New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

OODA Loop Analysis

by neurofoo in neurofoo/agent-skills

Walks a problem or decision through the OODA loop: observe the facts, orient on causes and assumptions, decide among at least three options, and plan the execution.

MITAuto-check passedAgent Workflows

Install OODA Loop Analysis

skills CLI
$ npx skills add neurofoo/agent-skills --skill ooda -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install neurofoo/agent-skills ooda --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/neurofoo/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ooda .claude/skills/ooda && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ooda
GitHub stars
119
Used in
1 other repo
Token cost
~904 tokens
SKILL.md length
440 words
Files
1
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Walks a problem or decision through the OODA loop: observe the facts, orient on causes and assumptions, decide among at least three options, and plan the execution.

  • Works in 4 steps: OBSERVE → ORIENT → DECIDE → …
  • Facing a complex decision with trade-offs
  • SKILL.md covers Instructions, Format and Examples
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill runs four phases in order, each with fixed outputs. Observe collects facts only: the current state, the signals that prompted the inquiry, scope, constraints and unknowns. Orient asks why, covering root causes, mental models such as first principles and inversion, patterns from similar situations, stakeholder views, assumptions and biases.

Decide lays out at least three options with pros, cons and risk level, then a recommendation, success criteria and a contingency. Execute gives ordered action steps, verification points, a timeline and the first action, and the analysis closes with key risks and a trigger for reviewing the decision. Output uses a header per phase and stays direct, and the skill includes a worked business example about product launch timing.

When your agent uses it

  • Facing a complex decision with trade-offs
  • Someone is jumping to solutions without analysis
  • An unclear situation needs facts separated from interpretation

Example prompts

  • “Run an OODA analysis on whether we should delay the launch to fix edge cases.”
  • “We keep missing deadlines and nobody agrees why. Work it through the OODA loop.”
  • “Use OODA to decide between rewriting the importer and patching it.”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. OBSERVE
  2. ORIENT
  3. DECIDE
  4. EXECUTE

What it can do on your machine

Read from SKILL.md and the folder at commit 0e7ac2a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OODA Loop Analysis loads about 904 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 440 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~904

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from neurofoo/agent-skills at commit 0e7ac2a, republished under its MIT licence (© neurofoo). 440 words, ~904 tokens.

Download SKILL.mdSave it as .claude/skills/ooda/SKILL.md (or your agent's skills folder).
name
ooda
description
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.
user-invocable
true

OODA Loop Analysis

Run a complete OODA loop (Observe, Orient, Decide, Execute) on the problem or decision provided.

Instructions

Work through each phase sequentially. Be thorough but concise.

Phase 1: OBSERVE

Gather facts before analyzing. Ask: "What is actually happening?"

Output:

  • Current State: Facts only, no interpretation
  • Signals: What prompted this inquiry
  • Scope: Boundaries of the situation
  • Constraints: Resources, time, rules, dependencies
  • Unknowns: Information gaps to acknowledge
Phase 2: ORIENT

Analyze and build understanding. Ask: "Why is this happening?"

Output:

  • Root Cause Analysis: Underlying drivers, not just symptoms
  • Mental Models: Frameworks that apply (first principles, inversion, second-order effects, etc.)
  • Patterns: Similar situations and their outcomes
  • Stakeholder Views: How different parties see this
  • Assumptions: What we're taking for granted
  • Biases: Cognitive traps to watch for
Phase 3: DECIDE

Choose from viable options. Ask: "What's the best approach?"

Output:

  • Options (minimum 3):
    • Option A — Pros / Cons / Risk level
    • Option B — Pros / Cons / Risk level
    • Option C — Pros / Cons / Risk level
  • Recommendation: Selected approach with rationale
  • Success Criteria: How we'll know it worked
  • Contingency: Fallback if primary approach fails
Phase 4: EXECUTE

Plan implementation with verification. Ask: "How do we act and confirm?"

Output:

  • Action Steps: Ordered, concrete steps
  • Verification Points: How to check progress at each stage
  • Timeline: Realistic schedule
  • First Action: The immediate next step
Feedback Loop

End with:

  • Key Risks: What could derail this
  • Review Trigger: When to reassess (time or event based)

Format

Use clear headers for each phase. Be direct and actionable. Avoid fluff.

Examples

Show full SKILL.md (193 more words)Show less
Business: Product Launch Timing

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.

Personal: Job Offer Decision

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

© neurofoo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ooda of neurofoo/agent-skills.

Open the folder on GitHubat commit 0e7ac2a

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in neurofoo/agent-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

OODA Loop Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

OODA Loop Analysis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OODA Loop Analysis this skillneurofoo/agent-skills1191 repos~904Automated safety check: PassMIT
Paseo Committeegetpaseo/paseo20k1 repos~496Automated safety check: PassCustom licence
Deep Reasoning ModemakoMakoGo/fish-claude171—~1.1kAutomated safety check: PassMIT
PRP Implementation PlannerWirasm/prp2.3k—~4.1kAutomated safety check: PassMIT
PRP PlanWirasm/prp2.3k—~4kAutomated safety check: PassMIT
Dev ReportFHIR/fhir-codegen154—~4.1kAutomated safety check: PassMIT

Similar skills

  • Paseo Committee

    getpaseo/paseo

    Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.

    20k GitHub starsUsed in 1 repo~496 tokens
    Agent WorkflowsAuto-check passed

  • Deep Reasoning Mode

    makoMakoGo/fish-claude

    Sets a structured planning routine before every action: weigh dependencies and constraints, assess risk, test hypotheses, re-evaluate after each result and gather all sources of information.

    171 GitHub stars~1.1k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • PRP Implementation Planner

    Wirasm/prp

    Turns a PRD, issue or description into an implementation-ready plan grounded in codebase evidence, adding root-cause analysis for bugs and publishing issue plans back to the issue.

    2.3k GitHub stars~4.1k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • PRP Plan

    Wirasm/prp

    Writes an implementation-ready plan for a feature, bug fix, refactor or chore from a PRD, issue or description, grounded in codebase evidence, and can post it back to the source issue.

    2.3k GitHub stars~4k tokensUpdated 5 days ago
    DevelopmentAuto-check passed

  • Dev Report

    FHIR/fhir-codegen

    Drafts and iterates on local-development bug reports in the role of a staff-level Tech Lead.

    154 GitHub stars~4.1k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Bug Remediation Architect

    GulajavaMinistudio/Mayukai-Theme

    Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.

    139 GitHub stars~1.4k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed

More from neurofoo/agent-skills

All 22 skills in this repo

  • Five Whys Analysis

    neurofoo/agent-skills

    Runs a Five Whys root cause analysis, asking why repeatedly from the stated problem until it reaches an actionable cause, then lists corrective actions and verification.

    119 GitHub starsUsed in 1 repo~875 tokens
    Auto-check passed

  • Eisenhower Matrix Prioritizer

    neurofoo/agent-skills

    Sorts a task list into the four Eisenhower quadrants (do, schedule, delegate, eliminate) with reasons, a time distribution check and first actions.

    119 GitHub stars~705 tokensUpdated 8 mo ago
    Auto-check passed

  • Cynefin Problem Classifier

    neurofoo/agent-skills

    Sorts a problem into the Cynefin domains of simple, complicated, complex, chaotic or confused, then recommends a way of working that fits that domain.

    119 GitHub starsUsed in 1 repo~696 tokens
    Auto-check passed

  • Wardley Map Analysis

    neurofoo/agent-skills

    Maps a user need's value chain against evolution stages to guide build-versus-buy decisions and show competitive dynamics.

    119 GitHub stars~776 tokensUpdated 8 mo ago
    Auto-check passed

  • Jtbd

    neurofoo/agent-skills

    Jobs to Be Done analysis to understand what customers really want.

    119 GitHub starsUsed in 1 repo~754 tokens
    Auto-check passed

  • Swot

    neurofoo/agent-skills

    SWOT strategic analysis examining Strengths, Weaknesses, Opportunities, and Threats.

    119 GitHub starsUsed in 1 repo~634 tokens
    Auto-check passed

Categories

Questions about OODA Loop Analysis

What does OODA Loop Analysis do?

Walks a problem or decision through the OODA loop: observe the facts, orient on causes and assumptions, decide among at least three options, and plan the execution. The skill runs four phases in order, each with fixed outputs. Observe collects facts only: the current state, the signals that prompted the inquiry, scope, constraints and unknowns.

When should I use OODA Loop Analysis?

OODA Loop Analysis fits situations like: facing a complex decision with trade-offs; someone is jumping to solutions without analysis; an unclear situation needs facts separated from interpretation.

How do I install OODA Loop Analysis in Claude Code?

Run `npx skills add neurofoo/agent-skills --skill ooda -a claude-code`. Or copy the skill folder (ooda in neurofoo/agent-skills) into .claude/skills/ooda in your project. Claude Code loads it when a task matches its description.

How do I install OODA Loop Analysis in Codex?

Run `npx skills add neurofoo/agent-skills --skill ooda -a codex`. Or copy the skill folder (ooda in neurofoo/agent-skills) into .agents/skills/ooda in your project. Codex loads it when a task matches its description.

Can I use OODA Loop Analysis in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add neurofoo/agent-skills --skill ooda -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ooda, .gemini/skills/ooda, .github/skills/ooda and .opencode/skills/ooda in your project.

What does OODA Loop Analysis need to run?

SKILL.md names no scripts, command-line tools or credentials: OODA Loop Analysis is instructions for the agent only.

Does OODA Loop Analysis access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is OODA Loop Analysis safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does OODA Loop Analysis use?

OODA Loop Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does OODA Loop Analysis use?

About 904 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to OODA Loop Analysis?

Skills that share tags, products or a category with OODA Loop Analysis: Paseo Committee (getpaseo/paseo, 20k stars), Deep Reasoning Mode (makoMakoGo/fish-claude, 171 stars), PRP Implementation Planner (Wirasm/prp, 2.3k stars) and PRP Plan (Wirasm/prp, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OODA Loop Analysis?

neurofoo (a GitHub user) maintains it in neurofoo/agent-skills, which has 119 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on January 19, 2026.

Source: neurofoo/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.