Hand off an unfinished session to the next one — what's done, what's next, what's blocked.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ToruAI/toru-claude-agents --skill megg-state --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Megg State?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/toruai-megg-state-toru-claude-agents)More formats (shields.io, HTML) on the badges page.
---
name: megg-state
description: Hand off an unfinished session to the next one — what's done, what's next, what's blocked.
user-invocable: true
arguments:
- name: action
description: clear | show (default captures state)
required: false
---
# Session State Management
Capture or manage session state for cross-session handoff.
## Process
### Default (no argument) - Capture State
1. Review what was worked on in this session
2. Summarize into this format:
```markdown
## Working On
[One-liner: the main task/goal]
## Progress
- [What's been done]
- [Current status]
## Next
- [Immediate next steps]
## Context
[Relevant files, blockers, pending decisions - keep brief]
```
3. Call the `mcp__megg__state` tool with the content:
```
mcp__megg__state({ content: "<formatted content>" })
```
4. Confirm to user that state was saved
### `clear` - Clear State
1. Call `mcp__megg__state({ status: "done" })`
2. Confirm state was cleared
### `show` - Display Current State
1. Call `mcp__megg__state()` with no arguments
2. Display the current state or "No active state"
## Notes
- State is ephemeral - overwritten each session
- Auto-expires after 48 hours or when marked done
- Hard limit of 2k tokens to prevent bloat
- Keep content concise and actionable
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.