naval-thinking
Use Naval Ravikant's ideas to pressure-test career and business choices, ownership and scalable work, long-term partnerships, and ambition versus personal freedom. Apply when the user asks for a Naval or Almanack lens or explicitly wants reasoning about these tradeoffs.
- License 许可
- Apache-2.0
- 所属仓库
- getedgehq/skills
- 最近更新
- 2026-11-12
- Stars
- ★ 5
- Forks
- 0
01 前言 Front Matter
- name
- naval-thinking
- description
- Use Naval Ravikant's ideas to pressure-test career and business choices, ownership and scalable work, long-term partnerships, and ambition versus personal freedom. Apply when the user asks for a Naval or Almanack lens or explicitly wants reasoning about these tradeoffs.
02 资源文件 11
- 参考文档agents/openai.yaml209 B
- 参考文档DERIVATION.json3.0 KB
- 许可证LICENSE10.5 KB
- 参考文档references/decision-methods.md8.0 KB
- 参考文档references/freedom.md4.0 KB
- 参考文档references/judgment.md4.2 KB
- 参考文档references/lenses.md951 B
- 参考文档references/principle-interactions.md5.6 KB
- 参考文档references/sources-and-reuse.md3.2 KB
- 参考文档references/values-and-growth.md5.4 KB
- 参考文档references/wealth.md5.1 KB
03 SKILL.md 正文
Naval Thinking
Help the user make a concrete decision using ideas associated with Naval Ravikant and Eric Jorgenson's The Almanack of Naval Ravikant. This is an independent framework, not an authorized adaptation or a simulation of Naval. It is not affiliated with or endorsed by Naval Ravikant or Eric Jorgenson.
Method
Start with the actual choice, available options, desired outcome, and constraints. Use the user's evidence; label missing facts and assumptions. Ask only for information that could change the recommendation. If asked for general reflection, identify the underlying tension without inventing a decision.
Choose a reference by the actual decision; load only what is useful:
- Career, business model, equity, scalable work, focus, or partners: references/wealth.md.
- Conflicting evidence, identity, incentives, difficult choices, or learning: references/judgment.md.
- Ambition, comparison, dissatisfaction, acceptance, or freedom: references/freedom.md.
- Meaning, values, authenticity, personal growth, or philosophy: references/values-and-growth.md.
For a consequential decision, also read the relevant method in references/decision-methods.md. When two attractive principles imply different choices, consult the matching tension in references/principle-interactions.md. These are original operational syntheses, not a procedure dictated by the book.
Select the few mechanisms that distinguish the options. For each, connect user fact → mechanism → implication → what would change the conclusion. Naming an aphorism is not analysis. Do not run every lens mechanically or assume the entrepreneurial option wins.
Depth means explaining the causal bottleneck and decision sensitivity, not adding more maxims. Identify what must be true for each serious option to succeed, which condition is currently weakest, and how an intervention changes it. Distinguish evidence about willingness to pay, delivery ability, retention, and access to buyers; one does not prove the others.
Compare with the strongest alternative, including staying on the present course when relevant. Separate immediate feasibility from long-term attractiveness. Financial runway, obligations, contracts, health, and actual demand can outweigh philosophical preference. Avoid numerical scores that imply unsupported precision.
Stress-test your favored option: what assumption makes it work, what evidence contradicts it, and what downside could prevent another attempt? Treat these ideas as hypotheses, not laws. Identify when the Naval lens is unhelpful or incomplete.
Give a direct recommendation, the decisive reasons, the main uncertainty, and the smallest useful next action. For uncertain decisions, propose a bounded experiment with an observable result and a review point. The experiment design and recommendation are your synthesis, not advice attributed to Naval.
An experiment must answer the uncertainty that controls the choice. Name what will be tested, affordable cost and duration, observable result, and how the result changes the action. Use thresholds supplied by the user or justified by their constraints; label proposed thresholds as provisional. A pilot is not useful merely because it is small. Recommend committing when evidence is sufficient rather than prescribing another experiment indefinitely.
Match depth to the request. Brief questions still get brief answers. For a requested deep analysis, expose the important assumptions, economics, competing principles, adverse scenario, and reversal condition. If no decision is possible with the available facts, give a conditional recommendation and ask for the one missing fact that most changes it.
Use a simple calculation when the facts support one: runway, effective compensation, recurring delivery hours, or actual opportunity cost. State assumptions and units. Do not replace analysis with a weighted score or assign a dollar value to every personal activity.
Preserve the status of each fact: an offer is not a signed commitment, an agreement is not guaranteed collection, and revenue is not spendable income. Carry conditional terms through every calculation instead of checking them once and then treating them as established.
Response discipline
- Apply ideas to the user's facts; avoid a motivational essay or a collection of aphorisms.
- Distinguish a source idea, your interpretation, and the proposed action when attribution matters.
- Do not speak as Naval, invent quotations, or imply endorsement.
- Cite a relevant book section or primary source when explaining a source idea. Use printed book pages, not PDF viewer page numbers. Do not overload a short decision answer with citations.
- Use only relevant context. This skill does not authorize external actions or personal-context storage.
- Personal philosophy does not establish medical facts or investment suitability; verify factual claims when the decision depends on them.
For exact quotations, book-specific claims, or redistribution questions, read references/sources-and-reuse.md. Normal application works from the local lenses without downloading the PDF.
04 同仓库更多 Skills
zero-downtime-cloud-move
Runbook for moving a live app from one cloud to another (Google Cloud to AWS, AWS to Google Cloud, a PaaS to your own account, or one storage provider to another) without downtime. The agent inventories what is really running, builds the new stack next to the old one, keeps a one-line rollback for every phase, proves the new stack with real workloads before any traffic moves, cuts over with a checklist, watches a fixed window after the switch, copies data with an idempotent job whose second pass must report 0 left, and deletes the old cloud last. Use when someone asks to migrate, move or replatform a production app, switch cloud providers, move a backend, database files or object storage, plan a DNS cutover, or decommission an old cloud account.
zayats-ceo-branding
Build an evidence-based CEO positioning paper, Personal Branding Roadmap, and editorial workflow using Marina Zayats's public method. Use for executive branding, LinkedIn ghostwriting briefs, profile strategy, and recurring CEO-approved content planning.
yc-app-roast
YC App Roast: roast a YC or a16z Speedrun application. Use when a founder wants their YC or Speedrun answers scored, asks "what would a YC partner think", wants the weak answers found or rewritten, or wants their draft checked before they submit. Scores every answer 0-10 against public advice from YC and Speedrun partners, names the top issue with the exact words that cost points, and writes a rewrite from the founder's own facts. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.
yc-app-review
YC App Review: get a YC or a16z Speedrun application reviewed by people you trust. Use when a founder wants friends, mentors or alumni to review their YC or Speedrun application, or asks to share their draft for feedback. Builds a shareable review page (one HTML file, application-portal look) where reviewers leave notes per question and press "Send my notes" to send them back as text, then parses the notes into proposed rewrites. Optional tracked private links per reviewer. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.
x-growth-playbook
X Growth Playbook. Analyse a person's own X (Twitter) posts and tell them what to post next, with the numbers behind every claim. Compares quote posts vs originals, links vs no links, short vs long, time of day in their timezone, media vs text and the topics they name, reports medians with n, then writes a 10-step plan and the next 7 posts in their voice. Use when the user says "analyse my X posts", "what works on my Twitter", "how do I grow on X", "what should I post next on X", "audit my X account", or shares an X data archive, X API export or a list of their posts. Runs on the user's computer.
workplan
Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: "workplan", "work plan", "create a plan", "what's the plan", "where was I", or when Claude detects a multi-step task that needs tracking.