acm-config
Use when the user wants to customize Claudikins Automatic Context Manager behavior, configure trigger threshold, snooze duration, summary length, or runs '/acm:config'. Interactively asks questions and saves preferences to config file.
Best use case
acm-config is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when the user wants to customize Claudikins Automatic Context Manager behavior, configure trigger threshold, snooze duration, summary length, or runs '/acm:config'. Interactively asks questions and saves preferences to config file.
Teams using acm-config should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/acm-config/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How acm-config Compares
| Feature / Agent | acm-config | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when the user wants to customize Claudikins Automatic Context Manager behavior, configure trigger threshold, snooze duration, summary length, or runs '/acm:config'. Interactively asks questions and saves preferences to config file.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Claudikins Automatic Context Manager Interactive Configuration
You are helping the user configure Claudikins Automatic Context Manager. This skill guides you through an interactive configuration process where you ask the user questions and save their preferences to `~/.claude/claudikins-acm.conf`.
## Configuration Flow
Follow this conversational flow to configure Claudikins Automatic Context Manager:
### 1. Welcome & Current Settings
First, check if a config file exists and show current settings:
```bash
# Check for existing config
if [ -f ~/.claude/claudikins-acm.conf ]; then
echo "Current Claudikins Automatic Context Manager Configuration:"
cat ~/.claude/claudikins-acm.conf
else
echo "No configuration found. Let's set up Claudikins Automatic Context Manager!"
fi
```
### 2. Ask Configuration Questions
Ask the user about each setting in a friendly, conversational way:
**Context Trigger Threshold:**
- Question: "At what context percentage should the handoff dialog appear?"
- Default: 60
- Valid range: 50-90
- Explain: "This controls when Claudikins alerts you. Lower = more frequent alerts, higher = fewer alerts but less context headroom."
**Snooze Duration:**
- Question: "How long should the snooze duration be (in minutes)?"
- Default: 5
- Valid range: 1-60
- Explain: "When you click 'SNOOZE', how long should Claudikins wait before asking again?"
**Summary Token Length:**
- Question: "How detailed should handoff summaries be (in tokens)?"
- Default: 500
- Valid range: 200-2000
- Explain: "Larger = more detailed summaries but takes longer to generate. 500 is usually perfect."
**Dialog Style:**
- Question: "Which dialog style do you prefer?"
- Options: "vibrant" (colorful, current default) or "minimal" (subtle colors)
- Default: vibrant
- Explain: "Vibrant uses bright orange/pink colors. Minimal uses muted tones."
### 3. Validate Input
For each answer:
- Ensure values are within valid ranges
- If invalid, explain why and ask again
- Provide examples of good values
### 4. Save Configuration
After all questions are answered, create the config file:
```bash
cat > ~/.claude/claudikins-acm.conf << EOF
# Claudikins Automatic Context Manager Configuration
# Generated on $(date)
# Context trigger threshold (50-90)
THRESHOLD=${threshold_value}
# Snooze duration in seconds
SNOOZE_DURATION=$((snooze_minutes * 60))
# Summary token length (200-2000)
SUMMARY_TOKENS=${summary_tokens}
# Dialog style (vibrant|minimal)
DIALOG_STYLE="${dialog_style}"
EOF
```
### 5. Apply Changes
After saving, offer to reload the configuration:
```bash
# Source the new config
source ~/.claude/claudikins-acm.conf
echo "Configuration saved to ~/.claude/claudikins-acm.conf"
echo ""
echo "Note: Changes will take effect in new sessions or after running:"
echo " source ~/.claude/claudikins-acm.conf"
```
### 6. Show Summary
Display a friendly summary of what was configured:
```
╔═══════════════════════════════════════════╗
║ Claudikins Automatic Context Manager Configuration Saved! ║
╚═══════════════════════════════════════════╝
✓ Trigger threshold: 60%
✓ Snooze duration: 5 minutes
✓ Summary length: 500 tokens
✓ Dialog style: vibrant
Your changes will take effect in new sessions.
```
## Tone & Style
- Be conversational and friendly
- Explain technical terms in simple language
- Show enthusiasm about customization
- Use the Claudikins branding colors (orange, pink, cyan) in output
- No emoji (matches Claudikins' clean aesthetic)
## Example Interaction
```
USER: /acm:config
ASSISTANT: Let's configure Claudikins Automatic Context Manager! I'll ask you a few questions about your preferences.
Current settings not found. Let's set up fresh!
First question: At what context percentage should the handoff dialog appear?
The default is 60%, which means you'll get alerted when your session is 60% full.
This gives you plenty of headroom. You can set it anywhere from 50% to 90%.
What would you like? (Press enter for 60%)
```
## Additional Commands
If the user wants to:
- **View current config**: Show the contents of `~/.claude/claudikins-acm.conf`
- **Reset to defaults**: Delete the config file and recreate with defaults
- **Edit manually**: Open the config file in their editor
## Error Handling
- If config file cannot be written, check permissions on `~/.claude/`
- If values are out of range, explain valid ranges and ask again
- If user cancels (Ctrl+C), save partial configuration if any values were set
## Integration Notes
The config file will be sourced by:
- `install.sh` during installation (if exists)
- `handoff-prompt.sh` at runtime
- `statusline-command.sh` for threshold value
Format is simple bash variables that can be sourced directly.Related Skills
add-config-field
Guide adding a new config field across types, defaults, config.yaml, and optional state/env wiring.
add-app-config
Use when adding configuration for a new application to the dotfiles, setting up a new tool's config, or when user says "add config for X"
adapter-configurator
Activate when users need help setting up, configuring, or troubleshooting LimaCharlie adapters to ingest telemetry from cloud services, identity providers, log sources, or other data sources.
configuring-acquisition-system
Guides users through configuring data acquisition systems on local machines using MCP tools for hardware discovery and direct YAML file editing for system parameters. Covers working directory setup, hardware discovery, system configuration, and credential management. Use when setting up a new acquisition PC, reconfiguring hardware, or troubleshooting system configuration issues.
aceternity-ui-configuration
Specifies that Aceternity UI dependencies should be considered during code generation or modification.
a2a-server-config
Agent-to-Agent (A2A) server configuration patterns for HTTP, STDIO, SSE, and WebSocket transports. Use when building A2A servers, configuring MCP transports, setting up server endpoints, or when user mentions A2A configuration, server transport, MCP server setup, or agent communication protocols.
a-b-test-config-creator
A B Test Config Creator - Auto-activating skill for ML Deployment. Triggers on: a b test config creator, a b test config creator Part of the ML Deployment skill category.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.