OODA loop decision framework (Observe, Orient, Decide, Act). Use for complex decisions, problem-solving, unclear situations, or when someone is jumping to solutions without analysis.
npx skills add https://github.com/neurofoo/agent-skills --skill ooda
Run a complete OODA loop (Observe, Orient, Decide, Execute) on the problem or decision provided.
Work through each phase sequentially. Be thorough but concise.
Gather facts before analyzing. Ask: "What is actually happening?"
Output:
Analyze and build understanding. Ask: "Why is this happening?"
Output:
Choose from viable options. Ask: "What's the best approach?"
Output:
Plan implementation with verification. Ask: "How do we act and confirm?"
Output:
End with:
Use clear headers for each phase. Be direct and actionable. Avoid fluff.
Context: Feature 85% complete, competitor launching similar feature next month.
OBSERVE: Core functionality works; edge cases unhandled. Competitor announced similar launch. 3 engineers available; Q4 revenue targets looming.
ORIENT: Root tension is first-mover advantage vs. quality reputation. Last rushed launch caused 3-month support burden. Sales wants it now; Support worried; Engineering wants 2 more weeks.
DECIDE: Options evaluated—Launch now (high risk), Delay 4 weeks (medium), Soft launch to 10 customers (low risk). Selected: Soft launch → gather feedback → full launch in 3 weeks.
EXECUTE: Identify 10 beta customers (2 days) → Deploy with feature flag (1 day) → Monitor 2 weeks → Full launch with case studies.
Context: 3 years at current company, plateaued. Offer is 30% raise, bigger scope, requires travel.
OBSERVE: Current role comfortable but stagnant. New role offers growth but spouse's job isn't portable; young child at home.
ORIENT: Root feeling is being undervalued + seeking growth. Models: Regret minimization; total compensation (salary + learning + relationships).
DECIDE: Selected transparent conversation with current manager + gather more info on new role before deciding.
EXECUTE: List non-negotiables → Career conversation with manager → Talk to future team → 48-hour reflection before final decision.
$ARGUMENTS
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take neurofoo/ooda from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.