[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E4P4KF6W8YT7WTM8YQB5WN":3,"skill-same:01M7E4P4KF6W8YT7WTM8YQB5WN":53},{"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":46},"01M7E4P4KF6W8YT7WTM8YQB5WN","session-close",null,"End a working session in a fixed order: clean tree, short retrospective, roadmap and log, handoff file, commit and push. Use when the user says 'close the session', 'end the session' or 'wrap up this session', or when work stops for the day, the context is nearly full, or a roadmap item is done and the next will not fit.","paureis\u002Fpau-skills","paureis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F133926455?v=4","01M7E4HCQNKQ22F6VQFHRFHW8K","Alvaro Reis","01M7E4HCRJJ4EDXQHFJN1MW493",2,"MIT","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-discipline\u002Fsession-close\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: session-close\ndescription: \"End a working session in a fixed order: clean tree, short retrospective, roadmap and log, handoff file, commit and push. Use when the user says 'close the session', 'end the session' or 'wrap up this session', or when work stops for the day, the context is nearly full, or a roadmap item is done and the next will not fit.\"\nargument-hint: \"[optional: what the next session should focus on]\"\n---\n\n# Session close\n\nOne command for the loop: work -> reflect -> prepare the next session. It runs in full and in this order; no step is\nskipped silently. If a step does not apply, say why.\n\nIf you started this skill on your own, without the user typing its name or asking for what it does, first say in one\nor two lines what it will do and what it will cost, and wait for a yes. A remark or a question that only matches its\ndescription is not asking for it. If the user asked for it, or the brief you are working from does, go ahead.\n\n## Configuration\n\nThe file paths come from the project's `.claude\u002Froadmap.json` if it exists (the same file the `session-discipline`\nroadmap hook reads), otherwise the defaults:\n\n```json\n{ \"roadmap\": \"docs\u002FROADMAP.md\", \"log\": \"docs\u002FLOG.md\", \"handoff\": \"HANDOFF.md\" }\n```\n\nThe project's definition of done (which suites must pass before something counts as finished) lives in its own\n`CLAUDE.md` or process document. This skill applies it; it does not define it.\n\n## 0. When\n\nIt fits when:\n\n- the user wants to end the session;\n- the context is nearly full (a `CONTEXT WARNING` or `CONTEXT CRITICAL` in a tool result, if the project has a hook\n  that reports it);\n- a roadmap item meets its definition of done and the next one does not fit in what is left of the session.\n\nIf `CONTEXT WARNING` or `CONTEXT CRITICAL` appears during the close, keep going and keep each step short. Do not\nestimate context use yourself; the injected figure is authoritative. At a warning, the agent may start the close on its\nown, and it then asks first, as said at the top. A project that wants this every time can say so in its `CLAUDE.md`,\nfor example \"At a CONTEXT WARNING, finish the current action and start the session close\".\n\n## 1. Clean state\n\n- `git status --short`: nothing half-done. Finished work is committed with the project's definition of done.\n  Unfinished work goes in a `WIP: \u003Citem> - \u003Cwhat is missing>` commit only if it builds and does not break the suites,\n  and the handoff describes it. Never leave work uncommitted.\n- `git worktree list` and `git worktree prune`; remove worktrees whose work is merged or abandoned (confirm\n  `git -C \u003Cdir> status --short` is empty first).\n- Scratch files hold no secrets. If the project records a \"linked environment\" invariant (which cloud project or\n  account this checkout must point at), check it now.\n\n## 2. Retrospective\n\nThis skill carries its own copy of the rules audit, `${CLAUDE_SKILL_DIR}\u002Faudit.mjs`. It is the same script the\n`retrospective` skill uses, so this step works whether or not that skill is installed. Run it with `node` from the\nproject root.\n\n- Run the short version here: list the corrections the user made and the work that was redone; write each lesson\n  that will happen again as a proposed line in a scratch file; score it with\n  `node \"${CLAUDE_SKILL_DIR}\u002Faudit.mjs\" --check \u003Cfile>`; and apply only the lines that are not already there and that\n  the user approves. If the `retrospective` skill is installed and the user wants the full version, run it now, and\n  continue with the next step when it is done.\n- Either way, run `node \"${CLAUDE_SKILL_DIR}\u002Faudit.mjs\" --stale` from the project root: every path, command or script\n  cited in `CLAUDE.md` and memory that no longer exists is fixed or deleted in the same session.\n- Bar for adding anything: it will happen again, a future agent would act differently because of it, it names the\n  failure it prevents, and it fits in 8 lines. If a rule already existed and was broken anyway, the answer is to\n  mechanize it, not to rewrite it. Net growth of the rule stores is zero or negative per session (before\u002Fafter bytes\n  in the final message).\n- \"Nothing to add\" is a valid result, and it is said.\n\n## 3. Roadmap and log\n\n- Roadmap: the status of every item touched (`pending` \u002F `in progress` \u002F `blocked (reason)` \u002F `done (date)`). Review\n  the Ideas section, if there is one: when an entry changed or looks ripe, put it to the user as a decision with a\n  recommendation per entry (promote, keep, delete). That decision is the user's, not the model's. If the order stopped\n  being the best one, reorder and write down why in the log.\n- Log: one line per close with the date, what was done and the evidence (commit, PR, URL, test run). Take times from\n  the machine clock (`date`), never from the UTC `Z` timestamps in agent notifications: a close once logged 02:40 of\n  the next day for 22:40, and the next session believed a day had passed.\n- Design and security documents only if the session made decisions in those areas.\n\n## 4. Handoff\n\nWrite the handoff file yourself (the same file the `handoff` skill writes in park mode, if it is installed) with these\nsections: what the work is (two or three sentences), what was done, key learnings, the current state, the\nnext steps (the user's priority first), and reference material (paths and decisions, not copies). Start the file with\nan instruction to the next session: say what you understand was done and your proposed next steps, then wait for\napproval before changing anything.\n\nThe handoff always carries:\n\n- **The exact state of the item in progress**: which parts are done, what is missing, which tests fail, what is in\n  WIP and why.\n- **The first command of the next session** (literal) and the result it should produce.\n- **A start-up order**: first commands -> read-only research agents on the next item (an inventory of what already\n  exists, a verification of the code to be touched, an audit) -> design discussion from their reports -> the user's\n  approval -> the builder. Never the design discussion before the research.\n- **What was tried and did not work** in the session, with the reason, so nobody repeats it.\n- **Open questions for other people**, each with the roadmap item it blocks.\n- References to documents for what is stable (`CLAUDE.md`, the process document, the roadmap), not copies: the\n  handoff is long on what is specific to this session and short on what already lives in a document.\n- **The models used**: the orchestrator's (from its system prompt) and the one each agent reported in its final\n  report. If either changed since the previous handoff, say so here and in the final message.\n\n## 5. Commit and push\n\n`git add` the docs, roadmap, log, handoff and any project rule changes; commit with the message from a file\n(`git commit -F \u003Cfile>`); push the working branch. Then confirm `git rev-parse origin\u002F\u003Cbranch>` equals the local head\nand the tree is clean. If a pull request is waiting to be merged and the project's CI skips re-running already-tested\nheads, note in the handoff that this push changes the head it will test.\n\n## 6. Final message\n\nShort, in this order: what was done, what is in WIP, what the retrospective learned (or \"nothing\") with each store's\nbytes before and after, and the next roadmap item with its first command. If a decision of the user's blocks the next\nitem, ask it as a question the user can answer directly.\n","# Session close\n\nOne command for the loop: work -> reflect -> prepare the next session. It runs in full and in this order; no step is\nskipped silently. If a step does not apply, say why.\n\nIf you started this skill on your own, without the user typing its name or asking for what it does, first say in one\nor two lines what it will do and what it will cost, and wait for a yes. A remark or a question that only matches its\ndescription is not asking for it. If the user asked for it, or the brief you are working from does, go ahead.\n\n## Configuration\n\nThe file paths come from the project's `.claude\u002Froadmap.json` if it exists (the same file the `session-discipline`\nroadmap hook reads), otherwise the defaults:\n\n```json\n{ \"roadmap\": \"docs\u002FROADMAP.md\", \"log\": \"docs\u002FLOG.md\", \"handoff\": \"HANDOFF.md\" }\n```\n\nThe project's definition of done (which suites must pass before something counts as finished) lives in its own\n`CLAUDE.md` or process document. This skill applies it; it does not define it.\n\n## 0. When\n\nIt fits when:\n\n- the user wants to end the session;\n- the context is nearly full (a `CONTEXT WARNING` or `CONTEXT CRITICAL` in a tool result, if the project has a hook\n  that reports it);\n- a roadmap item meets its definition of done and the next one does not fit in what is left of the session.\n\nIf `CONTEXT WARNING` or `CONTEXT CRITICAL` appears during the close, keep going and keep each step short. Do not\nestimate context use yourself; the injected figure is authoritative. At a warning, the agent may start the close on its\nown, and it then asks first, as said at the top. A project that wants this every time can say so in its `CLAUDE.md`,\nfor example \"At a CONTEXT WARNING, finish the current action and start the session close\".\n\n## 1. Clean state\n\n- `git status --short`: nothing half-done. Finished work is committed with the project's definition of done.\n  Unfinished work goes in a `WIP: \u003Citem> - \u003Cwhat is missing>` commit only if it builds and does not break the suites,\n  and the handoff describes it. Never leave work uncommitted.\n- `git worktree list` and `git worktree prune`; remove worktrees whose work is merged or abandoned (confirm\n  `git -C \u003Cdir> status --short` is empty first).\n- Scratch files hold no secrets. If the project records a \"linked environment\" invariant (which cloud project or\n  account this checkout must point at), check it now.\n\n## 2. Retrospective\n\nThis skill carries its own copy of the rules audit, `${CLAUDE_SKILL_DIR}\u002Faudit.mjs`. It is the same script the\n`retrospective` skill uses, so this step works whether or not that skill is installed. Run it with `node` from the\nproject root.\n\n- Run the short version here: list the corrections the user made and the work that was redone; write each lesson\n  that will happen again as a proposed line in a scratch file; score it with\n  `node \"${CLAUDE_SKILL_DIR}\u002Faudit.mjs\" --check \u003Cfile>`; and apply only the lines that are not already there and that\n  the user approves. If the `retrospective` skill is installed and the user wants the full version, run it now, and\n  continue with the next step when it is done.\n- Either way, run `node \"${CLAUDE_SKILL_DIR}\u002Faudit.mjs\" --stale` from the project root: every path, command or script\n  cited in `CLAUDE.md` and memory that no longer exists is fixed or deleted in the same session.\n- Bar for adding anything: it will happen again, a future agent would act differently because of it, it names the\n  failure it prevents, and it fits in 8 lines. If a rule already existed and was broken anyway, the answer is to\n  mechanize it, not to rewrite it. Net growth of the rule stores is zero or negative per session (before\u002Fafter bytes\n  in the final message).\n- \"Nothing to add\" is a valid result, and it is said.\n\n## 3. Roadmap and log\n\n- Roadmap: the status of every item touched (`pending` \u002F `in progress` \u002F `blocked (reason)` \u002F `done (date)`). Review\n  the Ideas section, if there is one: when an entry changed or looks ripe, put it to the user as a decision with a\n  recommendation per entry (promote, keep, delete). That decision is the user's, not the model's. If the order stopped\n  being the best one, reorder and write down why in the log.\n- Log: one line per close with the date, what was done and the evidence (commit, PR, URL, test run). Take times from\n  the machine clock (`date`), never from the UTC `Z` timestamps in agent notifications: a close once logged 02:40 of\n  the next day for 22:40, and the next session believed a day had passed.\n- Design and security documents only if the session made decisions in those areas.\n\n## 4. Handoff\n\nWrite the handoff file yourself (the same file the `handoff` skill writes in park mode, if it is installed) with these\nsections: what the work is (two or three sentences), what was done, key learnings, the current state, the\nnext steps (the user's priority first), and reference material (paths and decisions, not copies). Start the file with\nan instruction to the next session: say what you understand was done and your proposed next steps, then wait for\napproval before changing anything.\n\nThe handoff always carries:\n\n- **The exact state of the item in progress**: which parts are done, what is missing, which tests fail, what is in\n  WIP and why.\n- **The first command of the next session** (literal) and the result it should produce.\n- **A start-up order**: first commands -> read-only research agents on the next item (an inventory of what already\n  exists, a verification of the code to be touched, an audit) -> design discussion from their reports -> the user's\n  approval -> the builder. Never the design discussion before the research.\n- **What was tried and did not work** in the session, with the reason, so nobody repeats it.\n- **Open questions for other people**, each with the roadmap item it blocks.\n- References to documents for what is stable (`CLAUDE.md`, the process document, the roadmap), not copies: the\n  handoff is long on what is specific to this session and short on what already lives in a document.\n- **The models used**: the orchestrator's (from its system prompt) and the one each agent reported in its final\n  report. If either changed since the previous handoff, say so here and in the final message.\n\n## 5. Commit and push\n\n`git add` the docs, roadmap, log, handoff and any project rule changes; commit with the message from a file\n(`git commit -F \u003Cfile>`); push the working branch. Then confirm `git rev-parse origin\u002F\u003Cbranch>` equals the local head\nand the tree is clean. If a pull request is waiting to be merged and the project's CI skips re-running already-tested\nheads, note in the handoff that this push changes the head it will test.\n\n## 6. Final message\n\nShort, in this order: what was done, what is in WIP, what the retrospective learned (or \"nothing\") with each store's\nbytes before and after, and the next roadmap item with its first command. If a decision of the user's blocks the next\nitem, ask it as a question the user can answer directly.\n",{"name":5,"description":7,"argument-hint":24},"[optional: what the next session should focus on]","main","2817107c191e822dfe71d6aff5d286cc8211c592","skills\u002Fsession-discipline\u002Fsession-close",0,"https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills","https:\u002F\u002Fgithub.com\u002Fpaureis","AI engineer | building multi-tenant products end to end","2026-11-12 06:02:49",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add paureis\u002Fpau-skills --skill session-close",{"tool":39,"command":40},"bunx","bunx skills add paureis\u002Fpau-skills --skill session-close",{"tool":42,"command":43},"pnpm","pnpm dlx skills add paureis\u002Fpau-skills --skill session-close","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-discipline\u002Fsession-close\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"audit.mjs","SCRIPT","脚本",16039,"https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsession-discipline\u002Fsession-close\u002Faudit.mjs",[54,61,66,73,79,86],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7E4SRKNACXVPZYJ6HX2PQXY","tidy-notes","Tidy a plain text list: sort the lines and remove repeated ones. Use when the user types \u002Ftidy-notes.","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval\u002Fvariant-b\u002FSKILL.md",[],[],{"skillNo":62,"name":56,"nameZh":6,"description":57,"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},"01M7E4SMEGAVM1547Y611T38SM","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval\u002Fvariant-a\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},"01M7E4SGSPHAJKYR8RX45ZKH3F","other-notes","A skill with a different name, for the refusal case.","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval\u002Fother-name\u002FSKILL.md",[],[],{"skillNo":74,"name":56,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7E4SCTQ7AR5MGPJ3YRXSF06","Tidy a plain text list: sort the lines and remove repeated ones. Use when the user asks to tidy notes.","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval-triggers\u002Fskills\u002Ftidy-notes\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7E4S920AVTNN4W61JQY4X9Z","pack-boxes","Plan how to pack boxes for a move, room by room. Use when the user asks to pack for a move.","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval-triggers\u002Fskills\u002Fpack-boxes\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7E4S4ZXZWND0TGQ1E4N39KP","renamed-skill","A skill whose folder name differs from its name. Use when the user asks to rename something.","https:\u002F\u002Fgithub.com\u002Fpaureis\u002Fpau-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskill-eval-triggers\u002Frenamed\u002Fsome-folder\u002FSKILL.md",[],[]]