[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79SNJBK301QNWS0CC570N3M":3,"skill-same:01M79SNJBK301QNWS0CC570N3M":91},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M79SNJBK301QNWS0CC570N3M","handoff",null,"A session needs to end or continue elsewhere — \"write a handoff\", \"I'm running low on context\", \"continue where we left off\". Writes and resumes a handoff that survives compaction.","dannybrown37\u002Fskill-tree","dannybrown37","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28059438?v=4","01M79SKVHAKWQH9VF0G6KQRZZ2","Danny Brown","01M79SKVJ1X8VHPTK7MKMHBRD2",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: handoff\ndescription: \"A session needs to end or continue elsewhere — \\\"write a handoff\\\", \\\"I'm running low on context\\\", \\\"continue where we left off\\\". Writes and resumes a handoff that survives compaction.\"\nuser-invocable: true\nallowed-tools: Read, Write, Edit, Grep, Glob, Bash\n---\n\n# Handoff\n\nA handoff is a controlled `\u002Fcompact`: the model that did the work distills a **state packet\nthe next session can safely act on**, written for a competent stranger who has the repo and\nnothing else. Write it while there's context left to think with, not at 3%.\n\n## Files\n\nScoped per git branch at `docs\u002Fhandoffs\u002F\u003Cbranch>\u002F` (`\u002F` → `-`; nothing on detached HEAD).\nIf the repo already has a convention (a `HANDOFF.md`, a path named in `CLAUDE.md`), use it.\n\n- `CURRENT.md` — re-entry prompt. Short; exactly one next action. Consumed, then replaced.\n- `NARRATIVE.md` — what was done and decided, and why. Appended across sessions.\n- `BACKLOG.md` — work that isn't next. **Only touch via the CLI.**\n\nSmall single-session work can skip the narrative. Why the split:\n`references\u002Frationale.md`. Skeletons: `references\u002Ftemplate.md`.\n\n## CLI\n\nIf `handoff` isn't on `PATH`, use\n`\"${CLAUDE_PLUGIN_ROOT:-${SKILL_TREE_DIR:-$HOME\u002Fprojects\u002Fskill-tree}}\u002Fskills\u002Fhandoff\u002Fscripts\u002Fhandoff\"`.\n\n- `handoff add --title \"...\" --body \"...\"` — capture for later (`next` for the top)\n- `handoff backlog` \u002F `current` \u002F `narrative` — read a file\n- `handoff pop` — move the top backlog item into `CURRENT.md`. **Ask the user first.**\n- `handoff status [--set \u003Ckeyword>]` — status of every project, or set this one's\n- `handoff close` — delete this branch's handoff dir; distill keepers to `CLAUDE.md`\u002Fmemory first\n\nFlags and repo selection: `references\u002Fbacklog.md`.\n\n## Reference, don't absorb\n\nLogs, diffs, test output, specs stay where they are — reference by path, command, or ID. Never\nwrite what the repo already answers (file inventories, diff recaps). No `PLAN.md`: decisions go\nin the narrative, the next step in `CURRENT.md`.\n\n## CURRENT.md\n\n1. **Goal** — one or two sentences, including why.\n2. **Anchor** — timestamp, branch, `git rev-parse --short HEAD`, dirty\u002Fclean, handoff counter\n   (`#3 of this thread`). Run the commands; never from memory.\n3. **Read order** — which files, in what sequence, which to grep rather than read.\n4. **In flight** — the half-finished edit by `file:line`, and what it needs.\n5. **Next action** — one concrete step startable without a decision.\n6. **Acceptance check** — the command that proves it worked.\n7. **Open questions** — marked blocked, so the next session asks.\n\nNear the top: `**Status:** \u003Ckeyword>`, read by the session-start hook and `handoff status`:\n\n- `in-progress` — mid-flight (`pop` sets this)\n- `awaiting-review` — done and green, user's turn. Committing past the anchor auto-promotes it\n  to between-tasks.\n- `between-tasks` — settled. With an empty backlog, suggest `handoff close`.\n\n## NARRATIVE.md\n\nOrdered by how unrecoverable it is otherwise:\n\n1. **Tried and failed** — what, what happened, why abandoned. The most valuable, most dropped.\n2. **Decisions and constraints** with reasons, incl. the user's rejections (\"no new dep\").\n3. **Done, with evidence** — `\u003Cclaim>` — `\u003Ccommand>` → result, at `\u003Csha>`. Use `verify`.\n4. **Lessons and surprises.**\n\n## Resuming\n\n1. Read `CURRENT.md` completely; follow its read order.\n2. Check the anchor against reality. HEAD moved → every claim is suspect.\n3. Re-run the done-evidence. If one fails, correct the narrative first. If it can't run here\n   (service down, env missing), say so and keep the claim — only a real failure invalidates it.\n4. Skim `handoff backlog` titles, so deferred work is known but not started.\n5. State back goal, state, and next action in a few lines; let the user correct you.\n\n## Write-back — per task, same turn, not at session end\n\n- Narrative: append done-claim + evidence, plus any decision, dead end, or surprise.\n- `CURRENT.md`: rewrite next action + acceptance check, clear resolved in-flight, re-anchor if\n  committed. Edit in place — replace, never append a second prompt.\n- `handoff status --set` as state changes.\n- Anything surfaced that isn't next → `handoff add`, never parked in `CURRENT.md`.\n\nHook automation: `references\u002Fhooks.md`. Lifecycle diagrams: `references\u002Fflow.md`. Failure\nmodes: `references\u002Frationale.md`.\n","# Handoff\n\nA handoff is a controlled `\u002Fcompact`: the model that did the work distills a **state packet\nthe next session can safely act on**, written for a competent stranger who has the repo and\nnothing else. Write it while there's context left to think with, not at 3%.\n\n## Files\n\nScoped per git branch at `docs\u002Fhandoffs\u002F\u003Cbranch>\u002F` (`\u002F` → `-`; nothing on detached HEAD).\nIf the repo already has a convention (a `HANDOFF.md`, a path named in `CLAUDE.md`), use it.\n\n- `CURRENT.md` — re-entry prompt. Short; exactly one next action. Consumed, then replaced.\n- `NARRATIVE.md` — what was done and decided, and why. Appended across sessions.\n- `BACKLOG.md` — work that isn't next. **Only touch via the CLI.**\n\nSmall single-session work can skip the narrative. Why the split:\n`references\u002Frationale.md`. Skeletons: `references\u002Ftemplate.md`.\n\n## CLI\n\nIf `handoff` isn't on `PATH`, use\n`\"${CLAUDE_PLUGIN_ROOT:-${SKILL_TREE_DIR:-$HOME\u002Fprojects\u002Fskill-tree}}\u002Fskills\u002Fhandoff\u002Fscripts\u002Fhandoff\"`.\n\n- `handoff add --title \"...\" --body \"...\"` — capture for later (`next` for the top)\n- `handoff backlog` \u002F `current` \u002F `narrative` — read a file\n- `handoff pop` — move the top backlog item into `CURRENT.md`. **Ask the user first.**\n- `handoff status [--set \u003Ckeyword>]` — status of every project, or set this one's\n- `handoff close` — delete this branch's handoff dir; distill keepers to `CLAUDE.md`\u002Fmemory first\n\nFlags and repo selection: `references\u002Fbacklog.md`.\n\n## Reference, don't absorb\n\nLogs, diffs, test output, specs stay where they are — reference by path, command, or ID. Never\nwrite what the repo already answers (file inventories, diff recaps). No `PLAN.md`: decisions go\nin the narrative, the next step in `CURRENT.md`.\n\n## CURRENT.md\n\n1. **Goal** — one or two sentences, including why.\n2. **Anchor** — timestamp, branch, `git rev-parse --short HEAD`, dirty\u002Fclean, handoff counter\n   (`#3 of this thread`). Run the commands; never from memory.\n3. **Read order** — which files, in what sequence, which to grep rather than read.\n4. **In flight** — the half-finished edit by `file:line`, and what it needs.\n5. **Next action** — one concrete step startable without a decision.\n6. **Acceptance check** — the command that proves it worked.\n7. **Open questions** — marked blocked, so the next session asks.\n\nNear the top: `**Status:** \u003Ckeyword>`, read by the session-start hook and `handoff status`:\n\n- `in-progress` — mid-flight (`pop` sets this)\n- `awaiting-review` — done and green, user's turn. Committing past the anchor auto-promotes it\n  to between-tasks.\n- `between-tasks` — settled. With an empty backlog, suggest `handoff close`.\n\n## NARRATIVE.md\n\nOrdered by how unrecoverable it is otherwise:\n\n1. **Tried and failed** — what, what happened, why abandoned. The most valuable, most dropped.\n2. **Decisions and constraints** with reasons, incl. the user's rejections (\"no new dep\").\n3. **Done, with evidence** — `\u003Cclaim>` — `\u003Ccommand>` → result, at `\u003Csha>`. Use `verify`.\n4. **Lessons and surprises.**\n\n## Resuming\n\n1. Read `CURRENT.md` completely; follow its read order.\n2. Check the anchor against reality. HEAD moved → every claim is suspect.\n3. Re-run the done-evidence. If one fails, correct the narrative first. If it can't run here\n   (service down, env missing), say so and keep the claim — only a real failure invalidates it.\n4. Skim `handoff backlog` titles, so deferred work is known but not started.\n5. State back goal, state, and next action in a few lines; let the user correct you.\n\n## Write-back — per task, same turn, not at session end\n\n- Narrative: append done-claim + evidence, plus any decision, dead end, or surprise.\n- `CURRENT.md`: rewrite next action + acceptance check, clear resolved in-flight, re-anchor if\n  committed. Edit in place — replace, never append a second prompt.\n- `handoff status --set` as state changes.\n- Anything surfaced that isn't next → `handoff add`, never parked in `CURRENT.md`.\n\nHook automation: `references\u002Fhooks.md`. Lifecycle diagrams: `references\u002Fflow.md`. Failure\nmodes: `references\u002Frationale.md`.\n",{"name":5,"description":7,"allowed-tools":24,"user-invocable":25},"Read, Write, Edit, Grep, Glob, Bash",true,"main","aec70683dacdf9512d27e04a1e04069bbd199b5e","skills\u002Fhandoff","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree","https:\u002F\u002Fgithub.com\u002Fdannybrown37","dannybrown.dev","Software Engineer","2026-11-12 15:25:14",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add dannybrown37\u002Fskill-tree --skill handoff",{"tool":40,"command":41},"bunx","bunx skills add dannybrown37\u002Fskill-tree --skill handoff",{"tool":43,"command":44},"pnpm","pnpm dlx skills add dannybrown37\u002Fskill-tree --skill handoff","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002FSKILL.md",[47,53,57,61,65,69,75,79,83,87],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fbacklog.md","REFERENCE","参考文档",4993,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Freferences\u002Fbacklog.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fflow.md",3273,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Freferences\u002Fflow.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fhooks.md",4407,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Freferences\u002Fhooks.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Frationale.md",2944,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Freferences\u002Frationale.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftemplate.md",2651,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Freferences\u002Ftemplate.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fhandoff","SCRIPT","脚本",7619,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Fscripts\u002Fhandoff",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fhandoff_cli.py",28334,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Fscripts\u002Fhandoff_cli.py",{"path":80,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fhandoff_session_start.sh",4969,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Fscripts\u002Fhandoff_session_start.sh",{"path":84,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":85,"sourceHtmlUrl":86},"scripts\u002Ftest_handoff_wrapper.py",14210,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Fscripts\u002Ftest_handoff_wrapper.py",{"path":88,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Ftest_handoff.py",34526,"https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fhandoff\u002Fscripts\u002Ftest_handoff.py",[92,99,106,113,120,127],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M79SQ7Z4DXMYJECV1NTEP9WY","wait-what","Stop. Your plan\u002Fidea did not land. Re-pitch it.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M79SQ4WQB5YZ7Q2A87JVR219","verify","Verify before answering whether something works, still passes, is gone, is used, or is correct — and whenever the user says \"can you confirm\", \"are you sure\", \"did that actually work\", or reports something is \"still\" broken. Produces the answer plus the evidence that would have falsified it. A failed GitHub Actions run is skill-tree:debug-ci instead.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M79SQ0GKSM5891DKPXE8J7TZ","ui-designer","Design or restyle a web UI — landing pages, dashboards, docs sites, app chrome — or when the user asks why a site \"looks generic\", \"looks like a template\", or wants it to feel intentional. A running list of design lessons learned, applied as rules rather than suggestions.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fui-designer\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":19},"01M79SPVN5C0XYAXWBH9HD1YF1","two-axis-review","Two-axis review of changes since a fixed point (commit, tag, HEAD~N, or default HEAD~1): Standards (does the code follow this repo's conventions?) and Spec (does the code do what it should?). Axes run as parallel sub-agents so neither masks the other. Use when the user says \"review against the spec\", \"does this follow our conventions\", \"standards and spec review\", or \"two-axis review\". Not a correctness bug hunt — that's the built-in `\u002Fcode-review`.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Ftwo-axis-review\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":19},"01M79SPRT8GV1RPQ2VVR9K08BB","tui-screenshots","Use for generating or refreshing TUI screenshots for docs — \"regenerate the screenshots\", \"the README screenshots are stale\". Drives a Textual\u002FTUI app headlessly and exports SVG. Not for reading a user's screenshot — that is `screenshot`.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Ftui-screenshots\u002FSKILL.md",[],[],{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":19},"01M79SPNVJQ0WNWH7PBEM5Y463","to-tickets","Break a spec, plan, or conversation into tracer-bullet vertical-slice tickets with blocking edges — \"turn this into tickets\", \"break this down\", \"what's the work?\". Pairs with skill-tree:to-spec upstream and skill-tree:handoff downstream.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[]]