How do I install the Self Update skill?

Run npx skillmds@latest add tomevault-io/self-update in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Self Update safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Self Update?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Self Update free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Self Update?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Self Update by tomevault-io — Agent Skill

Name: Self Update
Author: tomevault-io

File contents

Self-Update Skill

Updates the AGI Agent Kit framework components (skills, agents, workflows) to the latest published version.

When to Use

When a new version of @techwavedev/agi-agent-kit is available
When you want to sync your local installation with the latest templates
After the user asks to "update", "upgrade", or "get latest skills"

How It Works

Check Current Version: Reads .agi.json for installed version (if present)
Fetch Latest: Runs npm view @techwavedev/agi-agent-kit version
Update: Re-runs init with --pack=full to overlay new templates

Quick Commands

# Check installed version
cat .agi.json 2>/dev/null || echo "No version metadata found"

# Check latest NPM version
npm view @techwavedev/agi-agent-kit version

# Update to latest (re-init with full pack)
npx @techwavedev/agi-agent-kit@latest init --pack=full

Update Script

Use the provided script for a guided update:

python3 skills/self-update/scripts/update_kit.py

What Gets Updated

Component	Updated?	Notes
Skills	✅ Yes	All skills from templates
Agents	✅ Yes	`.agent/` directory
Workflows	✅ Yes	`.agent/workflows/`
Skill Creator	✅ Yes	`skill-creator/`
AGENTS.md	✅ Yes	Overwrites with latest
User's .env	❌ No	Never touched
User's directives	❌ No	Preserved

Notes

The update process overwrites skill scripts. If you've customized them, back up first.
Your .env and custom directives are always preserved.
After updating, run /checkup to verify everything is working.

AGI Framework Integration

Qdrant Memory Integration

Before executing complex tasks with this skill:

python3 execution/memory_manager.py auto --query "<task summary>"

Decision Tree:

Cache hit? Use cached response directly — no need to re-process.
Memory match? Inject context_chunks into your reasoning.
No match? Proceed normally, then store results:

python3 execution/memory_manager.py store \
  --content "Description of what was decided/solved" \
  --type decision \
  --tags self-update <relevant-tags>

Note: Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.

Agent Team Collaboration

Strategy: This skill communicates via the shared memory system.
Orchestration: Invoked by orchestrator via intelligent routing.
Context Sharing: Always read previous agent outputs from memory before starting.

Local LLM Support

When available, use local Ollama models for embedding and lightweight inference:

Embeddings: nomic-embed-text via Qdrant memory system
Lightweight analysis: Local models reduce API costs for repetitive patterns

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: self-updatedescription: Update the AGI Agent Kit to the latest version from NPM Use when this capability is needed.---# Self-Update SkillUpdates the AGI Agent Kit framework components (skills, agents, workflows) to the latest published version.## When to Use- When a new version of `@techwavedev/agi-agent-kit` is available- When you want to sync your local installation with the latest templates- After the user asks to "update", "upgrade", or "get latest skills"## How It Works1. **Check Current Version**: Reads `.agi.json` for installed version (if present)2. **Fetch Latest**: Runs `npm view @techwavedev/agi-agent-kit version`3. **Update**: Re-runs init with `--pack=full` to overlay new templates## Quick Commands```bash# Check installed versioncat .agi.json 2>/dev/null || echo "No version metadata found"# Check latest NPM versionnpm view @techwavedev/agi-agent-kit version# Update to latest (re-init with full pack)npx @techwavedev/agi-agent-kit@latest init --pack=full```## Update ScriptUse the provided script for a guided update:```bashpython3 skills/self-update/scripts/update_kit.py```## What Gets Updated| Component | Updated? | Notes || ----------------- | -------- | ------------------------- || Skills | ✅ Yes | All skills from templates || Agents | ✅ Yes | `.agent/` directory || Workflows | ✅ Yes | `.agent/workflows/` || Skill Creator | ✅ Yes | `skill-creator/` || AGENTS.md | ✅ Yes | Overwrites with latest || User's .env | ❌ No | Never touched || User's directives | ❌ No | Preserved |## Notes- The update process **overwrites** skill scripts. If you've customized them, back up first.- Your `.env` and custom directives are always preserved.- After updating, run `/checkup` to verify everything is working.## AGI Framework Integration### Qdrant Memory IntegrationBefore executing complex tasks with this skill:```bashpython3 execution/memory_manager.py auto --query "<task summary>"```**Decision Tree:**- **Cache hit?** Use cached response directly — no need to re-process.- **Memory match?** Inject `context_chunks` into your reasoning.- **No match?** Proceed normally, then store results:```bashpython3 execution/memory_manager.py store \ --content "Description of what was decided/solved" \ --type decision \ --tags self-update <relevant-tags>```> **Note:** Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.### Agent Team Collaboration- **Strategy**: This skill communicates via the shared memory system.- **Orchestration**: Invoked by `orchestrator` via intelligent routing.- **Context Sharing**: Always read previous agent outputs from memory before starting.### Local LLM SupportWhen available, use local Ollama models for embedding and lightweight inference:- Embeddings: `nomic-embed-text` via Qdrant memory system- Lightweight analysis: Local models reduce API costs for repetitive patterns---> Converted and distributed by [TomeVault](https://tomevault.io/claim/techwavedev) — claim your Tome and manage your conversions.

Frequently asked questions

Self Update