organon
This skill should be used when the user faces an engineering decision, asks "should we...", "which approach...", "trade-off between...", "how to structure...", "evaluate this design", "review this code philosophically", "think through this", "analyze this approach", "what principles apply here", or invokes /organon, /organon:decide, /organon:review. Also auto-triggers on architectural decisions, debugging sessions, code reviews, design evaluations, and any situation where structured philosophical reasoning improves the outcome. This skill turns 62 philosophical principles from 20 philosophers into a live reasoning engine for engineering.
What this skill does
# Organon — Philosophical Reasoning Engine > Source: [Organon](https://gitlab.com/lightcyphers-open/organon) by Lightcyphers SRL, licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/). A decision engine and review framework that applies 62 principles from 20 philosophers to engineering problems. Not a reference — an engine. Detect the situation, select principles, run the protocol, produce structured output. ## Modes **Auto-detect** (default): Read context, determine if this is a decision or a review, select depth, execute. **Decision mode** (`/organon:decide`): Engineering decision analysis. Takes a situation, identifies applicable principles, runs protocol steps, produces recommendation with objections addressed. **Review mode** (`/organon:review`): Philosophical code/design review. Takes code or design, systematically evaluates against quality dimensions derived from the 62 principles. ## Depth Levels | Level | When | Context loaded | Output | |-------|------|---------------|--------| | **Quick** | Clear situation, single principle applies | This SKILL.md only | 3-5 lines: principle + action | | **Standard** | Non-trivial, multiple principles apply | + relevant philosopher references | Principles with rationale + protocol summary | | **Deep** | Architectural, irreversible, high-stakes | Full protocol via philosopher-council agent | 22-step walk + Summa objections + confidence | Auto-select depth by: Quick if one principle clearly maps. Standard if 2+ principles or ambiguity. Deep if irreversible decision, architectural choice, or conflicting principles. User can override with `/organon quick`, `/organon standard`, `/organon deep`. ## Execution Protocol ### Step 1: Detect Situation Read the current context — what is the user doing? Map to one of these categories: | Context signal | Mode | Typical depth | |---|---|---| | "should we", "which approach", "trade-off" | Decision | Standard | | "review this", "what's wrong with", code snippet | Review | Standard | | "debug", "why does this", "root cause" | Decision (abductive) | Standard | | "architecture", "design system", "how to structure" | Decision | Deep | | Routine question, clear answer exists | Decision | Quick | | Explicit `/organon:decide` or `/organon:review` | As specified | As specified or auto | ### Step 2: Route to Principles Use the compact routing table below. Match the situation to applicable principles, then load the relevant reference files for those principles. ### Step 3: Apply and Produce Output **Decision mode output format:** ``` ORGANON — Decision Analysis =========================== Situation: [detected/stated] Depth: Quick | Standard | Deep Applicable Principles: #XX Principle (Philosopher) -> Concrete action for this situation #XX Principle (Philosopher) -> Concrete action for this situation [Standard/Deep only:] Protocol Steps: 1. Four Causes -> Material: X | Formal: Y | Efficient: Z | Final: W 2. Effectual Truth -> Verified: [what was checked] ... [Deep only:] Summa Method — Objections: Videtur quod non 1: [objection] -> Ad 1: [resolution] Videtur quod non 2: [objection] -> Ad 2: [resolution] Decision: [recommendation] Confidence: [High|Medium|Low] — Cumulative case: [N signals listed] ``` **Review mode output format:** ``` ORGANON — Philosophical Review =============================== Target: [file/code/design] Quality Dimensions: Kalokagathia (beauty=good): [pass|warn|fail] [finding] Golden Mean (balance): [pass|warn|fail] [finding] Structural Stability: [pass|warn|fail] [finding] Falsifiability (tests): [pass|warn|fail] [finding] Proportionate Causality: [pass|warn|fail] [finding] Beetle in the Box (contracts): [pass|warn|fail] [finding] Information Theory (S/N ratio): [pass|warn|fail] [finding] Categorical Imperative: [pass|warn|fail] [finding] Simplicity Prior: [pass|warn|fail] [finding] Paradox of Tolerance (validation): [pass|warn|fail] [finding] Layer Separation (what vs how): [pass|warn|fail] [finding] Scope Discipline (bindings): [pass|warn|fail] [finding] Principle Violations: [list with specific references] Strengths: [what the code does well] Recommendation: [concrete next actions] ``` ## Compact Routing Table Map situations to principles. For full detail on any principle, load the relevant reference file. | Situation | Principle | Action | Detail | |---|---|---|---| | Don't understand requirement | Dialectic (8) | Ask 1-2 maximally clarifying questions | `references/principles-plato.md` | | Don't know where to start | Four Causes (I) | Decompose: Material, Formal, Efficient, Final | `references/principles-aristotle.md` | | Blocked by dependency/bug | Obstacle is the Way (4) | The blocker IS the task now | `references/principles-stoics.md` | | About to deploy/execute | Praemeditatio (5) | Risk checklist. Confirm if irreversible | `references/principles-stoics.md` | | Writing docs/PR/messages | Brevity (12) | Maximum density, zero filler | `references/principles-seneca.md` | | Aggressive code review | De Ira (18) | Respond on substance, ignore tone | `references/principles-seneca.md` | | "Trivial" task | Askesis (6) | Same quality standard as major tasks | `references/principles-stoics.md` | | Output OK but not excellent | Kalokagathia (10) | Is it clear, not just correct? | `references/principles-plato.md` | | Everything on fire | Tranquillitas (14) | Reduce scope, not quality | `references/principles-seneca.md` | | Applying a design pattern | Phronesis (3) | Relevant here? Benefit vs. cost? | `references/principles-aristotle.md` | | Docs don't match reality | Verita effettuale (19) | Trust code over documentation | `references/principles-machiavelli.md` | | All options are bad | Necessita (23) | Least harmful, document trade-off | `references/principles-machiavelli.md` | | Problem resists direct attack | Lion/Fox (21) | Try indirection: strangler fig, facade | `references/principles-machiavelli.md` | | Breaking change needed | Economy of Force (22) | One clean cut with full communication | `references/principles-machiavelli.md` | | Perfect blocking good | Virtu (20) | Ship, observe, iterate | `references/principles-machiavelli.md` | | Ambiguous naming/requirements | Characteristica (26) | Formalize first, then implement | `references/principles-engineers.md` | | Debate measurement can settle | Calculemus (27) | Calculate, don't argue | `references/principles-engineers.md` | | Complex system design | Alphabet of Thought (28) | Decompose into composable primitives | `references/principles-engineers.md` | | API design / validation | Syntax vs. Semantics (30) | Separate interface from implementation | `references/principles-engineers.md` | | Verification strategy | Incompleteness (32) | Defense in depth; no single method catches all | `references/principles-engineers.md` | | Two designs seem equal | Conventionalism (54) | It's a convention. Pick for simplicity. Document. | `references/principles-poincare.md` | | One spec change touches many files | Structural Stability (55) | Abstraction boundaries are wrong. Refactor. | `references/principles-poincare.md` | | Stuck on a design problem | Creative Recombination (56) | Decompose into known patterns, recombine | `references/principles-poincare.md` | | Making architectural recommendation | Copernican Turn (38) | State your bias: "I'm more familiar with X" | `references/principles-kant.md` | | Analyzing code not fully read | Noumena (42) | Say "in the files I've reviewed" | `references/principles-kant.md` | | Tempted to skip tests | Categorical Imperative (40) | If everyone skipped this, would the system survive? | `references/principles-kant.md` | | Writing tests | Falsifiability (45) | Try to destroy, not confirm | `references/principles-popper.md` | | Designing API input validation | Paradox of Tolerance (47) | Define what it will NO
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.