decision-frameworks
kumaran-is/claude-code-onboarding/.claude/skills/decision-frameworks/SKILL.md
Use when working through a specific problem or decision using a single reasoning framework applied deeply and interactively. Covers First Principles (break assumptions, rebuild from truth), Inversion (guarantee failure, then flip), Regret Minimization (decide from age 80), and Opportunity Cost (make tradeoffs visible). Triggers: "first principles", "inversion", "regret minimization", "opportunity cost", "help me think through", "challenge my assumptions", "what am I giving up", "work backwards from failure", "what would I regret".
What's in it
- Iron Law
- Decision Frameworks
- When to Use This Skill
- The Four Modes
- Mode Selection
- Core Workflow
- Reference Guide
- Constraints
- MUST DO
- MUST NOT DO
- Complementary Framework Pairings
- Related
Tools it asks for
- Read
--- name: decision-frameworks description: Use when working through a specific problem or decision using a single reasoning framework applied deeply and interactively. Covers First Principles (break assumptions, rebuild from truth), Inversion (guarantee failure, then flip), Regret Minimization (decide from age 80), and Opportunity Cost (make tradeoffs visible). Triggers: "first principles", "inversion", "regret minimization", "opportunity cost", "help me think through", "challenge my assumptions", "what am I giving up", "work backwards from failure", "what would I regret". allowed-tools: Read metadata: triggers: first principles, inversion, regret minimization, opportunity cost, challenge my assumptions, think through this decision, work backwards, what am I giving up, what would I regret, break this down to fundamentals related-skills: the-fool, second-order-thinker, mental-model-applier domain: workflow role: expert scope: analysis output-format: report last-reviewed: "2026-05-26" --- ## Iron Law **NO GENERIC ADVICE — every framework must be applied to the specific situation the user describes; "consider your assumptions" is not an application; naming the actual assumptions is** # Decision Frameworks Four single-framework deep-dives for decisions, problems, and commitments. Each mode applies one reasoning framework interactively — asking follow-up questions, pushing for specificity, and refusing vague answers. Use this skill when you want to go deep on one framework. Use `mental-model-applier` when you want three frameworks applied in parallel for a broader perspective shift. ## When to Use This Skill - You are stuck on a specific problem and want to reason through it systematically - A decision keeps feeling hard despite having information — you need a different lens - You want to challenge your own assumptions before committing - You are about to make an irreversible choice and want to stress-test it - You need to make tradeoffs explicit rather than implicit ## The Four Modes | Mode | Framework | Best For | |------|-----------|----------| | **First Principles** | Break to fundamental truths, rebuild | Overcoming convention, designing from scratch, "why do we do it this way?" | | **Inversion** | Guarantee failure, then flip | Risk surfacing, strategy validation, pre-commitment checks | | **Regret Minimization** | Decide from age 80 | Long-horizon personal or career decisions, emotional clarity | | **Opportunity Cost** | Make tradeoffs visible | Commitments, resource allocation, "should I do this?" decisions | ## Mode Selection Ask the user which framework to apply if they have not specified one. Present the four options with a one-line description. Use `AskUserQuestion` when interactive mode permits. If the user's problem maps clearly to one mode, state which you are using and why before beginning. ## Core Workflow 1. **Read the problem** — Understand what is being decided or solved. If the description is vague, ask one clarifying question before proceeding. 2. **Select mode** — Match to the problem type using the table above, or ask. 3. **Load reference** — Read the corresponding reference file for the full method and output template. 4. **Apply interactively** — Do not produce a monologue. Ask follow-up questions. Push for specificity. Refuse vague answers. 5. **Produce structured output** — Use the output template from the reference file. 6. **Offer a second pass** — After completing one mode, offer to run a complementary framework. ## Reference Guide | Mode | Reference File | Load When | |------|---------------|-----------| | First Principles | `references/first-principles.md` | User wants to break assumptions and rebuild | | Inversion | `references/inversion.md` | User wants to work backwards from failure | | Regret Minimization | `references/regret-minimization.md` | User faces a long-horizon personal or career decision | | Opportunity Cost | `references/opportunity-cost.md` | User is evaluating a commitment or resource allocation | ## Constraints ### MUST DO - Apply the framework specifically to the user's situation — name their actual assumptions, their actual tradeoffs, their actual failure modes - Push back on vague answers: "poor execution" is not a failure mode; "the API migration slips 3 weeks because the external team has no SLA" is - Ask follow-up questions rather than filling gaps with invention - State which framework you are applying and why before starting - End with a concrete output the user can act on — not just analysis ### MUST NOT DO - Apply multiple frameworks simultaneously — this skill is for single-framework depth; use `mental-model-applier` for multi-model breadth - Produce generic advice that would apply to any situation - Accept "it depends" as a final answer — push for the specific version that applies here - Skip the interactive element and produce a monologue ## Complementary Framework Pairings After completing one mode, suggest a natural follow-on: | Completed Mode | Natural Follow-On | Why | |----------------|-------------------|-----| | First Principles | Inversion | First Principles finds the right foundation; Inversion stress-tests it | | Inversion | Second-Order Thinker | Inversion finds failure modes; Second-Order maps their downstream consequences | | Regret Minimization | Opportunity Cost | Emotional clarity on direction + explicit tradeoffs of the chosen path | | Opportunity Cost | First Principles | Tradeoffs made visible + assumptions challenged on why those options exist | ## Related > For adversarially stress-testing any decision or plan: use `the-fool` skill. > For applying three frameworks in parallel for perspective shift: use `mental-model-applier` skill. > For mapping downstream consequences of a decision: use `second-order-thinker` skill.
More agent context in kumaran-is/claude-code-onboarding
157 other files this repository gives its agents, the first 60 shown.
CLAUDE.md
Skill
- a2ui-angular.claude/skills/a2ui-angular/SKILL.md
- accessibility-audit.claude/skills/accessibility-audit/SKILL.md
- adk-deploy-guide.claude/skills/adk-deploy-guide/SKILL.md
- adk-dev-guide.claude/skills/adk-dev-guide/SKILL.md
- adk-eval-guide.claude/skills/adk-eval-guide/SKILL.md
- adk-observability-guide.claude/skills/adk-observability-guide/SKILL.md
- agentic-ai-coding-standard.claude/skills/agentic-ai-coding-standard/SKILL.md
- agentic-ai-dev.claude/skills/agentic-ai-dev/SKILL.md
- ai-audit.claude/skills/ai-audit/SKILL.md
- ai-chat.claude/skills/ai-chat/SKILL.md
- ai-decision-record.claude/skills/ai-decision-record/SKILL.md
- ai-incident-response.claude/skills/ai-incident-response/SKILL.md
- ai-launch-check.claude/skills/ai-launch-check/SKILL.md
- ai-playbook.claude/skills/ai-playbook/SKILL.md
- angular-best-practices.claude/skills/angular-best-practices/SKILL.md
- angular.claude/skills/angular/SKILL.md
- angular-spa.claude/skills/angular-spa/SKILL.md
- angular-ui-patterns.claude/skills/angular-ui-patterns/SKILL.md
- api-design-principles.claude/skills/api-design-principles/SKILL.md
- app-store-optimization.claude/skills/app-store-optimization/SKILL.md
- architect-review.claude/skills/architect-review/SKILL.md
- architecture-decision-records.claude/skills/architecture-decision-records/SKILL.md
- architecture-design.claude/skills/architecture-design/SKILL.md
- asc-cli-usage.claude/skills/asc-cli-usage/SKILL.md
- asc-crash-triage.claude/skills/asc-crash-triage/SKILL.md
- asc-id-resolver.claude/skills/asc-id-resolver/SKILL.md
- asc-release-flow.claude/skills/asc-release-flow/SKILL.md
- asc-signing-setup.claude/skills/asc-signing-setup/SKILL.md
- asc-submission-health.claude/skills/asc-submission-health/SKILL.md
- asc-testflight-orchestration.claude/skills/asc-testflight-orchestration/SKILL.md
- browser-testing.claude/skills/browser-testing/SKILL.md
- changelog-generator.claude/skills/changelog-generator/SKILL.md
- claude-actions-auditor.claude/skills/claude-actions-auditor/SKILL.md
- clean-code.claude/skills/clean-code/SKILL.md
- codebase-onboarding.claude/skills/codebase-onboarding/SKILL.md
- code-explainer.claude/skills/code-explainer/SKILL.md
- code-reviewer.claude/skills/code-reviewer/SKILL.md
- code-simplifier.claude/skills/code-simplifier/SKILL.md
- comment-analyzer.claude/skills/comment-analyzer/SKILL.md
- database-schema-designer.claude/skills/database-schema-designer/SKILL.md
- ddd-architect.claude/skills/ddd-architect/SKILL.md
- dedup-code-agent.claude/skills/dedup-code-agent/SKILL.md
- deployment-ci-cd.claude/skills/deployment-ci-cd/SKILL.md
- design-system.claude/skills/design-system/SKILL.md
- docker.claude/skills/docker/SKILL.md
- documentation-generation.claude/skills/documentation-generation/SKILL.md
- domain-finder.claude/skills/domain-finder/SKILL.md
- error-detective.claude/skills/error-detective/SKILL.md
- eval-guide.claude/skills/eval-guide/SKILL.md
- feature-forge.claude/skills/feature-forge/SKILL.md
- firebase-basics.claude/skills/firebase-basics/SKILL.md
- firebase-hosting-basics.claude/skills/firebase-hosting-basics/SKILL.md
- fixing-accessibility.claude/skills/fixing-accessibility/SKILL.md
- fixing-motion-performance.claude/skills/fixing-motion-performance/SKILL.md
- flutter-animations.claude/skills/flutter-animations/SKILL.md
- flutter-genui.claude/skills/flutter-genui/SKILL.md
- flutter-mobile.claude/skills/flutter-mobile/SKILL.md
- flutter-security-expert.claude/skills/flutter-security-expert/SKILL.md
- frontend-design.claude/skills/frontend-design/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

