Skip to main content

What Are Skills?

Skills are reusable procedures and domain knowledge that can be invoked by commands, agents, or users. They provide structured workflows for common coding tasks, enforce best practices, and capture learnings that compound over time.

11 Production Skills

Battle-tested workflows from real development sessions

Cross-Agent Support

Works with Claude Code, Cursor, and 32+ agents via SkillKit

Learning System

Self-correcting patterns that improve with every session

Orchestration Ready

Wire skills into multi-phase workflows with validation gates

Core Skills

The Pro Workflow system includes 11 specialized skills:
The master skill containing all core patterns:
  • Self-correction loop
  • Parallel worktrees for zero dead time
  • Context discipline and token management
  • Learning capture and replay
  • Multi-phase development orchestration
View full documentation →
Automate quality checks and create well-crafted commits:
  • Run lint, typecheck, tests on affected files
  • Scan for console.log, TODOs, secrets
  • Generate conventional commit messages
  • Stage specific files (never git add .)
View full documentation →
End sessions with intention:
  • Audit modified files and uncommitted changes
  • Run quality checks
  • Capture learnings from mistakes
  • Generate session summary
View full documentation →
Turn mistakes into permanent memory:
  • Extract lessons from corrections
  • Categorize by type (Navigation, Testing, Git, etc.)
  • Store with full context
  • Surface in future sessions
View full documentation →
Work on multiple tasks simultaneously:
  • Create isolated git worktrees
  • Run parallel sessions while tests run
  • Manage background agents
  • Clean up automatically
View full documentation →
Surface relevant learnings before starting work:
  • Search past corrections by keyword
  • Rank by relevance to current task
  • Flag high correction-rate areas
  • Suggest approaches based on history
View full documentation →
Generate handoff documents for session continuity:
  • Current branch and commit status
  • Completed, in-progress, pending tasks
  • Key decisions and reasoning
  • Copy-pasteable resume command
View full documentation →
Track patterns and productivity:
  • Learning category breakdown
  • Correction rate trends
  • Most/least applied patterns
  • Stale learnings that need review
View full documentation →
Clean up AI-generated over-engineering:
  • Remove unnecessary comments
  • Strip defensive try/catch blocks
  • Simplify premature abstractions
  • Delete backwards-compatibility hacks
View full documentation →
Manage context window and token budget:
  • Proactive compaction at 50%
  • MCP audit (keep <10 MCPs, <80 tools)
  • Subagent delegation patterns
  • CLAUDE.md optimization
View full documentation →
Wire Commands, Agents, and Skills together:
  • Research → Plan → Implement → Review
  • Validation gates between phases
  • Confidence scoring (GO/HOLD)
  • Never proceed without approval
View full documentation →

How Skills Work

Two Types of Skills

---
name: planner
skills: ["api-conventions", "project-patterns"]
---
# Full skill content injected at agent startup
# Always available, no invocation needed
Agent skills use context tokens but are always available. On-demand skills load only when called, keeping main context clean.

Invocation Methods

MethodExampleWhen to Use
Command/smart-commitUser-triggered workflows
Agent preloadskills: ["pro-workflow"]Domain knowledge always needed
Skill toolSkill("replay-learnings")AI-initiated, conditional use

Usage Patterns

Pattern 1: Self-Correction Loop

The most powerful pattern - Claude learns from corrections automatically:
User: You edited the wrong file
Claude: I edited src/utils.ts when you meant src/lib/utils.ts.

[LEARN] Navigation: Confirm full path before editing files with common names.

Should I add this?
After approval, the rule persists to memory. Future sessions avoid the same mistake.

Pattern 2: Session Lifecycle

Structured workflow from start to finish:

Pattern 3: Multi-Phase Development

For complex features requiring validation gates:
/develop "add webhook support"

[Research] → confidence score → GO/HOLD

[Plan] → present approach → wait for approval

[Implement] → quality gates every 5 edits

[Review] → security & quality check commit
Never skip phases. Never proceed without approval between phases.

Installation

/add-plugin pro-workflow
All 11 skills load automatically.

Quick Start

Minimal Setup (30 seconds)

Add to your CLAUDE.md:
## Pro Workflow

### Self-Correction
When corrected, propose rule → add to LEARNED after approval.

### Planning
Multi-file: plan first, wait for "proceed".

### Quality
After edits: lint, typecheck, test.

### LEARNED
<!-- Auto-populated through corrections -->

First Session

  1. Start with context: /replay what do I know about auth
  2. Make changes: Claude implements with quality gates
  3. Capture mistakes: “Remember this” triggers learn-rule
  4. Commit: /smart-commit runs quality checks automatically
  5. End intentionally: /wrap-up captures learnings and generates summary
  6. Handoff: /handoff creates resume context for next session

Integration with Pro Workflow

Skills work seamlessly with other Pro Workflow components:

Agents

5 specialized agents with skills preloaded

Commands

10 slash commands that invoke skills

Hooks

18 hook events that trigger skills

Rules

6 Cursor rules enforce skill patterns

Philosophy

1

Compound Improvements

Small corrections lead to big gains over time. After 50 sessions, Claude barely needs correcting.
2

Trust but Verify

Let AI work between checkpoints. Review at planning, milestones, destructive operations.
3

Zero Dead Time

Parallel worktrees keep momentum while tests run or builds compile.
4

Memory is Precious

Both yours and Claude’s. Context discipline, proactive compaction, subagent delegation.
5

Orchestrate, Don't Micromanage

Wire patterns together with Command > Agent > Skill. Let agents execute.

Next Steps

Learn the Core Workflow

Master the complete AI coding workflow system

Start with Smart Commit

Add quality gates to your commit process

Try Multi-Phase Dev

Build features through structured phases

Optimize Context

Manage your token budget effectively

Build docs developers (and LLMs) love