[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E5WVPFQSM171C156NNR4JC":3,"skill-same:01M7E5WVPFQSM171C156NNR4JC":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":43},"01M7E5WVPFQSM171C156NNR4JC","figure-it-out",null,"Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for \u002Ffigure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.","hasegama\u002Fpstack-agents","hasegama","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F40445443?v=4","01M7E58WENS57JDNDXCV1QVSP9","01M7E5PAP7RAMC9DC2PCR1CHJF",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Ffigure-it-out\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: figure-it-out\ndescription: \"Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for \u002Ffigure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.\"\ndisable-model-invocation: true\n---\n\n# Figure it out\n\nWhen the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away. Bias toward more rigor. The cost of building the wrong thing dwarfs the cost of being careful.\n\nDon't reinvent a playbook you already have. A focused single-unit task that matches Bug fix, Perf, Feature, Visual parity, Eval, or Multi-phase plan routes there. But a large or cross-cutting version of one (a migration across many call sites, an ambitious multi-part change), or work the user reviews after stepping away, belongs here even though a single-unit version would be a Feature. The rigor and the audit trail are the point.\n\n## Start\n\nOpen a todolist whose first item is to read the Principles section of the **poteto-mode** skill. Then add the phases below as todos.\n\n## Phase A: Frame\n\nGround first, then commit. Don't start the run until you can state:\n\n- The definition of done as a falsifiable predicate (the **prove-it-works** principle skill). \"Done well\" has to be checkable.\n- Scope, quantified: rough units and effort, plus the blockers grounding surfaced. Raise them before spending hours, not after fifty doomed commits.\n- The rigor level, biased high. One-way doors and high blast radius get more; reversible low-stakes steps get less. Rigor is gates and artifacts, not \"try harder\".\n\nPresent the framing and tradeoffs before committing to a long run. Reversible work proceeds (the **never-block-on-the-human** principle skill), but a multi-hour run earns one checkpoint.\n\n## Phase B: Design the workflow\n\nDecompose into atomic, independently-landable units. Sequence riskiest-unknown-first so option value stays high. Scaffold and verification come before features (the **foundational-thinking** principle skill).\n\n- Build the verification harness before the work, with the baseline captured from the pre-change state, so the check reads as \"old value vs new value\".\n- For one-way-door design decisions, run the **architect** skill (it runs **arena**) with diverse, isolated, opinionated candidates and a read-only judge on a different model family. Skip it for mechanical work whose shape is already concrete. A second arena over a settled design is over-engineering (the **laziness-protocol** principle skill).\n- Decide what fans out. Parallelize only across genuine seams, and give each worker its own worktree or branch (the **separate-before-serializing-shared-state** principle skill). Don't over-fan.\n- Write the designed phase list down. That list is what the human reviews.\n\nThen put the design into motion. Add its steps to the todolist as concrete items, after the Phase C entry and before Phase D. Run each under the Phase C loop discipline, and weave the Phase D log through them, a row as each step lands, rather than saving the whole trail for the end.\n\n## Phase C: Run the loop\n\nEach unit is an experiment: state the hypothesis, make the smallest change, measure against the predicate on the real artifact, keep it if it advanced, revert it if it didn't.\nApply the **sequence-verifiable-units** principle skill, verifying each unit before starting the next instead of batching checks at the end.\n\n- Verify by inspecting the artifact, never a self-report. When something passes too easily, suspect the observation method before the system. A blank screenshot passes a lazy gate.\n- Pair delegated work with a judge and audit the delegates' artifacts yourself before trusting them. If a worker games the gate, reset and harden the contract. If the gate itself is wrong, fix the gate in its own change rather than routing around it.\n- A verdict is VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Inconclusive is not a pass. Don't hide a negative.\n\n## Phase D: Keep the audit trail\n\nLog the run via the **show-me-your-work** skill, one canonical TSV with a row per decision and per unit, evidence as links. figure-it-out's work is usually ambitious enough to commit the trail so the reviewer can read it in the PR; commit it when confidence has to be shown. Prefer evidence produced by committed scripts so a reviewer can re-run it. The trail plus the diff is what lets the human come back and trust the work.\n\n## Phase E: Verify and hand back\n\nCheck the whole against the Phase A predicate on the real product, not just the harness. Encode any recurring correction as a gate, a lint rule, a check, or a script, so the win can't silently regress (the **encode-lessons-in-structure** principle skill).\n\n**Reply:** the playbook you designed, the rigor level and why, the decision-trail path, what's verified against the predicate, and what's still open.\n","# Figure it out\n\nWhen the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away. Bias toward more rigor. The cost of building the wrong thing dwarfs the cost of being careful.\n\nDon't reinvent a playbook you already have. A focused single-unit task that matches Bug fix, Perf, Feature, Visual parity, Eval, or Multi-phase plan routes there. But a large or cross-cutting version of one (a migration across many call sites, an ambitious multi-part change), or work the user reviews after stepping away, belongs here even though a single-unit version would be a Feature. The rigor and the audit trail are the point.\n\n## Start\n\nOpen a todolist whose first item is to read the Principles section of the **poteto-mode** skill. Then add the phases below as todos.\n\n## Phase A: Frame\n\nGround first, then commit. Don't start the run until you can state:\n\n- The definition of done as a falsifiable predicate (the **prove-it-works** principle skill). \"Done well\" has to be checkable.\n- Scope, quantified: rough units and effort, plus the blockers grounding surfaced. Raise them before spending hours, not after fifty doomed commits.\n- The rigor level, biased high. One-way doors and high blast radius get more; reversible low-stakes steps get less. Rigor is gates and artifacts, not \"try harder\".\n\nPresent the framing and tradeoffs before committing to a long run. Reversible work proceeds (the **never-block-on-the-human** principle skill), but a multi-hour run earns one checkpoint.\n\n## Phase B: Design the workflow\n\nDecompose into atomic, independently-landable units. Sequence riskiest-unknown-first so option value stays high. Scaffold and verification come before features (the **foundational-thinking** principle skill).\n\n- Build the verification harness before the work, with the baseline captured from the pre-change state, so the check reads as \"old value vs new value\".\n- For one-way-door design decisions, run the **architect** skill (it runs **arena**) with diverse, isolated, opinionated candidates and a read-only judge on a different model family. Skip it for mechanical work whose shape is already concrete. A second arena over a settled design is over-engineering (the **laziness-protocol** principle skill).\n- Decide what fans out. Parallelize only across genuine seams, and give each worker its own worktree or branch (the **separate-before-serializing-shared-state** principle skill). Don't over-fan.\n- Write the designed phase list down. That list is what the human reviews.\n\nThen put the design into motion. Add its steps to the todolist as concrete items, after the Phase C entry and before Phase D. Run each under the Phase C loop discipline, and weave the Phase D log through them, a row as each step lands, rather than saving the whole trail for the end.\n\n## Phase C: Run the loop\n\nEach unit is an experiment: state the hypothesis, make the smallest change, measure against the predicate on the real artifact, keep it if it advanced, revert it if it didn't.\nApply the **sequence-verifiable-units** principle skill, verifying each unit before starting the next instead of batching checks at the end.\n\n- Verify by inspecting the artifact, never a self-report. When something passes too easily, suspect the observation method before the system. A blank screenshot passes a lazy gate.\n- Pair delegated work with a judge and audit the delegates' artifacts yourself before trusting them. If a worker games the gate, reset and harden the contract. If the gate itself is wrong, fix the gate in its own change rather than routing around it.\n- A verdict is VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Inconclusive is not a pass. Don't hide a negative.\n\n## Phase D: Keep the audit trail\n\nLog the run via the **show-me-your-work** skill, one canonical TSV with a row per decision and per unit, evidence as links. figure-it-out's work is usually ambitious enough to commit the trail so the reviewer can read it in the PR; commit it when confidence has to be shown. Prefer evidence produced by committed scripts so a reviewer can re-run it. The trail plus the diff is what lets the human come back and trust the work.\n\n## Phase E: Verify and hand back\n\nCheck the whole against the Phase A predicate on the real product, not just the harness. Encode any recurring correction as a gate, a lint rule, a check, or a script, so the win can't silently regress (the **encode-lessons-in-structure** principle skill).\n\n**Reply:** the playbook you designed, the rigor level and why, the decision-trail path, what's verified against the predicate, and what's still open.\n",{"name":5,"description":7,"disable-model-invocation":23},true,"codex\u002Fpstack-agents","4d7f92a090c259bfccccd49f64a0e7da8312c026","upstream\u002Fpstack\u002Fskills\u002Ffigure-it-out","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents","https:\u002F\u002Fgithub.com\u002Fhasegama","Computer Vision","2026-10-05 10:35:18",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":23},[33,36,39],{"tool":34,"command":35},"npx","npx skills add hasegama\u002Fpstack-agents --skill figure-it-out",{"tool":37,"command":38},"bunx","bunx skills add hasegama\u002Fpstack-agents --skill figure-it-out",{"tool":40,"command":41},"pnpm","pnpm dlx skills add hasegama\u002Fpstack-agents --skill figure-it-out","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Ffigure-it-out\u002FSKILL.md",[],[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":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M7E60GNZT6DN9CK11Z0J1FVK","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M7E60F55XM7PYQZ7ZNBRBEDM","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M7E60C5KYHYTK1ET4KTFJ8QD","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M7E6088TYJKEPB62Q99KKPMV","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M7E603VCQKQRA4V6J791EYPN","teach","Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Fteach\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M7E600P53BE5X3XCEC03G8ZK","tdd","Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.","https:\u002F\u002Fgithub.com\u002Fhasegama\u002Fpstack-agents\u002Fblob\u002Fcodex\u002Fpstack-agents\u002Fupstream\u002Fpstack\u002Fskills\u002Ftdd\u002FSKILL.md",[],[]]