para-pkm
Manage PARA-based personal knowledge management (PKM) systems using Projects, Areas, Resources, and Archives organization method. Use when users need to (1) Create a new PARA knowledge base, (2) Organize or reorganize existing knowledge bases into PARA structure, (3) Decide where content belongs in PARA (Projects vs Areas vs Resources vs Archives), (4) Create AI-friendly navigation files for knowledge bases, (5) Archive completed projects, (6) Validate PARA structure, or (7) Learn PARA organizational patterns for specific use cases (developers, consultants, researchers, etc.)
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/killerapp/para-pkmPARA PKM
Organize by actionability, not topic. Projects/Areas/Resources/Archives for optimal AI navigation. Monthly review cadence.
Core Concepts
- Projects = Time-bound goals with deadlines (completes → Archives); includes
projects/stories/for job applications - Areas = Ongoing responsibilities (use
_overview.mdper area for context) - Resources = Reference material; when unsure, put here temporarily
- Archives = Inactive items from any category
Decision Tree
Has deadline/end state? → Projects
Ongoing responsibility? → Areas
Reference material? → Resources (default for uncertain items)
Completed/inactive? → Archives
Quick Start
python scripts/init_para_kb.py <name>- Creates PARA +projects/stories/+ navigation- Identify projects (deadlines) → areas (ongoing) → resources (reference)
python scripts/generate_nav.py- Generate AI navigation
Scripts
| Script | Purpose | Usage |
|---|---|---|
init_para_kb.py | Scaffold new KB | <name> [--path <dir>] |
validate_para.py | Check structure, detect anti-patterns | [path] |
archive_project.py | Archive with metadata (date, origin) | <project-file> [--kb-path] |
generate_nav.py | Create AI nav (<100 lines) | [--kb-path] [--output] |
Templates
| Template | Purpose |
|---|---|
assets/AGENTS.md.template | AI navigation index |
assets/project.md.template | Project file structure |
assets/area-overview.md.template | Area _overview.md format |
assets/README.md.template | Knowledge base README |
Patterns by Role
- Developers:
projects/active/features/bugs,areas/professional-development/,resources/coding-standards/ - Consultants:
projects/active/deliverables +projects/stories/,areas/consulting/clients/,resources/templates/ - Researchers:
projects/active/papers/grants,areas/research-program/,resources/literature-review/ - Product Builders:
projects/active/launches,areas/product-development/{active,research,graduated,legacy}/
Complex Scenarios
Client = project + relationship: projects/active/client-x.md (deliverables) + areas/consulting/clients/client-x.md (relationship, billing)
Research lifecycle: areas/product-development/{research → graduated → active → legacy} with cross-references
Anti-Patterns
- inbox/ folder (capture directly into PARA; use Resources when uncertain)
- Deep nesting (max 2-3 levels; flat > nested)
- Topic-based organization ("work/personal" → use actionability)
- Todo folders (tasks belong with their projects/areas)
- Perfectionism (move freely as understanding evolves; monthly review catches misplacements)
Content Lifecycle
Resources → Projects → Archives (research → active work → completed)
Areas → Archives (no longer responsible)
Projects ⟺ Areas (goal becomes ongoing or vice versa)
AI Navigation & Success Tips
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-killerapp-para-pkm": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
agentskills-io
Create, validate, and publish Agent Skills following the official open standard from agentskills.io. Use when (1) creating new skills for AI agents, (2) validating skill structure and metadata, (3) understanding the Agent Skills specification, (4) converting existing documentation into portable skills, or (5) ensuring cross-platform compatibility with Claude Code, Cursor, GitHub Copilot, and other tools.
aws-agentcore-langgraph
Deploy production LangGraph agents on AWS Bedrock AgentCore. Use for (1) multi-agent systems with orchestrator and specialist agent patterns, (2) building stateful agents with persistent cross-session memory, (3) connecting external tools via AgentCore Gateway (MCP, Lambda, APIs), (4) managing shared context across distributed agents, or (5) deploying complex agent ecosystems via CLI with production observability and scaling.
baml-codegen
Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations from natural language requirements. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), Python/TypeScript/Ruby/Go, 10+ frameworks, 50-70% token optimization, 95%+ compilation success.
adversarial-coach
Adversarial implementation review based on Block's g3 dialectical autocoding research. Use when validating implementation completeness against requirements with fresh objectivity.
chain-of-density
Iteratively densify text summaries using Chain-of-Density technique. Use when compressing verbose documentation, condensing requirements, or creating executive summaries while preserving information density.