gemini-checkpoint-management
Central authority for Gemini CLI Checkpointing. Covers git-based file snapshots, automatic state saving, /restore command, and rollback. Use when enabling checkpointing, restoring previous states, undoing changes, or planning experimental workflows with Gemini. Delegates 100% to gemini-cli-docs for official documentation.
What this skill does
# Gemini Checkpoint Management
## MANDATORY: Invoke gemini-cli-docs First
> **STOP - Before providing ANY response about Gemini checkpointing:**
>
> 1. **INVOKE** `gemini-cli-docs` skill
> 2. **QUERY** for the specific checkpointing topic
> 3. **BASE** responses EXCLUSIVELY on official documentation loaded
## Overview
Meta-skill for managing Gemini CLI's checkpointing system. Checkpointing creates automatic snapshots before file modifications, enabling instant rollback.
## When to Use This Skill
**Keywords:** checkpoint, rollback, restore, undo, snapshot, revert, experiment, checkpointing, /restore
**Use this skill when:**
- Enabling or configuring checkpointing
- Listing available checkpoints
- Restoring to a previous state
- Understanding checkpoint storage
- Planning experimental workflows
## How Checkpointing Works
When enabled, before any file modification Gemini creates:
1. **Git Snapshot**: Shadow repo at `~/.gemini/history/<project_hash>`
2. **Conversation History**: Complete session state
3. **Pending Tool Call**: The operation about to execute
Checkpoints are stored locally and don't interfere with your project's Git repository.
## Configuration
### Enable Checkpointing
Add to `settings.json`:
```json
{
"general": {
"checkpointing": {
"enabled": true
}
}
}
```
### Verify Configuration
```bash
cat ~/.gemini/settings.json | jq '.general.checkpointing'
```
## Commands
### List Checkpoints
```text
/restore
```
Shows available checkpoint files for the current project.
### Restore Checkpoint
```text
/restore <checkpoint_file>
```
Restores files and conversation to the checkpoint state.
### Checkpoint Naming
Format: `{timestamp}-{filename}-{tool_name}`
Example: `2025-06-22T10-00-00_000Z-my-file.txt-write_file`
## Storage Locations
| Data | Location |
| --- | --- |
| Git snapshots | `~/.gemini/history/<project_hash>` |
| Checkpoint metadata | `~/.gemini/tmp/<project_hash>/checkpoints` |
## Keyword Registry (Delegates to gemini-cli-docs)
| Topic | Query Keywords |
| --- | --- |
| Enable | `checkpointing enabled`, `enable checkpointing settings` |
| Commands | `/restore command`, `list checkpoints`, `restore checkpoint` |
| Storage | `checkpoint storage`, `~/.gemini/history`, `snapshot location` |
| Workflow | `checkpointing workflow`, `automatic snapshots` |
## Quick Decision Tree
**What do you want to do?**
1. **Enable checkpointing** -> Query gemini-cli-docs: "checkpointing enabled settings"
2. **List checkpoints** -> Use `/restore` command
3. **Restore state** -> Use `/restore <checkpoint_name>`
4. **Find storage** -> Query gemini-cli-docs: "checkpoint storage ~/.gemini/history"
5. **Understand workflow** -> Query gemini-cli-docs: "checkpointing workflow"
## Best Practices
1. **Enable for experiments**: Always enable when doing risky refactors
2. **Note checkpoint names**: Before major changes, list existing checkpoints
3. **Test after restore**: Verify state after restoring
4. **Clean up periodically**: Old checkpoints consume disk space
## Verification Checkpoint
- [ ] Did I invoke gemini-cli-docs skill?
- [ ] Did official documentation load?
- [ ] Is my response based EXCLUSIVELY on official docs?
## Test Scenarios
### Scenario 1: Direct Activation
**Query**: "Use the gemini-checkpoint-management skill to enable checkpointing"
**Expected Behavior**:
- Skill activates on keyword "checkpoint"
- Delegates to gemini-cli-docs for official documentation
**Success Criteria**: User receives accurate checkpointing configuration steps
### Scenario 2: Keyword Activation
**Query**: "How do I rollback changes in Gemini CLI?"
**Expected Behavior**:
- Skill activates on keywords "rollback", "restore"
- Provides /restore command usage
**Success Criteria**: Response includes command syntax and checkpoint listing
### Scenario 3: Troubleshooting
**Query**: "Where are Gemini checkpoints stored?"
**Expected Behavior**:
- Skill activates on "checkpoint storage"
- Provides ~/.gemini/history path information
**Success Criteria**: User understands checkpoint storage structure
## References
Query `gemini-cli-docs` for official documentation on:
- "checkpointing"
- "/restore command"
- "checkpoint storage"
## Version History
- v1.1.0 (2025-11-30): Added Test Scenarios section
- v1.0.0 (2025-11-25): Initial release
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.