
- Sessions migrated, history entries rewritten
- Environment fixups applied (mise trust, venv recreated)
- Remaining manual steps (git remote update, etc.)
- Rollback command if anything goes wrong
---
## Quick Reference
### Claude Code Path Encoding
Claude Code encodes directory paths by replacing `/` with `-`:
```
/Users/alice/projects/my-app --> -Users-alice-projects-my-app
```
### Storage Locations
| Asset | Location |
| ------------- | ----------------------------------------------------------- |
| Sessions | `~/.claude/projects/{encoded-path}/*.jsonl` |
| Memory | `~/.claude/projects/{encoded-path}/memory/MEMORY.md` |
| Session index | `~/.claude/projects/{encoded-path}/sessions-index.json` |
| History | `~/.claude/history.jsonl` |
| Subagents | `~/.claude/projects/{encoded-path}/{session-id}/subagents/` |
### What Contains Path References
| File | Fields with paths | Needs rewriting? |
| ---------------------- | ------------------------------------------------------------- | ---------------- |
| `sessions-index.json` | `originalPath`, `entries[].projectPath`, `entries[].fullPath` | **Yes** |
| `history.jsonl` | `project` field per entry | **Yes** |
| Session `.jsonl` files | None | No |
| `MEMORY.md` | None (content only) | No |
---
## Migration Script
Located at `scripts/claude-code-migrate.sh`.
### Usage
```bash
# Dry run (preview what would happen)
bash scripts/claude-code-migrate.sh --dry-run /old/path /new/path
# Execute migration
bash scripts/claude-code-migrate.sh /old/path /new/path
# Rollback from most recent backup
bash scripts/claude-code-migrate.sh --rollback
# Show help
bash scripts/claude-code-migrate.sh --help
```
### 9-Phase Execution
1. **Pre-flight validation** — 7 checks (paths, Claude Code dir, python3, no running sessions)
2. **Backup** — Timestamped copy to `~/.claude/migration-backup-YYYYMMDD-HHMMSS/`
3. **Move project directory** — Rename in `~/.claude/projects/`
4. **Rewrite sessions-index.json** — Update projectPath, fullPath, originalPath
5. **Rewrite history.jsonl** — Update project field (JSON-safe, preserves Unicode)
6. **Backward-compatibility symlink** — Old encoded path symlinks to new
7. **Rename repo directory** — `mv /old/path /new/path`
8. **Environment fixups** — mise trust, venv recreate, direnv/asdf warnings
9. **Post-flight verification** — Sessions count, memory, symlink, env health
---
## Reference Documentation
- [Session Storage Anatomy](./references/session-storage-anatomy.md) — How Claude Code stores project data
- [Troubleshooting Guide](./references/troubleshooting.md) — Common post-migration issues and fixes
- [Evolution Log](./references/evolution-log.md) — Skill improvement history
---
## Troubleshooting
| Issue | Auto-fixed? | Manual Solution |
| ----------------------------- | -------------------- | -------------------------------------- |
| mise trust error after rename | **Yes** (Phase 8) | `mise trust <new-path>` |
| `(old-name)` in shell prompt | **Yes** (Phase 8) | Restart terminal or `uv sync` |
| VIRTUAL_ENV path mismatch | **Yes** (Phase 8) | `uv sync --dev` recreates venv |
| "No conversations found" | **Yes** (Phase 4) | Re-run migration script |
| `.envrc` not allowed | **Warned** (Phase 8) | `direnv allow` |
| Git push auth fails | No | Update credential helper or remote URL |
| Session subdirs missing | No | Use `--rollback`, retry |
## Post-Execution Reflection
After this skill completes, reflect before closing the task:
0. **Locate yourself.** — Find this SKILL.md's canonical path before editing.
1. **What failed?** — Fix the instruction that caused it.
2. **What worked better than expected?** — Promote to recommended practice.
3. **What drifted?** — Fix any script, reference, or dependency that no longer matches reality.
4. **Log it.** — Evolution-log entry with trigger, fix, and evidence.
Do NOT defer. The next invocation inherits whatever you leave behind.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.