ai-tools-setup
Skill22 starsChanged 2 months agoMITView on GitHub
Set up, repair, and report on the RTK+ICM+Vox AI development toolkit. Installs missing tools, fixes broken hooks and MCP config, and shows an effectiveness digest (token savings, memory accumulation, voice health) on demand or as a scheduled weekly report.
- Installs packages
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Run this to see what is installed and what is missing:
- Distinctive: line 72
Read the output and determine which of the following repair steps are needed.
- Distinctive: line 78
Only run for tools that showed MISSING above.
- Very specific: line 104
Add the PreToolUse RTK hook to ~/.claude/settings.json.
- Very specific: line 149
Verify both by checking ~/.claude.json:
- Very specific: line 158
If ICM instructions are missing from ~/.claude/CLAUDE.md:
- Distinctive: line 170
Run this report to see how the toolkit is performing.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Tools Setup: RTK + ICM + Vox
Install, repair, and measure the RTK+ICM+Vox toolkit for Claude Code.
What This Skill Does
| Mode | When to use |
| Setup | First install on a new machine |
| Repair | Something broke: hooks missing, MCP not loading |
| Digest | Weekly check: token savings, memory health, voice stats |
Tools in the Bundle
| Tool | Version | Purpose |
| RTK | latest | Compresses CLI output by ~89% before it reaches the model |
| ICM | latest | Persistent SQLite memory across sessions (knowledge graph + hybrid search) |
| Vox | latest | Spoken task notifications via local TTS (zero API calls) |
Step 1: Detect Current State
Run this to see what is installed and what is missing:
echo "=== Binary check ===" && \
(rtk --version 2>/dev/null && echo "RTK: ok") || echo "RTK: MISSING" && \
(icm --version 2>/dev/null && echo "ICM: ok") || echo "ICM: MISSING" && \
(vox --version 2>/dev/null && echo "Vox: ok") || echo "Vox: MISSING"
echo "=== RTK hook ===" && \
grep -c '"rtk hook claude"' ~/.claude/settings.json 2>/dev/null \
&& echo "RTK hook: ok" || echo "RTK hook: MISSING"
echo "=== ICM hooks ===" && \
grep -c '"icm hook' ~/.claude/settings.json 2>/dev/null \
&& echo "ICM hooks: ok" || echo "ICM hooks: MISSING"
echo "=== ICM MCP ===" && \
python3 -c "import json; d=json.load(open(open('$HOME/.claude.json').name)); print('ICM MCP: ok' if 'icm' in d.get('mcpServers',{}) else 'ICM MCP: MISSING')" 2>/dev/null || echo "ICM MCP: MISSING"
echo "=== Vox MCP ===" && \
python3 -c "import json; d=json.load(open(open('$HOME/.claude.json').name)); print('Vox MCP: ok' if 'vox' in d.get('mcpServers',{}) else 'Vox MCP: MISSING')" 2>/dev/null || echo "Vox MCP: MISSING"
echo "=== ICM CLAUDE.md ===" && \
grep -c 'icm:start' ~/.claude/CLAUDE.md 2>/dev/null \
&& echo "ICM CLAUDE.md: ok" || echo "ICM CLAUDE.md: MISSING"Read the output and determine which of the following repair steps are needed.
Step 2: Install Missing Binaries
Only run for tools that showed MISSING above.
RTK:
brew install rtk
rtk --versionICM:
brew install rtk-ai/tap/icm
icm --versionVox:
brew install rtk-ai/tap/vox
vox --versionStep 3: Repair Hooks
RTK hook missing
Add the PreToolUse RTK hook to ~/.claude/settings.json. Read the file first, then add inside the existing "hooks" block (or create one):
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [{ "type": "command", "command": "rtk hook claude" }]
}
]Then verify: grep -c '"rtk hook claude"' ~/.claude/settings.json
ICM hooks missing
Run:
icm init --mode hookThis adds PreToolUse, PostToolUse, PreCompact, UserPromptSubmit, SessionStart, SessionEnd hooks automatically.
Vox Stop hook missing
Run:
vox init --mode cliStep 4: Repair MCP Servers
ICM MCP missing
icm init --mode mcpVox MCP missing
vox init --mode mcpVerify both by checking ~/.claude.json:
python3 -c "import json; d=json.load(open('$HOME/.claude.json')); print(list(d.get('mcpServers',{}).keys()))"Step 5: Repair CLAUDE.md Instructions
If ICM instructions are missing from ~/.claude/CLAUDE.md:
icm init --mode cliThen move the block from wherever icm init placed it into ~/.claude/CLAUDE.md (the global file), and remove it from any project-local files.
Step 6: Effectiveness Digest
Run this report to see how the toolkit is performing. Good to run weekly.
echo "=============================="
echo " AI TOOLS EFFECTIVENESS"
echo "=============================="
echo ""
echo "--- RTK: Token Savings ---"
rtk gain 2>/dev/null || echo "No data yet (run some commands first)"
echo ""
echo "--- ICM: Memory Health ---"
icm health 2>/dev/null || echo "No memories yet"
echo ""
echo "--- ICM: Topics ---"
icm topics 2>/dev/null || echo "No topics yet"
echo ""
echo "--- Vox: Usage ---"
vox stats 2>/dev/null || echo "No stats yet"
echo ""
echo "=============================="What healthy output looks like
- RTK:
Tokens saved: 5M+ (85%+)across500+ commands. If savings are low, runrtk discoverto find uncovered commands - ICM: Topics like
decisions-*,errors-resolved,preferenceswith recent timestamps. If empty, start storing manually withicm store - Vox: Non-zero speak count means the Stop hook fired
Step 7 (Optional): Schedule a Weekly Digest
To get a weekly automated report without having to remember to run this skill:
# Create a weekly digest script
cat > ~/ai-tools-digest.sh << 'EOF'
#!/bin/bash
echo "=== Weekly AI Tools Digest: $(date) ===" | tee -a ~/ai-tools-digest.log
echo "" | tee -a ~/ai-tools-digest.log
rtk gain 2>/dev/null | tee -a ~/ai-tools-digest.log
echo "" | tee -a ~/ai-tools-digest.log
icm health 2>/dev/null | tee -a ~/ai-tools-digest.log
echo "" | tee -a ~/ai-tools-digest.log
icm topics 2>/dev/null | tee -a ~/ai-tools-digest.log
# Speak the summary if Vox is available
vox "Weekly digest complete. Check your log." 2>/dev/null || true
EOF
chmod +x ~/ai-tools-digest.shThen set up a weekly launchd job (macOS):
cat > ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist << 'EOF'
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.oleg.ai-tools-digest</string>
<key>ProgramArguments</key>
<array>
<string>/bin/bash</string>
<string>/Users/oleg.koval/ai-tools-digest.sh</string>
</array>
<key>StartCalendarInterval</key>
<dict>
<key>Weekday</key>
<integer>1</integer>
<key>Hour</key>
<integer>9</integer>
<key>Minute</key>
<integer>0</integer>
</dict>
<key>StandardOutPath</key>
<string>/tmp/ai-tools-digest.log</string>
<key>StandardErrorPath</key>
<string>/tmp/ai-tools-digest.err</string>
</dict>
</plist>
EOF
launchctl load ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist
echo "Weekly digest scheduled for Mondays at 9am"To view the digest log anytime: cat ~/ai-tools-digest.log
To unload: launchctl unload ~/Library/LaunchAgents/com.oleg.ai-tools-digest.plist
Quick Reference
| Command | What it does |
rtk gain | Total tokens saved to date |
rtk discover | Find commands not yet covered by RTK |
icm topics | List all memory topic buckets |
icm health | Memory hygiene: stale, redundant, decay stats |
icm recall "query" | Search memories semantically |
icm store -t topic -c "content" -i high | Store a memory manually |
vox "text" | Speak text immediately |
vox stats | Usage stats for the Vox backend |
cat ~/ai-tools-digest.log | View scheduled digest history |
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- wonderwhy-er/DesktopCommanderMCP★ 10ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository194 other files it gives its agents.
- 0-templateSkill
- ab-test-analyzerSkill
- academy-guideSkill
- add-to-my-skillsSkill
- adr-authorSkill
- algorithmic-artSkill
- api-and-interface-designSkill
- api-designerSkill
- api-docs-writerSkill
- apple-store-submitSkill
- aws-cost-optimizerSkill
- bash-script-hardeningSkill
- blog-post-writerSkill
- book-summarizerSkill
- branch-cleanupSkill
- brand-copy-landingSkill
- brand-copySkill
- brand-designSkill
- brand-guidelinesSkill
- browser-testing-with-devtoolsSkill
- canvas-designSkill
- changelog-generatorSkill
- changelog-keeperSkill
- chart-chooserSkill
- ci-cd-and-automationSkill
- ci-fix-loopSkill
- claude-apiSkill
- cloudflare-block-countriesSkill
- coderabbitloopSkill
- code-review-and-qualitySkill
- code-reviewerSkill
- code-simplificationSkill
- codexloopSkill
- comms-notionSkill
- comms-slackSkill
- comms-whatsappSkill
- competitive-analysisSkill
- concept-explainerSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- context-repoSkill
- cover-letter-writerSkill
- crash-courseSkill
- cron-schedulerSkill
- data-digestSkill
- data-pipeline-architectSkill
- debug-detectiveSkill
- debugging-and-error-recoverySkill
- decision-matrixSkill
- dependabot-triageSkill
- dependency-upgraderSkill
- deprecation-and-migrationSkill
- dev-instantdbSkill
- discernment-nudgeSkill
- doc-coauthoringSkill
- dockerfile-proSkill
- docs-index-keeperSkill
- documentation-and-adrsSkill
- docxSkill
- doubt-driven-developmentSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

