[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74GD5GHTXA2D5PJN07M1FV0":3,"skill-same:01M74GD5GHTXA2D5PJN07M1FV0":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M74GD5GHTXA2D5PJN07M1FV0","feynman-technique",null,"Verify your understanding of a concept by attempting an undergrad-level explanation; surface exactly where the explanation cracks and study those.","MohammadBafkar\u002Fpolymath","MohammadBafkar","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34940462?v=4","01M74G540TQFZWK6KVAPKFVGNR","Mohammad Bafkar","01M74G541HG19QP9V5DQCJVKYE",0,"MIT","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-learning\u002Fskills\u002Ffeynman-technique\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: feynman-technique\ndescription: Verify your understanding of a concept by attempting an undergrad-level explanation; surface exactly where the explanation cracks and study those.\n---\n\n# feynman-technique\n\n> Richard Feynman: if you can't explain it simply, you don't understand it. The point isn't the explanation — it's the cracks that surface during the attempt.\n\n**Mode:** analytical — judgment inside a fixed frame. Keep the output shape; every verdict cites its evidence; unknowns are marked `[TBD]` or `[VERIFY]`, never filled in.\n\n## When to use\n\n- You think you understand a concept and want to verify.\n- A team member is about to teach something and wants to pressure-test their grasp.\n- Onboarding: you've read the docs, now try to teach without them.\n\n## Inputs\n\n- The concept (required).\n- Your current understanding, in your own words (required — don't fetch a definition; produce one).\n\n## Procedure\n\n**Who writes what.** When coaching a person, *they* write Attempt 1 and Attempt 2 — you mark the cracks and point at sources. Writing their attempt for them defeats the technique. Write the attempts yourself only when the user asks you to pressure-test *your* understanding.\n\n1. **Step 1 — Attempt the explanation.** Write the concept in your own words, aimed at a curious undergrad who has not heard the term. Limit: ~250 words. Don't open the source material.\n2. **Step 2 — Identify the cracks.** Walk through the explanation and mark:\n   - **Vague**: \"somehow\", \"it just works\", \"magically\".\n   - **Jargon-leak**: a term you used without grounding it.\n   - **Hand-waved**: a step you can't actually defend.\n   Be honest. Cracks are the point; pretending they're not there defeats the technique.\n3. **Step 3 — Hit the source for exactly the cracks.** Don't re-read the whole thing. Find the answer to each crack specifically.\n4. **Step 4 — Re-attempt the explanation.** Same constraints. Now the cracks should be gone or honestly noted (\"we don't fully know — the literature says X\").\n5. **Step 5 — Test on a real person.** Whatever you couldn't explain to them is the next round.\n\n## Output\n\n```text\nfeynman: \u003Cconcept>\n\nAttempt 1:\n  \u003Cyour ~250-word explanation>\n\nCracks identified:\n  - VAGUE: \"somehow caches the result\" — by what mechanism? when invalidated?\n  - JARGON-LEAK: used \"memoization\" without grounding.\n  - HAND-WAVED: claimed it's O(1); is it amortized?\n\nSources consulted (only for the cracks above):\n  - \u003Cref> — explained the invalidation mechanism.\n  - \u003Cref> — confirmed amortized O(1).\n\nAttempt 2:\n  \u003Crevised ~250-word explanation; cracks closed or explicitly admitted>\n\nHonest residuals:\n  - \"Why this specific replacement policy?\" — couldn't find a clean answer.\n    Note this for follow-up.\n```\n\n## Quality bar\n\n- Attempt 1 is yours, not a paste of the docs.\n- Cracks are specific (line\u002Fword level), not \"I'm fuzzy on this\".\n- Source consultation is targeted to the cracks.\n- Attempt 2 is materially better than Attempt 1; if it's not, the cracks weren't real.\n- Honest residuals are listed. Pretending mastery defeats the technique.\n\n## Anti-patterns to avoid\n\n- \"Attempt 1\" copied from the source — that's reading, not testing.\n- Vague crack list (\"I think I'm missing something\"). Be specific.\n- Skipping Step 5. Real audiences expose the cracks self-review can't.\n","# feynman-technique\n\n> Richard Feynman: if you can't explain it simply, you don't understand it. The point isn't the explanation — it's the cracks that surface during the attempt.\n\n**Mode:** analytical — judgment inside a fixed frame. Keep the output shape; every verdict cites its evidence; unknowns are marked `[TBD]` or `[VERIFY]`, never filled in.\n\n## When to use\n\n- You think you understand a concept and want to verify.\n- A team member is about to teach something and wants to pressure-test their grasp.\n- Onboarding: you've read the docs, now try to teach without them.\n\n## Inputs\n\n- The concept (required).\n- Your current understanding, in your own words (required — don't fetch a definition; produce one).\n\n## Procedure\n\n**Who writes what.** When coaching a person, *they* write Attempt 1 and Attempt 2 — you mark the cracks and point at sources. Writing their attempt for them defeats the technique. Write the attempts yourself only when the user asks you to pressure-test *your* understanding.\n\n1. **Step 1 — Attempt the explanation.** Write the concept in your own words, aimed at a curious undergrad who has not heard the term. Limit: ~250 words. Don't open the source material.\n2. **Step 2 — Identify the cracks.** Walk through the explanation and mark:\n   - **Vague**: \"somehow\", \"it just works\", \"magically\".\n   - **Jargon-leak**: a term you used without grounding it.\n   - **Hand-waved**: a step you can't actually defend.\n   Be honest. Cracks are the point; pretending they're not there defeats the technique.\n3. **Step 3 — Hit the source for exactly the cracks.** Don't re-read the whole thing. Find the answer to each crack specifically.\n4. **Step 4 — Re-attempt the explanation.** Same constraints. Now the cracks should be gone or honestly noted (\"we don't fully know — the literature says X\").\n5. **Step 5 — Test on a real person.** Whatever you couldn't explain to them is the next round.\n\n## Output\n\n```text\nfeynman: \u003Cconcept>\n\nAttempt 1:\n  \u003Cyour ~250-word explanation>\n\nCracks identified:\n  - VAGUE: \"somehow caches the result\" — by what mechanism? when invalidated?\n  - JARGON-LEAK: used \"memoization\" without grounding.\n  - HAND-WAVED: claimed it's O(1); is it amortized?\n\nSources consulted (only for the cracks above):\n  - \u003Cref> — explained the invalidation mechanism.\n  - \u003Cref> — confirmed amortized O(1).\n\nAttempt 2:\n  \u003Crevised ~250-word explanation; cracks closed or explicitly admitted>\n\nHonest residuals:\n  - \"Why this specific replacement policy?\" — couldn't find a clean answer.\n    Note this for follow-up.\n```\n\n## Quality bar\n\n- Attempt 1 is yours, not a paste of the docs.\n- Cracks are specific (line\u002Fword level), not \"I'm fuzzy on this\".\n- Source consultation is targeted to the cracks.\n- Attempt 2 is materially better than Attempt 1; if it's not, the cracks weren't real.\n- Honest residuals are listed. Pretending mastery defeats the technique.\n\n## Anti-patterns to avoid\n\n- \"Attempt 1\" copied from the source — that's reading, not testing.\n- Vague crack list (\"I think I'm missing something\"). Be specific.\n- Skipping Step 5. Real audiences expose the cracks self-review can't.\n",{"name":5,"description":7},"main","23f6e21841a39580c9da2b5ec941f39dda17cd86","plugins\u002Fpolymath-learning\u002Fskills\u002Ffeynman-technique","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath","https:\u002F\u002Fgithub.com\u002FMohammadBafkar","2026-10-29 18:34:59",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add MohammadBafkar\u002Fpolymath --skill feynman-technique",{"tool":36,"command":37},"bunx","bunx skills add MohammadBafkar\u002Fpolymath --skill feynman-technique",{"tool":39,"command":40},"pnpm","pnpm dlx skills add MohammadBafkar\u002Fpolymath --skill feynman-technique","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-learning\u002Fskills\u002Ffeynman-technique\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M74GN87EBRHM9N87M7AP1HDD","runbook","Write or refresh an operational runbook for an alert\u002Fsymptom; structured as TL;DR + Pre-checks + Steps + Verification + Rollback + Escalation.","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Frunbook\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M74GN5GPKEC1JEKP2DFQNEQJ","rfc","Draft a lightweight design RFC to docs\u002Frfcs\u002F\u003Cslug>.md; Summary, Motivation, Detailed design, Drawbacks, Alternatives, Unresolved questions. A proposal to debate, not a recorded decision (adr).","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Frfc\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M74GN2F4CWPMV4X09TG4E304","editorial-pass","Review and tighten prose in a Markdown artifact for a target tone (terse, formal, friendly) without dropping information; preserve quotations and load-bearing constraints.","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Feditorial-pass\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M74GMZWGYMZ37C4DYGT6P23G","architecture-review-facilitation","Run an architecture review as a process — entry criteria, reviewer checklist, decision log, and follow-up actions — pairing the design artifact with a red-team pass.","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Farchitecture-review-facilitation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M74GMXVX0YX3ETDXS527XDGM","architecture-doc","Write a C4-style architecture document; System Context + Containers (+ Components when interesting) with mermaid diagrams. Describes structure, not a decision (adr) or proposal (rfc).","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Farchitecture-doc\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M74GMVG1WSMCK066S3KE6V5K","adr","Write an Architecture Decision Record (Michael Nygard format) to docs\u002Fadrs\u002FNNNN-\u003Cslug>.md; frontmatter validated by the ADR artifact schema. Records a made decision, not a proposal to debate (rfc).","https:\u002F\u002Fgithub.com\u002FMohammadBafkar\u002Fpolymath\u002Fblob\u002Fmain\u002Fplugins\u002Fpolymath-writing\u002Fskills\u002Fadr\u002FSKILL.md",[],[]]