will/claude-code
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor remaining skills with resources pattern and allowed-tools

Browse Source 
- k8s-quick-status: Add scripts/quick-status.sh, allowed-tools
- sysadmin-health: Add scripts/health-check.sh, allowed-tools
- usage: Add scripts/usage_report.py, simplify SKILL.md
- programmer-add-project: Add allowed-tools

All skills now:
- Have executable scripts for main operations
- Use allowed-tools to restrict capabilities
- Have improved descriptions with trigger phrases
- Follow the "Skill with Bundled Resources" pattern

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
OpenCode Test
2026-01-01 02:38:58 -08:00
parent daac279fa4
commit d9be8145f8
7 changed files with 316 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
skills/k8s-quick-status/SKILL.md
View File

@@ -1,43 +1,61 @@
---
name: k8s-quick-status
description: Quick cluster health pulse check
model: haiku
description: Quick cluster health pulse check. Use when asked about cluster status, k8s health, or kubernetes overview.
allowed-tools:
- Bash
- Read
---
# K8s Quick Status Skill
Performs a lightweight health pulse check on the Raspberry Pi Kubernetes cluster.
## Quick Command
```bash
~/.claude/skills/k8s-quick-status/scripts/quick-status.sh
```
Or run individual checks:
```bash
# Node status
kubectl get nodes -o wide
# Unhealthy pods
kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded
# Warning events
kubectl get events -A --field-selector=type=Warning --sort-by='.lastTimestamp' | tail -10
# ArgoCD apps
argocd app list
```
## Checks Performed
### Node Status
- Node readiness (`kubectl get nodes`)
- Node conditions (MemoryPressure, DiskPressure, PIDPressure)
### Pod Health
- Unhealthy pods (`kubectl get pods -A --field-selector=status.phase!=Running`)
- High restart counts (pods with >5 restarts)
### Recent Events
- Warning events in last hour (`kubectl get events -A --field-selector=type=Warning --sort-by='.lastTimestamp'`)
### ArgoCD Status
- Application sync status (`argocd app list`)
- Any OutOfSync or Degraded apps
| Check | Command | What It Shows |
|-------|---------|---------------|
| Nodes | `kubectl get nodes` | Readiness, conditions |
| Pods | `kubectl get pods -A` | Unhealthy pods |
| Restarts | jsonpath query | Pods with >5 restarts |
| Events | `kubectl get events` | Recent warnings |
| ArgoCD | `argocd app list` | Sync status |
## Output Format
Report as structured summary with:
- Overall status (healthy/warning/critical)
- Node summary table
- Unhealthy pods list (if any)
- ArgoCD app status
- Immediate concerns (if any)
## Autonomy
This skill is read-only and can run without confirmation.
Report as structured summary:
- **Overall status**: healthy/warning/critical
- **Node summary**: table of nodes
- **Issues**: unhealthy pods, high restarts
- **ArgoCD**: sync status
- **Concerns**: immediate action items
## When to Use
Use this skill for a quick pulse check. For comprehensive analysis with metrics and detailed recommendations, use the `/cluster-status` command which invokes the full `cluster-health-check` workflow.
- Quick pulse check: use this skill
- Comprehensive analysis: use `/cluster-status` command
## Autonomy
Read-only - runs without confirmation.

28
skills/k8s-quick-status/scripts/quick-status.sh Executable file
View File

@@ -0,0 +1,28 @@
#!/bin/bash
# Quick Kubernetes cluster status check
# Returns structured output for easy parsing
set -euo pipefail
echo "=== Node Status ==="
kubectl get nodes -o wide 2>/dev/null || echo "Error: Cannot reach cluster"
echo ""
echo "=== Unhealthy Pods ==="
kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded 2>/dev/null | grep -v "^NAMESPACE" || echo "All pods healthy"
echo ""
echo "=== High Restart Pods ==="
kubectl get pods -A -o jsonpath='{range .items[?(@.status.containerStatuses[0].restartCount>5)]}{.metadata.namespace}/{.metadata.name}: {.status.containerStatuses[0].restartCount} restarts{"\n"}{end}' 2>/dev/null || echo "No high restart pods"
echo ""
echo "=== Recent Warning Events ==="
kubectl get events -A --field-selector=type=Warning --sort-by='.lastTimestamp' 2>/dev/null | tail -10 || echo "No warning events"
echo ""
echo "=== ArgoCD Apps ==="
if command -v argocd &>/dev/null; then
argocd app list --output wide 2>/dev/null || echo "ArgoCD not accessible"
else
echo "ArgoCD CLI not installed"
fi

6
skills/programmer-add-project/SKILL.md
View File

@@ -1,6 +1,10 @@
---
name: programmer-add-project
description: Register a new project with the programmer agent system
description: Register a new project with the programmer agent system. Use when adding a new codebase or project.
allowed-tools:
- Bash
- Read
- Write
---
# Add Project to Programmer Agent

89
skills/sysadmin-health/SKILL.md
View File

@@ -1,51 +1,70 @@
---
name: sysadmin-health
description: Run comprehensive health check on Arch Linux workstation
model: haiku
description: Comprehensive health check on Arch Linux workstation. Use when asked about system health, disk space, memory, updates, or services.
allowed-tools:
- Bash
- Read
---
# Sysadmin Health Check Skill
Performs a comprehensive health check on the local Arch Linux workstation.
## Quick Command
```bash
~/.claude/skills/sysadmin-health/scripts/health-check.sh
```
Or run individual checks:
```bash
# Resources
df -h / /home
free -h
uptime
# Packages
checkupdates | wc -l
yay -Qua | wc -l
pacman -Qtdq | wc -l
# Services
systemctl --failed
systemctl --user --failed
# Logs
journalctl -p err --since "24 hours ago" -n 10
```
## Checks Performed
### System Resources
- Disk usage (`df -h`)
- Memory usage (`free -h`)
- Swap usage
- CPU load (`uptime`)
- Top processes by resource usage
### Package Status
- Pending pacman updates (`checkupdates`)
- AUR updates available (`yay -Qua`)
- Orphaned packages (`pacman -Qtdq`)
- Package cache size (`du -sh /var/cache/pacman/pkg`)
### Service Status
- Failed systemd services (`systemctl --failed`)
- Key services status (NetworkManager, sshd, etc.)
### User Timers (Claude Automation)
- Active user timers (`systemctl --user list-timers`)
- Failed user services (`systemctl --user --failed`)
- Recent timer runs (`journalctl --user -u k8s-agent-health-check --since "24 hours ago" -n 5`)
### Security
- Recent failed login attempts (`journalctl -u sshd --since "24 hours ago" | grep -i failed`)
- Last logins (`last -n 5`)
### Logs
- Recent errors in journal (`journalctl -p err --since "24 hours ago" -n 20`)
| Category | Checks |
|----------|--------|
| **Resources** | Disk, memory, swap, CPU load |
| **Packages** | Pacman updates, AUR updates, orphans |
| **Services** | Failed systemd services (system + user) |
| **Security** | Recent logins, failed SSH attempts |
| **Logs** | Recent errors in journal |
## Output Format
Report as structured summary with:
- Overall health status (healthy/warning/critical)
- Issues found (if any)
- Recommended actions
Report as structured summary:
- **Overall health**: healthy/warning/critical
- **Resource usage**: disk %, memory %
- **Pending updates**: count
- **Failed services**: list
- **Issues found**: with recommendations
## Thresholds
| Metric | Warning | Critical |
|--------|---------|----------|
| Disk usage | >80% | >95% |
| Memory usage | >80% | >95% |
| Pending updates | >20 | >50 |
| Failed services | any | any critical |
## Autonomy
This skill is read-only and can run without confirmation.
Read-only - runs without confirmation.

45
skills/sysadmin-health/scripts/health-check.sh Executable file
View File

@@ -0,0 +1,45 @@
#!/bin/bash
# Comprehensive Arch Linux health check
# Returns structured output for easy parsing
set -euo pipefail
echo "=== System Resources ==="
echo "--- Disk Usage ---"
df -h / /home 2>/dev/null || df -h
echo ""
echo "--- Memory ---"
free -h
echo ""
echo "--- Load ---"
uptime
echo ""
echo "=== Package Status ==="
echo "--- Pending Updates ---"
checkupdates 2>/dev/null | wc -l | xargs echo "Pacman updates:"
yay -Qua 2>/dev/null | wc -l | xargs echo "AUR updates:" || echo "AUR updates: N/A"
echo ""
echo "--- Orphaned Packages ---"
pacman -Qtdq 2>/dev/null | wc -l | xargs echo "Orphans:" || echo "Orphans: 0"
echo ""
echo "=== Service Status ==="
echo "--- Failed Services ---"
systemctl --failed --no-pager 2>/dev/null || echo "No failed services"
echo ""
echo "--- Failed User Services ---"
systemctl --user --failed --no-pager 2>/dev/null || echo "No failed user services"
echo ""
echo "=== Recent Errors ==="
journalctl -p err --since "24 hours ago" -n 10 --no-pager 2>/dev/null || echo "No recent errors"
echo ""
echo "=== Security ==="
echo "--- Recent Logins ---"
last -n 5 2>/dev/null || echo "No login history"

147
skills/usage/SKILL.md
View File

@@ -1,6 +1,6 @@
---
name: usage
description: Track and report model usage across sessions
description: Track and report model usage across sessions. Use when asked about usage, stats, or session history.
allowed-tools:
- Bash
- Read
@@ -10,13 +10,13 @@ allowed-tools:
Query session history and report usage statistics.
## Data Sources
## Quick Command
| Source | Status | Data Available |
|--------|--------|----------------|
| `history/index.json` | Available | Session IDs, start times |
| `history/*.jsonl` | Future | Session content, commands, tokens |
| `usage/config.json` | Available | Log level, preferences |
```bash
python3 ~/.claude/skills/usage/scripts/usage_report.py [range]
```
Ranges: `today`, `week` (default), `month`, `all`
## Command Routing
@@ -27,11 +27,29 @@ Query session history and report usage statistics.
| `/usage week` | Last 7 days |
| `/usage month` | Last 30 days |
| `/usage all` | All time stats |
| `/usage --by agent` | Group by agent |
| `/usage --by skill` | Group by skill |
| `/usage --by model` | Group by model tier |
| `/usage --set-level <level>` | Set log level |
| `/usage --show-config` | Show current config |
## Data Sources
| Source | Status | Data |
|--------|--------|------|
| `history/index.json` | Available | Session IDs, start times |
| `usage/config.json` | Available | Log level, preferences |
## Output Format
```
📊 Usage Summary — Week
Sessions: 12
Total time: 8h 32m
Days active: 5
Model: opus (primary)
📅 Sessions by Date:
2026-01-01: 3 sessions (95m)
2025-12-31: 4 sessions (120m)
...
```
## Log Levels
@@ -41,111 +59,6 @@ Query session history and report usage statistics.
| `standard` | + agents, skills, tokens (default) |
| `detailed` | + commands, delegations, errors |
## Implementation
### Query Sessions
```python
import json
from datetime import datetime, timedelta
from pathlib import Path
from zoneinfo import ZoneInfo
LOCAL_TZ = ZoneInfo('America/Los_Angeles')
HISTORY_DIR = Path.home() / ".claude/state/personal-assistant/history"
CONFIG_PATH = Path.home() / ".claude/state/usage/config.json"
def load_sessions():
index_path = HISTORY_DIR / "index.json"
if not index_path.exists():
return []
with open(index_path) as f:
data = json.load(f)
return data.get("sessions", [])
def filter_sessions(sessions, range_type="week"):
now = datetime.now(LOCAL_TZ)
if range_type == "today":
cutoff = now.replace(hour=0, minute=0, second=0, microsecond=0)
elif range_type == "week":
cutoff = now - timedelta(days=7)
elif range_type == "month":
cutoff = now - timedelta(days=30)
else: # all
return sessions
filtered = []
for s in sessions:
started = datetime.fromisoformat(s["started"])
if started >= cutoff:
filtered.append(s)
return filtered
def estimate_duration(sessions):
"""Estimate session duration from consecutive start times."""
if not sessions:
return []
sorted_sessions = sorted(sessions, key=lambda s: s["started"])
for i, session in enumerate(sorted_sessions):
if i + 1 < len(sorted_sessions):
start = datetime.fromisoformat(session["started"])
next_start = datetime.fromisoformat(sorted_sessions[i + 1]["started"])
duration = (next_start - start).total_seconds() / 60
# Cap at 2 hours (likely session gap)
session["duration_mins"] = min(duration, 120)
else:
# Current/last session: estimate 30 mins
session["duration_mins"] = 30
return sorted_sessions
```
### Generate Report
```python
def generate_report(sessions, range_type="week"):
total_mins = sum(s.get("duration_mins", 0) for s in sessions)
hours = int(total_mins // 60)
mins = int(total_mins % 60)
report = f"""
📊 Usage Summary — {range_type.title()}
Sessions: {len(sessions)}
Total time: {hours}h {mins}m
Model: opus (primary)
"""
return report
```
## Output Format
```
📊 Usage Summary — Last 7 Days
Sessions: 12
Total time: 8h 32m
Model: opus (primary)
┌─────────────┬──────────┬────────┐
│ Agent │ Sessions │ Time │
├─────────────┼──────────┼────────┤
│ PA │ 12 │ 8h 32m │
└─────────────┴──────────┴────────┘
Note: Detailed metrics available when session
content logging is enabled.
```
## Future Enhancements
When `history/*.jsonl` files are available:
- Parse actual commands used
- Detect skill invocations
- Count delegations (sonnet/haiku)
- Estimate token usage
- Track errors
## Policy
- Read-only operations

109
skills/usage/scripts/usage_report.py Executable file
View File

@@ -0,0 +1,109 @@
#!/usr/bin/env python3
"""Generate usage statistics from session history."""
import json
import sys
from datetime import datetime, timedelta
from pathlib import Path
from zoneinfo import ZoneInfo
LOCAL_TZ = ZoneInfo('America/Los_Angeles')
HISTORY_DIR = Path.home() / ".claude/state/personal-assistant/history"
CONFIG_PATH = Path.home() / ".claude/state/usage/config.json"
def load_sessions():
"""Load sessions from history index."""
index_path = HISTORY_DIR / "index.json"
if not index_path.exists():
return []
with open(index_path) as f:
data = json.load(f)
return data.get("sessions", [])
def filter_sessions(sessions, range_type="week"):
"""Filter sessions by time range."""
now = datetime.now(LOCAL_TZ)
if range_type == "today":
cutoff = now.replace(hour=0, minute=0, second=0, microsecond=0)
elif range_type == "week":
cutoff = now - timedelta(days=7)
elif range_type == "month":
cutoff = now - timedelta(days=30)
else: # all
return sessions
filtered = []
for s in sessions:
try:
started = datetime.fromisoformat(s["started"])
if started.tzinfo is None:
started = started.replace(tzinfo=LOCAL_TZ)
if started >= cutoff:
filtered.append(s)
except (KeyError, ValueError):
continue
return filtered
def estimate_duration(sessions):
"""Estimate session duration from consecutive start times."""
if not sessions:
return []
sorted_sessions = sorted(sessions, key=lambda s: s["started"])
for i, session in enumerate(sorted_sessions):
if i + 1 < len(sorted_sessions):
start = datetime.fromisoformat(session["started"])
next_start = datetime.fromisoformat(sorted_sessions[i + 1]["started"])
duration = (next_start - start).total_seconds() / 60
# Cap at 2 hours (likely session gap)
session["duration_mins"] = min(duration, 120)
else:
# Current/last session: estimate 30 mins
session["duration_mins"] = 30
return sorted_sessions
def generate_report(sessions, range_type="week"):
"""Generate usage report."""
sessions = estimate_duration(sessions)
total_mins = sum(s.get("duration_mins", 0) for s in sessions)
hours = int(total_mins // 60)
mins = int(total_mins % 60)
# Group by date
by_date = {}
for s in sessions:
date = s["started"][:10]
by_date.setdefault(date, []).append(s)
report = f"""📊 Usage Summary — {range_type.title()}
Sessions: {len(sessions)}
Total time: {hours}h {mins}m
Days active: {len(by_date)}
Model: opus (primary)
"""
if by_date:
report += "\n📅 Sessions by Date:\n"
for date in sorted(by_date.keys(), reverse=True)[:7]:
count = len(by_date[date])
day_mins = sum(s.get("duration_mins", 0) for s in by_date[date])
report += f" {date}: {count} sessions ({int(day_mins)}m)\n"
return report
def main():
range_type = sys.argv[1] if len(sys.argv) > 1 else "week"
sessions = load_sessions()
filtered = filter_sessions(sessions, range_type)
report = generate_report(filtered, range_type)
print(report)
if __name__ == "__main__":
main()