Compare commits

...
Author SHA1 Message Date
Chris Bartholomew 5d43c37fdc feat: add cloud mode to skill installer for team memory sharing
Adds support for Hindsight Cloud in the skill installer, enabling teams
to share memories about a codebase. Changes include:

- Add `--mode cloud` option to get-skill installer
- Install hindsight CLI binary for cloud mode (via get-cli)
- Configure ~/.hindsight/config with API URL and key
- Generate cloud-specific SKILL.md with team-aware guidance
- Distinguish between project conventions and individual preferences
- Update skills.md documentation with cloud setup instructions

Cloud mode workflow:
1. Team admin creates a bank in Hindsight Cloud
2. Each developer runs: curl ... | bash -s -- --mode cloud
3. All team members share the same memory bank
4. Knowledge retained by one member benefits everyone
2026-01-13 20:57:55 -05:00
Chris Bartholomew 0ff904682c doc: update expired Slack invite link 2026-01-13 16:51:05 -05:00
3 changed files with 466 additions and 50 deletions
+2 -2
View File
@@ -5,7 +5,7 @@
[Documentation](https://hindsight.vectorize.io) • [Paper](https://arxiv.org/abs/2512.12818) • [Cookbook](https://hindsight.vectorize.io/cookbook) • [Hindsight Cloud](https://vectorize.io/hindsight/cloud)
[![CI](https://github.com/vectorize-io/hindsight/actions/workflows/release.yml/badge.svg)](https://github.com/vectorize-io/hindsight/actions/workflows/release.yml)
[![Slack Community](https://img.shields.io/badge/Slack-Join%20Community-4A154B?logo=slack)](https://join.slack.com/t/hindsight-space/shared_invite/zt-3klo21kua-VUCC_zHP5rIcXFB1_5yw6A)
[![Slack Community](https://img.shields.io/badge/Slack-Join%20Community-4A154B?logo=slack)](https://join.slack.com/t/hindsight-space/shared_invite/zt-3nhbm4w29-LeSJ5Ixi6j8PdiYOCPlOgg)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
![PyPI - Downloads](https://img.shields.io/pypi/dm/hindsight-api?label=PyPI)
![NPM Downloads](https://img.shields.io/npm/dm/%40vectorize-io%2Fhindsight-client?logoColor=orange&label=NPM&color=blue&link=https%3A%2F%2Fwww.npmjs.com%2Fpackage%2F%40vectorize-io%2Fhindsight-client)
@@ -242,7 +242,7 @@ client.reflect(bank_id="my-bank", query="What should I know about Alice?")
- [CLI](https://hindsight.vectorize.io/sdks/cli)
**Community:**
- [Slack](https://join.slack.com/t/hindsight-space/shared_invite/zt-3klo21kua-VUCC_zHP5rIcXFB1_5yw6A)
- [Slack](https://join.slack.com/t/hindsight-space/shared_invite/zt-3nhbm4w29-LeSJ5Ixi6j8PdiYOCPlOgg)
- [GitHub Issues](https://github.com/vectorize-io/hindsight/issues)
---
+187 -7
View File
@@ -14,6 +14,15 @@ Hindsight provides an Agent Skill that gives AI coding assistants persistent mem
| [OpenCode](https://github.com/opencode-ai/opencode) | `~/.opencode/skills/` |
| [Codex CLI](https://github.com/openai/codex) | `~/.codex/skills/` |
## Deployment Modes
The skill supports two deployment modes:
| Mode | Best For | Data Location |
|------|----------|---------------|
| **Local** | Individual developers | Your machine (`~/.pg0/`) |
| **Cloud** | Teams sharing knowledge | Hindsight Cloud |
## Quick Install
```bash
@@ -22,13 +31,14 @@ curl -fsSL https://hindsight.vectorize.io/get-skill | bash
The installer will:
1. Prompt you to select your AI coding assistant
2. Run the LLM provider configuration
3. Install the skill to the appropriate directory
2. Select deployment mode (local or cloud)
3. Configure the appropriate settings
4. Install the skill to the appropriate directory
### Install for a Specific Platform
```bash
# Claude Code
# Claude Code (interactive mode selection)
curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude
# OpenCode
@@ -38,6 +48,13 @@ curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app opencode
curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app codex
```
### Install with Cloud Mode
```bash
# Direct cloud setup (skips interactive prompts for mode)
curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude --mode cloud
```
## What the Skill Provides
Once installed, your AI assistant gains the ability to:
@@ -68,6 +85,8 @@ The skill is optimized to store:
## Architecture
### Local Mode
```
AI Coding Assistant
@@ -86,7 +105,29 @@ Embedded PostgreSQL (~/.pg0/hindsight-embed/)
All data stays on your machine. The daemon auto-starts when needed and shuts down after inactivity.
## Configuration
### Cloud Mode
```
AI Coding Assistant
Hindsight Skill (SKILL.md)
hindsight-cli
Hindsight Cloud API (https://api.hindsight.vectorize.io)
Shared Memory Bank (team-accessible)
```
Data is stored in Hindsight Cloud and shared across your team. All team members with the same bank ID can access shared memories.
---
## Local Mode Setup
The skill uses configuration stored in `~/.hindsight/config.env`. Reconfigure anytime:
@@ -94,6 +135,110 @@ The skill uses configuration stored in `~/.hindsight/config.env`. Reconfigure an
uvx hindsight-embed configure
```
---
## Cloud Mode Setup
Cloud mode connects to [Hindsight Cloud](https://vectorize.io/hindsight/cloud), allowing teams to share memories about a codebase. When one team member learns something, everyone benefits.
### Prerequisites
1. A Hindsight Cloud account ([request access](https://vectorize.io/hindsight/cloud))
2. An API key from your team admin
3. A bank ID for your project (e.g., `team-acme-frontend`)
### Installation
Run the installer with cloud mode:
```bash
curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
```
You'll be prompted for:
| Setting | Description | Example |
|---------|-------------|---------|
| **Cloud API URL** | Hindsight Cloud endpoint | `https://api.hindsight.vectorize.io` |
| **API Key** | Your authentication key | `hs_xxx...` |
| **Bank ID** | Shared memory bank for your team | `team-acme-frontend` |
### Configuration Files
Cloud mode creates two files:
**`~/.hindsight/config`** — API connection settings (TOML format):
```toml
api_url = "https://api.hindsight.vectorize.io"
api_key = "hs_xxx..."
```
**`~/.claude/skills/hindsight/SKILL.md`** — Skill definition with your bank ID baked in.
### Team Setup
To set up cloud mode for your team:
1. **Team admin** creates a bank in Hindsight Cloud (e.g., `team-acme-frontend`)
2. **Team admin** generates API keys for each team member
3. **Each developer** runs the installer with their API key and the shared bank ID
4. All team members now share the same memory bank
### What to Store in Team Banks
Cloud mode uses a **shared team bank**. Be thoughtful about what goes in:
| Type | Examples | How to Store |
|------|----------|--------------|
| **Project conventions** | Linting rules, testing requirements, Node version | `"Project uses ESLint with Airbnb config"` |
| **Team knowledge** | Architecture decisions, common pitfalls, domain logic | `"Auth module requires Redis 7+"` |
| **Individual preferences** | Personal coding style, communication preferences | `"Alice prefers verbose commit messages"` |
**Key distinction**: Project conventions apply to everyone. Individual preferences should include the person's name so the AI knows when to apply them.
### Example Workflow
```
Day 1: Alice discovers a requirement
─────────────────────────────────────
Alice's AI assistant stores:
"The auth module requires Redis 7+ due to HEXPIRE command usage"
"Alice prefers explicit error handling over silent failures"
Day 2: Bob starts working on auth
─────────────────────────────────
Bob's AI assistant recalls:
"The auth module requires Redis 7+ due to HEXPIRE command usage"
Bob avoids the same issue Alice hit!
(Alice's personal preference is stored but won't be applied to Bob)
```
### Testing Cloud Connection
After installation, verify the connection:
```bash
# Store a test memory
hindsight memory retain team-acme-frontend "Test memory from setup"
# Recall it
hindsight memory recall team-acme-frontend "test"
```
### Switching Between Banks
If you work on multiple projects, you can have different skills installed for each AI assistant, or manually switch banks:
```bash
# Environment variable override (temporary)
HINDSIGHT_API_URL=https://api.hindsight.vectorize.io \
HINDSIGHT_API_KEY=hs_xxx \
hindsight memory recall different-bank "query"
```
For permanent multi-bank setups, reinstall the skill with a different bank ID.
## Troubleshooting
### Skill not activating
@@ -102,20 +247,55 @@ The skill activates based on its description matching your request. Try being ex
- "Remember that..." triggers storage
- "What do you know about..." triggers recall
### Daemon issues
### Local Mode Issues
**Daemon not starting:**
```bash
uvx hindsight-embed daemon status
uvx hindsight-embed daemon logs
```
### Reconfigure
**Reconfigure LLM provider:**
```bash
uvx hindsight-embed configure
```
### Cloud Mode Issues
**Authentication errors:**
```bash
# Verify your config
cat ~/.hindsight/config
# Test connection manually
hindsight bank list
```
**Wrong bank ID:**
Check your SKILL.md file to see which bank ID is configured:
```bash
cat ~/.claude/skills/hindsight/SKILL.md | grep "memory retain"
```
To change the bank ID, reinstall the skill:
```bash
curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
```
**Network/firewall issues:**
```bash
# Test connectivity to cloud API
curl -I https://api.hindsight.vectorize.io/health
```
## Requirements
### Local Mode
- Python 3.10+ (for `uvx`)
- An LLM API key (OpenAI, Anthropic, Groq, etc.)
### Cloud Mode
- Python 3.10+ (for `uvx`)
- Hindsight Cloud API key
- Network access to `https://api.hindsight.vectorize.io`
+277 -41
View File
@@ -6,11 +6,12 @@
# curl -fsSL https://hindsight.vectorize.io/get-skill | bash
#
# Options:
# --app <app> Target app: claude, opencode, codex
# --app <app> Target app: claude, opencode, codex
# --mode <mode> Mode: local (default) or cloud
#
# Examples:
# curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude
# curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app opencode
# curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude --mode cloud
#
set -e
@@ -62,8 +63,8 @@ print_banner() {
echo ""
}
# Embedded SKILL.md content
SKILL_CONTENT='---
# Embedded SKILL.md content for LOCAL mode (uses hindsight-embed with local daemon)
SKILL_CONTENT_LOCAL='---
name: hindsight
description: Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks.
---
@@ -139,6 +140,107 @@ uvx hindsight-embed memory reflect default "How should I approach this task base
4. **Recall first**: Always check for relevant context before starting work
'
# Template for CLOUD mode SKILL.md (uses hindsight-cli directly with remote API)
# The BANK_ID placeholder will be replaced during installation
SKILL_CONTENT_CLOUD_TEMPLATE='---
name: hindsight
description: Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. This is a shared team memory bank.
---
# Hindsight Memory Skill (Cloud)
You have persistent memory via **Hindsight Cloud**. This memory bank is **shared with the team**, so knowledge stored here benefits everyone working on this codebase.
**Proactively store team knowledge and recall context** to provide better assistance.
## Commands
### Store a memory
Use `memory retain` to store what you learn:
```bash
hindsight memory retain BANK_ID "Project uses ESLint with Airbnb config and Prettier for formatting"
hindsight memory retain BANK_ID "Running tests requires NODE_ENV=test" --context procedures
hindsight memory retain BANK_ID "Build failed when using Node 18, works with Node 20" --context learnings
hindsight memory retain BANK_ID "Alice prefers verbose commit messages with context" --context preferences
```
### Recall memories
Use `memory recall` BEFORE starting tasks to get relevant context:
```bash
hindsight memory recall BANK_ID "project conventions and coding standards"
hindsight memory recall BANK_ID "Alice preferences for this project"
hindsight memory recall BANK_ID "what issues have we encountered before"
hindsight memory recall BANK_ID "how does the auth module work"
```
### Reflect on memories
Use `memory reflect` to synthesize context:
```bash
hindsight memory reflect BANK_ID "How should I approach this task based on past experience?"
```
## IMPORTANT: When to Store Memories
This is a **shared team bank**. Store knowledge that benefits the team. For individual preferences, include the persons name.
### Project/Team Conventions (shared)
- Coding standards ("Project uses 2-space indentation")
- Required tools and versions ("Project requires Node 20+, PostgreSQL 15+")
- Linting and formatting rules ("ESLint with Airbnb config")
- Testing conventions ("Integration tests require Docker running")
- Branch naming and PR conventions
### Individual Preferences (attribute to person)
- Personal coding style ("Alice prefers explicit type annotations")
- Communication preferences ("Bob prefers detailed PR descriptions")
- Tool preferences ("Carol uses vim keybindings")
### Procedure Outcomes
- Steps that successfully completed a task
- Commands that worked (or failed) and why
- Workarounds discovered
- Configuration that resolved issues
### Learnings from Tasks
- Bugs encountered and their solutions
- Performance optimizations that worked
- Architecture decisions and rationale
- Dependencies or version requirements
### Team Knowledge
- Onboarding information for new team members
- Common pitfalls and how to avoid them
- Architecture decisions and their rationale
- Integration points with external systems
- Domain knowledge and business logic explanations
## IMPORTANT: When to Recall Memories
**Always recall** before:
- Starting any non-trivial task
- Making decisions about implementation
- Suggesting tools, libraries, or approaches
- Writing code in a new area of the project
- When answering questions about the codebase
- When a team member asks how something works
## Best Practices
1. **Store immediately**: When you discover something, store it right away
2. **Be specific**: Store "npm test requires --experimental-vm-modules flag" not "tests need a flag"
3. **Include outcomes**: Store what worked AND what did not work
4. **Recall first**: Always check for relevant context before starting work
5. **Think team-first**: Store knowledge that would help other team members
6. **Attribute individual preferences**: Store "Alice prefers X" not just "User prefers X"
7. **Distinguish project vs personal**: Project conventions apply to everyone; personal preferences are per-person
'
# Get skills directory for app (bash 3.x compatible)
get_skills_dir() {
case "$1" in
@@ -161,16 +263,18 @@ get_app_name() {
# Parse arguments
APP=""
MODE=""
show_usage() {
echo "Usage: $0 [--app <app>]"
echo "Usage: $0 [--app <app>] [--mode <mode>]"
echo ""
echo "Options:"
echo " --app <app> Target app: claude, opencode, codex"
echo " --app <app> Target app: claude, opencode, codex"
echo " --mode <mode> Mode: local (default) or cloud"
echo ""
echo "Examples:"
echo " $0 --app claude"
echo " $0 --app opencode"
echo " $0 --app claude --mode cloud"
exit 1
}
@@ -180,6 +284,10 @@ while [[ $# -gt 0 ]]; do
APP="$2"
shift 2
;;
--mode)
MODE="$2"
shift 2
;;
--help|-h)
show_usage
;;
@@ -233,6 +341,41 @@ fi
print_info "Installing for ${BOLD}$APP_NAME${NC}"
# Select mode (local vs cloud)
if [ -z "$MODE" ]; then
if [ -t 0 ] || [ -e /dev/tty ]; then
echo ""
echo -e "${DIM}Select deployment mode:${NC}"
echo ""
echo -e " ${BOLD}1)${NC} Local ${DIM}- Run Hindsight on your machine (default)${NC}"
echo -e " ${BOLD}2)${NC} Cloud ${DIM}- Connect to Hindsight Cloud (for teams)${NC}"
echo ""
if [ -t 0 ]; then
read -p "Enter choice [1]: " mode_choice
else
read -p "Enter choice [1]: " mode_choice </dev/tty
fi
mode_choice=${mode_choice:-1}
case $mode_choice in
1) MODE="local" ;;
2) MODE="cloud" ;;
*) MODE="local" ;;
esac
echo ""
else
MODE="local"
print_info "Non-interactive mode detected, defaulting to local"
fi
fi
# Validate mode
if [ "$MODE" != "local" ] && [ "$MODE" != "cloud" ]; then
print_error "Unknown mode '$MODE'. Supported: local, cloud"
fi
print_info "Mode: ${BOLD}$MODE${NC}"
# Step 1: Check for Python/uvx
print_step "Checking prerequisites"
@@ -241,40 +384,133 @@ if ! command -v python3 &> /dev/null && ! command -v uvx &> /dev/null; then
fi
print_success "Python/uvx available"
# Step 2: Configure LLM provider using the CLI
print_step "Configuring LLM provider"
# Configuration depends on mode
if [ "$MODE" = "local" ]; then
# LOCAL MODE: Configure LLM provider using hindsight-embed
print_step "Configuring LLM provider"
# Install/run hindsight-embed configure
# Redirect stdin from /dev/tty to avoid "not a terminal" warnings
if command -v uvx &> /dev/null; then
uvx hindsight-embed configure </dev/tty
else
pip install -q hindsight-embed
hindsight-embed configure </dev/tty
fi
# Install local skill
print_step "Installing skill to $APP_NAME"
mkdir -p "$SKILLS_DIR/hindsight"
echo "$SKILL_CONTENT_LOCAL" > "$SKILLS_DIR/hindsight/SKILL.md"
print_success "Installed to $SKILLS_DIR/hindsight/"
# Done (local)!
echo ""
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo -e "${GREEN} ✓ Installation Complete!${NC}"
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo ""
echo -e " The Hindsight skill is now available in ${BOLD}$APP_NAME${NC}."
echo ""
echo -e " ${DIM}Test the CLI:${NC}"
echo -e " ${CYAN}uvx hindsight-embed memory retain default \"Test memory\"${NC}"
echo -e " ${CYAN}uvx hindsight-embed memory recall default \"test\"${NC}"
echo ""
echo -e " ${DIM}$APP_NAME will automatically use the skill when relevant.${NC}"
echo ""
echo -e " ${DIM}Documentation:${NC} ${BLUE}https://hindsight.vectorize.io${NC}"
echo ""
# Install/run hindsight-embed configure
# Redirect stdin from /dev/tty to avoid "not a terminal" warnings
if command -v uvx &> /dev/null; then
uvx hindsight-embed configure </dev/tty
else
pip install -q hindsight-embed
hindsight-embed configure </dev/tty
# CLOUD MODE: Install CLI and configure connection to Hindsight Cloud
print_step "Installing Hindsight CLI"
# Download and install the CLI binary
curl -fsSL https://hindsight.vectorize.io/get-cli | bash
print_step "Configuring Hindsight Cloud connection"
DEFAULT_CLOUD_URL="https://api.hindsight.vectorize.io"
echo -e "${DIM}Enter your Hindsight Cloud connection details.${NC}"
echo -e "${DIM}Get these from your team admin or https://ui.hindsight.vectorize.io${NC}"
echo ""
# Prompt for cloud URL
if [ -t 0 ]; then
read -p "Cloud API URL [$DEFAULT_CLOUD_URL]: " CLOUD_URL
else
read -p "Cloud API URL [$DEFAULT_CLOUD_URL]: " CLOUD_URL </dev/tty
fi
CLOUD_URL=${CLOUD_URL:-$DEFAULT_CLOUD_URL}
# Prompt for API key
if [ -t 0 ]; then
read -p "API Key: " CLOUD_API_KEY
else
read -p "API Key: " CLOUD_API_KEY </dev/tty
fi
if [ -z "$CLOUD_API_KEY" ]; then
print_error "API Key is required for cloud mode"
fi
# Prompt for bank ID
if [ -t 0 ]; then
read -p "Bank ID (e.g., team-myproject): " CLOUD_BANK_ID
else
read -p "Bank ID (e.g., team-myproject): " CLOUD_BANK_ID </dev/tty
fi
if [ -z "$CLOUD_BANK_ID" ]; then
print_error "Bank ID is required for cloud mode"
fi
# Save config to ~/.hindsight/config
print_step "Saving configuration"
HINDSIGHT_CONFIG_DIR="$HOME/.hindsight"
HINDSIGHT_CONFIG_FILE="$HINDSIGHT_CONFIG_DIR/config"
mkdir -p "$HINDSIGHT_CONFIG_DIR"
# Write config file (TOML format for hindsight-cli)
cat > "$HINDSIGHT_CONFIG_FILE" << EOF
api_url = "$CLOUD_URL"
api_key = "$CLOUD_API_KEY"
EOF
# Set restrictive permissions on config file (contains API key)
chmod 600 "$HINDSIGHT_CONFIG_FILE"
print_success "Saved to $HINDSIGHT_CONFIG_FILE"
# Install cloud skill with bank ID substituted
print_step "Installing skill to $APP_NAME"
mkdir -p "$SKILLS_DIR/hindsight"
# Replace BANK_ID placeholder with actual bank ID
SKILL_CONTENT_CLOUD=$(echo "$SKILL_CONTENT_CLOUD_TEMPLATE" | sed "s/BANK_ID/$CLOUD_BANK_ID/g")
echo "$SKILL_CONTENT_CLOUD" > "$SKILLS_DIR/hindsight/SKILL.md"
print_success "Installed to $SKILLS_DIR/hindsight/"
# Done (cloud)!
echo ""
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo -e "${GREEN} ✓ Installation Complete!${NC}"
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo ""
echo -e " The Hindsight skill is now available in ${BOLD}$APP_NAME${NC}."
echo -e " Connected to: ${CYAN}$CLOUD_URL${NC}"
echo -e " Memory bank: ${CYAN}$CLOUD_BANK_ID${NC}"
echo ""
echo -e " ${DIM}Test the CLI:${NC}"
echo -e " ${CYAN}hindsight memory retain $CLOUD_BANK_ID \"Test memory\"${NC}"
echo -e " ${CYAN}hindsight memory recall $CLOUD_BANK_ID \"test\"${NC}"
echo ""
echo -e " ${DIM}Share this bank ID with your team for shared memories.${NC}"
echo -e " ${DIM}$APP_NAME will automatically use the skill when relevant.${NC}"
echo ""
echo -e " ${DIM}Documentation:${NC} ${BLUE}https://hindsight.vectorize.io${NC}"
echo ""
fi
# Step 3: Install skill to app's skills directory
print_step "Installing skill to $APP_NAME"
mkdir -p "$SKILLS_DIR/hindsight"
# Write embedded SKILL.md content
echo "$SKILL_CONTENT" > "$SKILLS_DIR/hindsight/SKILL.md"
print_success "Installed to $SKILLS_DIR/hindsight/"
# Done!
echo ""
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo -e "${GREEN} ✓ Installation Complete!${NC}"
echo -e "${GREEN}━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━${NC}"
echo ""
echo -e " The Hindsight skill is now available in ${BOLD}$APP_NAME${NC}."
echo ""
echo -e " ${DIM}Test the CLI:${NC}"
echo -e " ${CYAN}uvx hindsight-embed memory retain default \"Test memory\"${NC}"
echo -e " ${CYAN}uvx hindsight-embed memory recall default \"test\"${NC}"
echo ""
echo -e " ${DIM}$APP_NAME will automatically use the skill when relevant.${NC}"
echo ""
echo -e " ${DIM}Documentation:${NC} ${BLUE}https://hindsight.vectorize.io${NC}"
echo ""