Skip to main content

​
Skills System

Panopticon’s skills system provides reusable workflows and best practices for AI agents.

​
What Are Skills

Skills are reusable, shareable workflows that encode best practices for common development tasks. They are:
  • Universal - Work across all AI coding tools (Claude Code, Cursor, Windsurf, etc.)
  • Shareable - Distribute via pan sync to sync to all connected AI tools
  • Contextual - Invoked with /skill-name in AI tool prompts
  • Best-practice-driven - Encode proven workflows and checklists
Skills eliminate the need to repeatedly explain how to do common tasks. Instead of telling an agent “please review this code for security issues”, you invoke /code-review-security and the agent follows the established workflow.

​
Built-In Skills

Panopticon ships with 67+ built-in skills organized by category:

​
Development Workflows

SkillDescription
feature-workStandard feature implementation workflow
bug-fixSystematic bug investigation and fixing
refactorSafe refactoring with tests first
code-reviewComprehensive code review checklist
code-review-securityOWASP Top 10 security analysis
code-review-performanceAlgorithm and resource optimization
releaseStep-by-step release process
dependency-updateSafe dependency updates
incident-responseProduction incident handling
onboard-codebaseUnderstanding new codebases
work-completeChecklist for completing agent work

​
AI Self-Monitoring

SkillDescription
knowledge-captureCaptures learnings when AI gets confused or corrected
refactor-radarDetects systemic issues causing AI confusion
session-healthDetect and clean up stuck sessions

​
Panopticon Operations (pan-*)

SkillDescription
pan-helpShow all Panopticon commands
pan-upStart dashboard and services
pan-downStop dashboard and services
pan-statusShow running agents
pan-issueSpawn agent for an issue
pan-planCreate execution plan for issue
pan-tellSend message to running agent
pan-killKill a running agent
pan-approveApprove agent work and merge
pan-healthCheck system health
pan-syncSync skills to AI tools
pan-installInstall prerequisites
pan-setupInitial setup wizard
pan-quickstartQuick start guide
pan-projectsManage registered projects
pan-trackerIssue tracker operations
pan-logsView agent logs
pan-rescueRecover crashed agents
pan-diagnoseDiagnose agent issues
pan-dockerDocker operations
pan-networkNetwork diagnostics
pan-configConfiguration management
pan-restartSafely restart Panopticon dashboard and services
pan-code-reviewOrchestrate parallel code review (3 reviewers + synthesis)
pan-convoy-synthesisSynthesize convoy coordination
pan-subagent-creatorCreate specialized subagents
pan-skill-creatorCreate new skills (guided)
pan-reopenReopen completed issue for re-work
pan-overseeSupervise agent through full work lifecycle
pan-sync-mainSync latest main into workspace feature branch
pan-docsSearch Panopticon documentation
pan-tldrToken-efficient codebase analysis

​
Utilities

SkillDescription
beadsGit-backed issue tracking with dependencies
skill-creatorGuide for creating new skills
web-design-guidelinesUI/UX review checklist
clear-writingProven rules for clearer prose in docs, commits, and UI text
crash-investigationInvestigate system crashes, OOM kills, and freezes
opus-planOpus-driven planning with PRD, STATE.md, and beads
spec-readinessEvaluate issue requirements readiness (scored 0-100)
check-mergedVerify if a feature branch has been merged into main
react-best-practicesReact/Next.js performance optimization from Vercel
stitch-design-mdSynthesize Stitch designs into DESIGN.md files

​
Using Skills

Skills are invoked via slash commands in any AI coding tool: 
# In Claude Code, Cursor, Windsurf, etc:
/feature-work
/code-review-security
/bug-fix
/pan-help
When you invoke a skill, the AI tool injects the skill’s prompt into the conversation, giving the agent detailed instructions on how to proceed.

​
Creating Custom Skills

Skills are markdown files stored in ~/.panopticon/skills/. Create your own with: 
# Use the guided skill creator
/pan-skill-creator

# Or manually create a skill
mkdir -p ~/.panopticon/skills/my-custom-skill
cat > ~/.panopticon/skills/my-custom-skill/skill.md <<'EOF'
# My Custom Skill

Brief description of what this skill does.

## When to Use

Describe when this skill should be invoked.

## Steps

1. Step 1 description
2. Step 2 description
3. Step 3 description

## Best Practices

- Tip 1
- Tip 2
EOF

# Sync to all AI tools
pan sync
Skill anatomy: 
# Skill Title

One-line description.

## When to Use

When to invoke this skill (triggers).

## Steps

1. Detailed step-by-step instructions
2. With specific commands or patterns
3. And expected outcomes

## Checklist

- [ ] Item 1
- [ ] Item 2
- [ ] Item 3

## Examples

\`\`\`bash
# Example command
\`\`\`

## Related Skills

- /other-skill - When to use instead
- /complementary-skill - Use together with this
See the skill-creator skill or use /pan-skill-creator for guided creation.

​
Skill Distribution

Skills can be distributed via:
  1. Project-specific - Store in .panopticon/skills/ in your repo
  2. User-specific - Store in ~/.panopticon/skills/ (synced to AI tools)
  3. Team-shared - Commit to version control and share via git
  4. Public packages - Distribute via npm or GitHub

​
Syncing Skills

# Sync all skills to AI tools (Claude Code, Cursor, etc.)
pan sync

# Only sync skills (skip agents, hooks)
pan sync --skills-only

# Verify sync status
pan sync --dry-run
The pan sync command:
  • Copies skills from ~/.panopticon/skills/ to each AI tool’s config directory
  • Updates existing skills if versions differ
  • Preserves local customizations (doesn’t overwrite modified files)

​
Subagents

Panopticon includes specialized subagent templates for common development tasks. Subagents are invoked via the Task tool or convoy orchestration for parallel execution.

​
Code Review Subagents

SubagentModelFocusOutput
code-review-correctnesshaikuLogic errors, edge cases, type safety.claude/reviews/<timestamp>-correctness.md
code-review-securitysonnetOWASP Top 10, vulnerabilities.claude/reviews/<timestamp>-security.md
code-review-performancehaikuAlgorithms, N+1 queries, memory.claude/reviews/<timestamp>-performance.md
code-review-synthesissonnetCombines all findings into unified report.claude/reviews/<timestamp>-synthesis.md
Usage Example: 
/pan-code-review --files "src/auth/*.ts"
This spawns all three reviewers in parallel, then synthesizes their findings into a prioritized report.

​
Planning & Exploration Subagents

SubagentModelFocusPermission Mode
planning-agentsonnetCodebase research, execution planningplan (read-only)
codebase-explorerhaikuFast architecture discovery, pattern findingplan (read-only)
triage-agenthaikuIssue categorization, complexity estimationdefault
health-monitorhaikuAgent stuck detection, log analysisdefault
Usage Examples: 
# Explore codebase architecture
Task(subagent_type='codebase-explorer', prompt='Map out the authentication system')

# Triage an issue
Task(subagent_type='triage-agent', prompt='Categorize and estimate ISSUE-123')

# Check agent health
Task(subagent_type='health-monitor', prompt='Check status of all running agents')

​
Best Practices

When creating skills:
  • Be specific - Include exact commands, not just concepts
  • Include examples - Show concrete usage patterns
  • Add checklists - Help agents verify completion
  • Cross-reference - Link to related skills and guides
  • Test thoroughly - Verify skills work end-to-end
When using skills:
  • Invoke early - Start with a skill, don’t switch mid-task
  • Follow fully - Don’t skip steps or customize on-the-fly
  • Report issues - If a skill doesn’t work, improve it
  • Combine wisely - Some skills complement each other, others conflict