[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F1SGNMCXQ2JARTT5Q1JB7J":3,"skill-same:01M7F1SGNMCXQ2JARTT5Q1JB7J":58},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7F1SGNMCXQ2JARTT5Q1JB7J","show-me-your-work",null,"Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for \u002Fshow-me-your-work or $show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.","willgosnold\u002Fpatchbook","willgosnold","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90176365?v=4","01M7F13J2VJ2R4DZHPQY7P92A0","Will Gosnold","01M7F1K8G0DXVG90J6F8WQR138",1,"MIT","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshow-me-your-work\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: show-me-your-work\ndescription: \"Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for \u002Fshow-me-your-work or $show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.\"\ndisable-model-invocation: true\n---\n\n# Show me your work\n\nKeep one canonical log.\n\n## The format\n\nA single TSV file, one row per decision. Cells stay single-line. Evidence is a pointer, not prose.\n\nCopy `references\u002Fdecision-log-template.tsv` (the header row) to start a clean log. Columns:\n\n- **ts.** ISO8601 timestamp.\n- **phase.** The phase or workstream.\n- **decision.** What was chosen or done, one line.\n- **why.** The reason in plain words. If a principle drove it, say it plainly, not as a jargon tag.\n- **evidence.** A link or path that proves it: commit SHA, PR number, `file:line`, or an artifact, trace, or screenshot path. Never a paragraph.\n- **result.** The outcome or predicate state: `tests green`, `reverted`, `pixel-diff 0`, `INCONCLUSIVE`, `open`.\n\nAn example, plain-spoken so a reviewer reads it at a glance.\n\n```\nts\tphase\tdecision\twhy\tevidence\tresult\n2026-05-24T09:02:00Z\tframe\tcounted the work first, about 100 components and roughly 75 hours\twanted to know the size before starting a long run\tcommit 3a9f1c2\tfound 5 things to sort out before starting\n2026-05-24T09:40:00Z\tharness\ttook screenshots of the old version before changing anything\tso we can compare old against new and catch any visual change\tscripts\u002Fsnapshot.sh, baseline\u002F\tsaved 120 reference screenshots\n2026-05-24T11:15:00Z\twidget\tmoved the widget styles over without changing how it looks\tkeep the change small and the result identical\tcommit 7c21e0a, pixel-diff 0\tlooks identical, tests pass\n2026-05-24T12:30:00Z\twidget\tthrew out a helper's work because its screenshots were blank\tchecked the real files instead of trusting its summary\tworktree reset\treverted, tightened the instructions for next time\n```\n\n## Logging a row\n\nWrite each entry the way you'd tell a teammate what you did. Plain words, concrete actions, no AI speak or abstract jargon (the **unslop** skill applies to log text too).\n\nUse the helper `scripts\u002Flog.sh \u003Clogfile> \u003Cphase> \u003Cdecision> \u003Cwhy> \u003Cevidence> \u003Cresult>`. It stamps `ts`, writes the header on first use, strips stray tabs\u002Fnewlines, and prefixes any cell starting with `=`, `+`, `-`, or `@` with a single quote. A bare `printf` appending a row works too, but mind those same bytes if cells come from generated or user-supplied text.\n\nLog decision points and checkpoints, not every action: a fork chosen, a unit completed with its verification result, a pivot or revert with its trigger, a blocker surfaced, a gate fixed. For loop runs, one row per iteration. Skip the trivial and self-evident.\n\nA run is one agent conversation, including its later turns and any summary of it. A pickup, a replacement agent, or a new chat starts a new run. When a run adds to a log that already has rows, its first row has phase `start`, and so does its first row after another run's `start` row. So a run that comes back to a log in a later turn first reads the log's last rows to see whether another run wrote since. A `start` row names the `ts` range of the rows before it that this run did not write, and its evidence names this run, such as its agent id. Use phase `start` for nothing else.\n\n## Where it lives\n\nBy default the log is a working artifact, not committed. Keep it at `decisions.tsv` in the work dir, or `.audit\u002F\u003Ctask-slug>.tsv` when several efforts run at once, and leave it out of git.\n\nCommit it only when the work is ambitious enough that a reviewer needs the trail to trust the result.\n\n## Rules\n\n- Append-only. A wrong call gets a new row that supersedes it. Never edit or delete history.\n- Prefer evidence produced by committed scripts over hand-made one-offs (the **encode-lessons-in-structure** principle skill).\n\n## Audit the log against the transcript\n\nAt the end of the run, before handing back, check the log told the truth. Read this run's transcript with `t3_thread_read` and this thread's ID (`parentThreadId` from `orchestrator_capabilities`), paging with `afterPosition`; `view: \"activity\"` shows tool calls. Don't search other threads for it. That reads unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's `start` rows, or at the first row if this run created the log, and ends at the next `start` row of another run:\n\n- Check that every row maps to a real decision or action.\n- Check that each row's evidence resolves and shows what the row claims.\n- A fork, pivot, or abandoned approach that shaped the work but isn't logged is a gap. Add it.\n\nCorrect the log, not the story. The audit never edits or removes a row, even an invented one. When a row records neither a real decision nor a real action, or its claim or evidence is wrong, add a row that supersedes it with what actually happened and a pointer that resolves. This audit does not check rows outside this run's stretches. If this run's own work shows one of them is wrong, supersede it like any wrong call.\n\n## Cross-model review of the trail\n\nBefore handing back, spawn a subagent with `delegate_task` on the same model and effort as the one that did the work, unless the user named another. Self-review is not a substitute. The subagent reads the audit trail and the run's transcript (give it this thread's ID to read with `t3_thread_read`), then flags what the user should pay attention to. Not a redo of the work, a scan for what's suboptimal or risky. Pick its effort for the job within that entry's ceiling, per the Subagents section of the **poteto-mode** skill.\n\n- Decisions logged with weak or absent evidence.\n- Verification steps skipped or claimed without proof in the transcript.\n- Choices that look risky in hindsight (premature, scope-creeping, papering over a symptom).\n- Gaps the user would otherwise miss on a casual skim.\n\nEvery reply for a run that produced a trail ends with an \"Attention\" section. Lead with the reviewer's model on its own line (`reviewed by \u003Cmodel>`), then list each flag pointing to specific rows or moments. \"No flags\" is a valid value. The model name is not.\n\n## Reviewing the trail\n\nRead top to bottom, follow the evidence pointers, spot-check. GitHub renders a committed TSV as a table. `column -s$'\\t' -t decisions.tsv` renders it in a terminal.\n\n## Composing this skill\n\nOther skills route their audit trail here instead of inventing one. Reference it by name and let it own the format. Don't restate the columns.\n","# Show me your work\n\nKeep one canonical log.\n\n## The format\n\nA single TSV file, one row per decision. Cells stay single-line. Evidence is a pointer, not prose.\n\nCopy `references\u002Fdecision-log-template.tsv` (the header row) to start a clean log. Columns:\n\n- **ts.** ISO8601 timestamp.\n- **phase.** The phase or workstream.\n- **decision.** What was chosen or done, one line.\n- **why.** The reason in plain words. If a principle drove it, say it plainly, not as a jargon tag.\n- **evidence.** A link or path that proves it: commit SHA, PR number, `file:line`, or an artifact, trace, or screenshot path. Never a paragraph.\n- **result.** The outcome or predicate state: `tests green`, `reverted`, `pixel-diff 0`, `INCONCLUSIVE`, `open`.\n\nAn example, plain-spoken so a reviewer reads it at a glance.\n\n```\nts\tphase\tdecision\twhy\tevidence\tresult\n2026-05-24T09:02:00Z\tframe\tcounted the work first, about 100 components and roughly 75 hours\twanted to know the size before starting a long run\tcommit 3a9f1c2\tfound 5 things to sort out before starting\n2026-05-24T09:40:00Z\tharness\ttook screenshots of the old version before changing anything\tso we can compare old against new and catch any visual change\tscripts\u002Fsnapshot.sh, baseline\u002F\tsaved 120 reference screenshots\n2026-05-24T11:15:00Z\twidget\tmoved the widget styles over without changing how it looks\tkeep the change small and the result identical\tcommit 7c21e0a, pixel-diff 0\tlooks identical, tests pass\n2026-05-24T12:30:00Z\twidget\tthrew out a helper's work because its screenshots were blank\tchecked the real files instead of trusting its summary\tworktree reset\treverted, tightened the instructions for next time\n```\n\n## Logging a row\n\nWrite each entry the way you'd tell a teammate what you did. Plain words, concrete actions, no AI speak or abstract jargon (the **unslop** skill applies to log text too).\n\nUse the helper `scripts\u002Flog.sh \u003Clogfile> \u003Cphase> \u003Cdecision> \u003Cwhy> \u003Cevidence> \u003Cresult>`. It stamps `ts`, writes the header on first use, strips stray tabs\u002Fnewlines, and prefixes any cell starting with `=`, `+`, `-`, or `@` with a single quote. A bare `printf` appending a row works too, but mind those same bytes if cells come from generated or user-supplied text.\n\nLog decision points and checkpoints, not every action: a fork chosen, a unit completed with its verification result, a pivot or revert with its trigger, a blocker surfaced, a gate fixed. For loop runs, one row per iteration. Skip the trivial and self-evident.\n\nA run is one agent conversation, including its later turns and any summary of it. A pickup, a replacement agent, or a new chat starts a new run. When a run adds to a log that already has rows, its first row has phase `start`, and so does its first row after another run's `start` row. So a run that comes back to a log in a later turn first reads the log's last rows to see whether another run wrote since. A `start` row names the `ts` range of the rows before it that this run did not write, and its evidence names this run, such as its agent id. Use phase `start` for nothing else.\n\n## Where it lives\n\nBy default the log is a working artifact, not committed. Keep it at `decisions.tsv` in the work dir, or `.audit\u002F\u003Ctask-slug>.tsv` when several efforts run at once, and leave it out of git.\n\nCommit it only when the work is ambitious enough that a reviewer needs the trail to trust the result.\n\n## Rules\n\n- Append-only. A wrong call gets a new row that supersedes it. Never edit or delete history.\n- Prefer evidence produced by committed scripts over hand-made one-offs (the **encode-lessons-in-structure** principle skill).\n\n## Audit the log against the transcript\n\nAt the end of the run, before handing back, check the log told the truth. Read this run's transcript with `t3_thread_read` and this thread's ID (`parentThreadId` from `orchestrator_capabilities`), paging with `afterPosition`; `view: \"activity\"` shows tool calls. Don't search other threads for it. That reads unrelated private chats. Walk this run's rows against what actually happened. Each stretch of them begins at one of this run's `start` rows, or at the first row if this run created the log, and ends at the next `start` row of another run:\n\n- Check that every row maps to a real decision or action.\n- Check that each row's evidence resolves and shows what the row claims.\n- A fork, pivot, or abandoned approach that shaped the work but isn't logged is a gap. Add it.\n\nCorrect the log, not the story. The audit never edits or removes a row, even an invented one. When a row records neither a real decision nor a real action, or its claim or evidence is wrong, add a row that supersedes it with what actually happened and a pointer that resolves. This audit does not check rows outside this run's stretches. If this run's own work shows one of them is wrong, supersede it like any wrong call.\n\n## Cross-model review of the trail\n\nBefore handing back, spawn a subagent with `delegate_task` on the same model and effort as the one that did the work, unless the user named another. Self-review is not a substitute. The subagent reads the audit trail and the run's transcript (give it this thread's ID to read with `t3_thread_read`), then flags what the user should pay attention to. Not a redo of the work, a scan for what's suboptimal or risky. Pick its effort for the job within that entry's ceiling, per the Subagents section of the **poteto-mode** skill.\n\n- Decisions logged with weak or absent evidence.\n- Verification steps skipped or claimed without proof in the transcript.\n- Choices that look risky in hindsight (premature, scope-creeping, papering over a symptom).\n- Gaps the user would otherwise miss on a casual skim.\n\nEvery reply for a run that produced a trail ends with an \"Attention\" section. Lead with the reviewer's model on its own line (`reviewed by \u003Cmodel>`), then list each flag pointing to specific rows or moments. \"No flags\" is a valid value. The model name is not.\n\n## Reviewing the trail\n\nRead top to bottom, follow the evidence pointers, spot-check. GitHub renders a committed TSV as a table. `column -s$'\\t' -t decisions.tsv` renders it in a terminal.\n\n## Composing this skill\n\nOther skills route their audit trail here instead of inventing one. Reference it by name and let it own the format. Don't restate the columns.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","b47f5118e95c2c9791e6e975b6a9a97571d2dc67",".agents\u002Fskills\u002Fshow-me-your-work",0,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook","https:\u002F\u002Fgithub.com\u002Fwillgosnold","Independent AI safety research | London | MSc @ University of Exeter ","2026-10-28 06:42:27",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add willgosnold\u002Fpatchbook --skill show-me-your-work",{"tool":39,"command":40},"bunx","bunx skills add willgosnold\u002Fpatchbook --skill show-me-your-work",{"tool":42,"command":43},"pnpm","pnpm dlx skills add willgosnold\u002Fpatchbook --skill show-me-your-work","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshow-me-your-work\u002FSKILL.md",[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdecision-log-template.tsv","REFERENCE","参考文档",38,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshow-me-your-work\u002Freferences\u002Fdecision-log-template.tsv",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Flog.sh","SCRIPT","脚本",1377,"https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshow-me-your-work\u002Fscripts\u002Flog.sh",[59,66,73,80,87,94],{"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},"01M7F1TFAS2GDQR010AV81M3H1","patchbook-update","Pull upstreams into a repo that keeps its changes in a patchbook (.patchbook\u002F), repair what broke from each change's intent, test and review, then merge and deploy only when the sync was clean or the test command passes, and otherwise ask, opening a pull request when there are commits to push. Use when a scheduled task or the user says to update a patchbook repo, or for \u002Fpatchbook-update or $patchbook-update.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002Fskills\u002Fpatchbook-update\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},"01M7F1T945FRSKCATSWWGM0HJG","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\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwhy\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},"01M7F1T54ST6QFMHX8CX01DKNB","verify-patchbook","Drive the patchbook CLI from this checkout in a disposable sandbox (its own git repos, store, config and a fake model) and capture a transcript as proof. Use to reproduce a patchbook bug, run an issue's repro script, or prove a change to clone, init, record, the pre-commit hook, build, status, check, sync or upstream works the way a user would see it.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-patchbook\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},"01M7F1T3NHKBVGVD4BT2C5BG7A","unslop","Cut AI tells from any writing.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Funslop\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7F1T1SSJSW2KVN8JXXBGZNN","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftypescript-best-practices\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7F1SXXN9RHQNWNG3JFBPZW0","technical-writing","Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for \u002Ftechnical-writing or $technical-writing, or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.","https:\u002F\u002Fgithub.com\u002Fwillgosnold\u002Fpatchbook\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftechnical-writing\u002FSKILL.md",[],[]]