🇺🇸English
/help - Workspace Discovery
Guide users through the capabilities of this workspace setup.
Usage
/help # Interactive guided discovery
/help workflows # Workflow orchestration skills
/help agents # Specialist agents catalog
/help tools # CLI tools (tldr, prove, recall)
/help hooks # Active hooks and what they do
/help advanced # MCP, frontmatter, customization
/help <name> # Deep dive on specific skill/agent
Behavior Based on Arguments
No Arguments: Interactive Discovery
Use AskUserQuestion to guide the user:
question: "What are you trying to do?"
header: "Goal"
options:
- label: "Explore/understand a codebase"
description: "Find patterns, architecture, conventions"
- label: "Fix a bug"
description: "Investigate, diagnose, implement fix"
- label: "Build a feature"
description: "Plan, implement, test new functionality"
- label: "Prove something mathematically"
description: "Formal verification with Lean 4"
Based on response, show relevant tools:
| Goal | Show |
|---|
| Explore codebase | scout agent, tldr CLI, /explore workflow |
| Fix a bug | /fix workflow, sleuth agent, debug-agent |
| Build feature | /build workflow, architect agent, kraken agent |
| Prove math | /prove skill, lean4 skill, Godel-Prover |
| Research docs | oracle agent, nia-docs, perplexity |
| Configure workspace | hooks, rules, settings, frontmatter |
/help workflows
Display workflow meta-skills:
## Workflow Skills
Orchestrate multi-agent pipelines for complex tasks.
| Workflow | Purpose | Agents Used |
|----------|---------|-------------|
| /fix | Bug investigation → diagnosis → implementation | sleuth → kraken → arbiter |
| /build | Feature planning → implementation → testing | architect → kraken → arbiter |
| /debug | Deep investigation of issues | debug-agent, sleuth |
| /tdd | Test-driven development cycle | arbiter → kraken → arbiter |
| /refactor | Code transformation with safety | phoenix → kraken → judge |
| /review | Code review and feedback | critic, judge |
| /security | Vulnerability analysis | aegis |
| /explore | Codebase discovery | scout |
| /test | Test execution and validation | arbiter, atlas |
| /release | Version bumps, changelog | herald |
| /migrate | Framework/infrastructure changes | pioneer, phoenix |
**Usage**: Just describe your goal. Claude routes to the right workflow.
/help agents
Display agent catalog:
## Specialist Agents
Spawn via Task tool with subagent_type.
### Exploration & Research
| Agent | Purpose | Model |
|-------|---------|-------|
| scout | Codebase exploration, pattern finding | sonnet |
| oracle | External research (web, docs, APIs) | sonnet |
| pathfinder | External repository analysis | sonnet |
### Planning & Architecture
| Agent | Purpose | Model |
|-------|---------|-------|
| architect | Feature planning, design docs | sonnet |
| plan-agent | Create implementation plans | sonnet |
| phoenix | Refactoring & migration planning | sonnet |
### Implementation
| Agent | Purpose | Model |
|-------|---------|-------|
| kraken | TDD implementation, refactoring | sonnet |
| spark | Quick fixes, lightweight changes | haiku |
### Review & Validation
| Agent | Purpose | Model |
|-------|---------|-------|
| arbiter | Test execution, validation | sonnet |
| critic | Code review | sonnet |
| judge | Refactoring review | sonnet |
### Investigation
| Agent | Purpose | Model |
|-------|---------|-------|
| sleuth | Bug investigation, root cause | sonnet |
| debug-agent | Issue investigation with logs | sonnet |
| profiler | Performance, race conditions | sonnet |
### Documentation & Handoff
| Agent | Purpose | Model |
|-------|---------|-------|
| scribe | Documentation, session summaries | sonnet |
| chronicler | Session analysis, learning extraction | sonnet |
/help tools
Display CLI tools and capabilities:
## Built-in Tools
### TLDR Code Analysis
Token-efficient code exploration (95% savings vs reading raw files).
```bash
tldr tree src/ # File tree
tldr structure src/ --lang python # Code structure (codemaps)
tldr search "pattern" src/ # Search files
tldr cfg file.py func # Control flow graph
tldr dfg file.py func # Data flow graph
tldr impact func src/ # Reverse call graph (who calls this?)
tldr dead src/ # Find dead code
tldr arch src/ # Detect architectural layers
/prove - Formal Verification
Machine-verified proofs without learning Lean syntax.
/prove every group homomorphism preserves identity
/prove continuous functions on compact sets are uniformly continuous
Requires: LM Studio running Godel-Prover model locally.
Memory System
Store and recall learnings across sessions.
# Recall past learnings
(cd opc && uv run python scripts/core/recall_learnings.py --query "hook patterns")
# Store new learning (via /remember skill)
/remember "Hook X works by..."
Premortem Risk Analysis
Identify failure modes before they occur.
/premortem [plan-file] # Analyze implementation plan for risks
### /help hooks
Display active hooks:
```markdown
## Active Hooks
Hooks extend Claude's behavior at key lifecycle points.
### Session Lifecycle
| Hook | Event | Purpose |
|------|-------|---------|
| session-register | SessionStart | Register session in coordination DB |
| session-start-recall | SessionStart | Auto-inject relevant learnings |
| session-end-cleanup | SessionEnd | Cleanup temp files |
| session-outcome | SessionEnd | Prompt for session outcome |
### User Prompt Processing
| Hook | Event | Purpose |
|------|-------|---------|
| skill-activation-prompt | UserPromptSubmit | Suggest relevant skills |
| premortem-suggest | UserPromptSubmit | Suggest risk analysis for implementations |
### Tool Interception
| Hook | Event | Purpose |
|------|-------|---------|
| tldr-read-enforcer | PreToolUse:Read | Suggest tldr for large files |
| smart-search-router | PreToolUse:Grep | Route to ast-grep for structural search |
| file-claims | PreToolUse:Edit | Track which sessions edit which files |
| signature-helper | PreToolUse:Edit | Inject function signatures |
| import-validator | PostToolUse:Edit | Validate imports after edits |
### Validation
| Hook | Event | Purpose |
|------|-------|---------|
| typescript-preflight | PreToolUse:Bash | Type-check before running |
| compiler-in-the-loop | Stop | Run Lean compiler for /prove |
### Subagent Coordination
| Hook | Event | Purpose |
|------|-------|---------|
| subagent-start | SubagentStart | Initialize agent context |
| subagent-stop | SubagentStop | Extract learnings from agents |
/help advanced
Display advanced customization:
## Advanced: Customization & Extension
### Skill Frontmatter
Skills use YAML frontmatter for metadata and tool restrictions:
```yaml
---
name: my-skill
description: What it does
triggers: ["keyword1", "keyword2"]
allowed-tools: [Bash, Read, Edit]
priority: high
skills: [other-skill] # Auto-load dependencies
---
Agent Frontmatter
Agents declare their capabilities:
---
name: my-agent
description: Specialist for X
model: sonnet|haiku|claude-opus-4-5-20251101
tools: [Read, Grep, Glob, Bash]
---
MCP Servers
External tool integrations:
| Server | Purpose |
|---|
| ast-grep | Structural code search/refactoring |
| firecrawl | Web scraping |
| github-search | Search GitHub code/issues |
| morph | Fast file editing (10k tokens/sec) |
| nia | Documentation search |
| perplexity | AI-powered web research |
Rules (.claude/rules/*.md)
Always-on instructions injected into context:
claim-verification.md - Verify before assertingdynamic-recall.md - How to use memory systemtldr-cli.md - TLDR usage reference
Creating Custom Skills
mkdir -p .claude/skills/my-skill
# Create .claude/skills/my-skill/SKILL.md with frontmatter
Creating Custom Agents
# Create .claude/agents/my-agent.md with frontmatter
### /help <specific-name>
For specific skill/agent lookup:
1. Search for matching skill: `.claude/skills/<name>/SKILL.md`
2. Search for matching agent: `.claude/agents/<name>.md`
3. Read the file and display:
- Description
- Usage examples
- When to use
- Related skills/agents
## Dynamic Discovery
To keep help current, dynamically read frontmatter:
```bash
# List all skills with descriptions
for f in .claude/skills/*/SKILL.md; do
head -10 "$f" | grep -E "^(name|description):"
done
# List all agents
for f in .claude/agents/*.md; do
head -10 "$f" | grep -E "^(name|description):"
done
Example Interaction
User : /help
Claude :
What are you trying to do?
[ ] Explore/understand a codebase
Find patterns, architecture, conventions
[ ] Fix a bug
Investigate, diagnose, implement fix
[ ] Build a feature
Plan, implement, test new functionality
[ ] Prove something mathematically
Formal verification with Lean 4
[Other: describe your goal]
User selects : "Fix a bug"
Claude :
## Bug Fixing Tools
### Quick Path
Just describe the bug. I'll use the /fix workflow automatically.
### Manual Control
- **sleuth** agent: Deep investigation, root cause analysis
- **debug-agent**: Log analysis, state inspection
- **kraken** agent: TDD implementation of fix
### Commands
- `/fix` - Full workflow (investigate → diagnose → implement → test)
- `/debug` - Investigation only
### Tips
- Provide error messages, logs, reproduction steps
- The premortem hook will suggest risk analysis before implementation
Weekly Installs
200
Repository
parcadei/contin…laude-v3
GitHub Stars
3.6K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
opencode194
codex193
gemini-cli190
cursor190
github-copilot187
amp184
