[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FNMZRDPCVKD7SWNWPMXENZ":3,"skill-same:01M6FNMZRDPCVKD7SWNWPMXENZ":66},{"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":23,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6FNMZRDPCVKD7SWNWPMXENZ","pickup",null,"Start-of-session context pickup. Reads the latest handoff file and resumes work where the last session left off. Run this at the start of a new session if a handoff file exists.","shenxingy\u002FClade","shenxingy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89829751?v=4","01M6CQXHTV3WQZJMG0JXD93MEK","Xingyu (Alex) Shen","01M6CQXHYCTGPJ5HD8Z7MD4Q5P",10,"MIT","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fpickup\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36],"handoff","run","file","start","new session","work","context","session","session context","last","latest","at","new","2026-11-10 10:12:30",false,"---\nname: pickup\ndescription: \"Start-of-session context pickup. Reads the latest handoff file and resumes work where the last session left off. Run this at the start of a new session if a handoff file exists.\"\n---\n\n# Clade for Codex\n\nThis workflow runs **directly in Codex**. Do not launch the `claude` CLI or\ndelegate the workflow to Clade's MCP bridge.\n\nCodex compatibility rules:\n\n- Plugin skills are namespaced. Invoke this workflow explicitly as\n  `$clade:pickup`; a bare `$name` does not select the installed Clade plugin.\n- Read the nearest `AGENTS.md` files for repository instructions. If a project\n  has only `CLAUDE.md`, treat it as legacy project guidance and read it too.\n- Store new Clade working state under `.clade\u002F` (or `~\u002F.clade\u002F` for personal\n  state). Existing legacy Claude state may be read for migration, but do not\n  create new vendor-specific state.\n- A `\u002Fskill-name` reference means the corresponding Codex\n  `$clade:skill-name` plugin skill, or the same workflow invoked naturally when\n  explicit skill invocation is not available.\n- Use Codex web, file, shell, image, and subagent capabilities when the source\n  workflow names a vendor-specific tool. If a capability is unavailable, use\n  the documented fallback instead of spawning another agent CLI.\n- Paths such as `\u003Cplugin-root>\u002F...` are relative to the installed Clade plugin\n  containing this `SKILL.md`; resolve that root before invoking a helper.\n\n## Canonical Clade workflow\n\n\u003Ccommand-metadata>\nname: pickup\ntrigger: user runs \u002Fpickup at start of new session, or after \u002Fhandoff\ncompletion-status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\n\u003C\u002Fcommand-metadata>\n\nResume work from the most recent handoff file.\n\n## Shared task pickup\n\nIf Git-common `clade\u002Ftasks\u002Fbinding.json` exists, first load `\u002Ftasks` and read\nits snapshot. A handoff's task reference must match this project and the live\nowner. Use a fresh session ID and claim ready work, or receive an explicit\nholder-guarded handoff; do not reuse the previous session's identity. Preserve\nthe original objective when choosing among ready tasks. A task blocked on a\ndependency is not runnable just because a handoff lists it as the next step.\nAn unavailable task backend blocks new claims, but existing work can still be\ncheckpointed. If no Markdown handoff exists, continue from the shared task\nrecord and acceptance criteria instead of stopping at Step 1.\n\n## Execution Steps\n\n### Step 1: Find Handoff File\n```bash\nls -t .clade\u002Fhandoff-*.md 2>\u002Fdev\u002Fnull | head -5\n```\n\nIf no files found: say \"No handoff file found. Starting fresh.\" and stop.\n\n### Step 2: Read + Parse\nRead the most recent handoff file completely.\n\nParse these sections:\n- **Goal**: the one-sentence objective\n- **Blocked**: check if \"none\" or has real blockers\n- **Hypotheses**: the `current` one with its Evidence and \"Drop it if\" line, the\n  `UNCONFIRMED` ones (not facts), and the `ruled-out` ones (do not re-try them\n  unless new evidence reopens one)\n- **Stop conditions & out of scope**: when the Goal counts as met, which result\n  means re-plan, and what the task must not widen into\n- **Next Steps**: the ordered list of PROPOSED actions — written by a session\n  already committed to its hypothesis, so they are proposals, not orders\n- **Meta**: branch, HEAD, uncommitted status, build status\n\nA v2 handoff (`STRUCTURED HANDOFF v2`) has no Hypotheses or Stop conditions\nsection. Take the assumption Next Steps #1 rests on as the current hypothesis,\nmark it UNCONFIRMED, and re-check it the same way in Step 5.\n\nA v3 handoff whose Hypotheses section is `- none — mechanical work` has no\nhypothesis to re-check. Step 5 still runs check 1 (on the files the Next Steps\nname, since no hypothesis cites any) and check 3 (stop conditions), skips check 2,\nand then acts as **Holds**.\n\n### Step 3: Verify Git State\n```bash\ngit branch --show-current\ngit status -sb\ngit merge-base --is-ancestor \u003CMeta.HEAD> HEAD; echo \"ancestor: $?\"\ngit log --oneline \u003CMeta.HEAD>..HEAD\n```\n\nIf current branch doesn't match handoff Meta.Branch: warn the user but continue.\n\n`\u003CMeta.HEAD>..HEAD` lists every commit since the handoff, however many — a fixed\n`-10` window misses the 11th. Work that landed after the handoff may have moved\nthe ground under its hypothesis; Step 5 checks whether it did, by content.\n\n- **ancestor: 0** — the handoff's HEAD is still in this history; the log is the\n  complete list of what landed since (empty when nothing did).\n- **ancestor: 1** — the commit is in this clone but not in this history (rebased,\n  squash-merged, or another branch), so the log is not a list of what landed.\n  Content still compares: Step 5's check 1 diffs the cited files from Meta.HEAD to\n  HEAD, and a squash merge of the handoff's own branch leaves that diff empty when\n  they are unchanged. A changed history alone is not evidence against the hypothesis.\n- **ancestor: 128** — this clone does not have the commit. If the handoff came\n  from another clone, `git fetch` once and re-run. Still 128: nothing here can say\n  what changed since the handoff, so check 1 cannot run, and Step 5 takes the\n  Cannot-be-checked path unless another check contradicts the hypothesis.\n\nA v2 handoff has no Meta.HEAD: run `git log --oneline -10` instead and compare it\nwith the handoff's Done list.\n\n### Step 4: Display Briefing (max 20 lines)\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nResuming: {handoff date} ({X hours\u002Fdays ago})\nGoal: {Goal section content}\n\nDone: {count of Done ✅ items}\nIn Progress: {In Progress items if any}\nBlocked: {Blocked content OR \"none\"}\nHypothesis: {current hypothesis, one line} [{status in the handoff}]\n\nBranch: {branch}  Build: {passing|failing|unknown}\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nProposed next (re-checked in Step 5):\n→ {Next Steps #1}\n→ {Next Steps #2}\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n### Step 5: Re-check the hypothesis, then resume\n\nExecuting the last session's Next Steps as orders carries its commitment to a\nhypothesis across the reset, even when the evidence has since turned (context\ninertia, Breunig, 2026-10-14). So test the ground under them before the first edit.\n\n**If Blocked has items**: List each blocker clearly. Ask user to resolve before continuing autonomously.\n\n**If handoff is >48 hours old**: Flag the age prominently. Ask user to confirm goal is still current before proceeding.\n\n**Once nothing is blocked (and an old handoff's goal is confirmed), re-check first.** Read-only and a few commands — not a re-investigation:\n1. **Repository**: do the files the current hypothesis cites still say what its\n   Evidence says? `git diff --stat \u003CMeta.HEAD> HEAD -- \u003Ccited paths>` compares them\n   by content, so it answers for ancestor 0 and 1 alike; read any hunk it lists.\n   A v2 handoff: look at the commits from Step 3 that are not in its Done list.\n   If Step 3 still got 128, this check cannot run: say so.\n2. **Verified facts**: re-run the cheapest check its Evidence or \"Drop it if\" line\n   names — one test, one grep, one command. A fact the handoff marks \"inferred\" is\n   not verified. A re-run whose output no longer matches what its Evidence\n   records takes the Contradicted branch, even when its drop condition is not met.\n3. **Stop conditions**: if \"Done when\" is already met, report that and stop — there\n   is nothing to resume. Drop any proposed step that falls under \"Out of scope\".\n\nPrint one line — `Re-check: {H} holds | contradicted | not re-checked — {evidence}`,\nor `Re-check: no hypothesis (mechanical work) — {evidence}` — and act on it.\nContradicted wins: one check that contradicts decides, even when another could not run.\n\n- **Holds** (the check supports it, finds nothing against it, or there is no\n  hypothesis because the work is mechanical): start the first\n  Next Step that still follows from it. Do NOT ask \"shall I proceed?\" — just start.\n- **Contradicted** (a \"Drop it if\" or \"Stop and re-plan if\" condition is met, a\n  cited file no longer says what its Evidence says, or check 2's re-run no longer\n  matches what its Evidence records): do not execute the old Next Steps.\n  Record the hypothesis on the evidence you just saw — ruled-out when its \"Drop it if\"\n  is met, otherwise UNCONFIRMED — so the next \u002Fhandoff carries it. Re-plan from the\n  Goal, the verified facts and the remaining hypotheses, state the new first step in\n  one line and start it — still without asking. Ask only if the re-plan would change\n  the Goal itself or take a destructive step.\n- **Cannot be checked cheaply** (another host, credentials, a long run, or Step 3\n  still got 128): proceed with it UNCONFIRMED, say \"not re-checked: {why}\", and\n  prefer a first step that tests it.\n\n## Completion Status\n\n- **✅ DONE**: Handoff loaded, hypothesis re-checked, and resumed (or blockers presented)\n- **⚠ DONE_WITH_CONCERNS**: Loaded but git state doesn't match, handoff >48h old, or the re-check contradicted the handoff's hypothesis and the plan changed\n- **❌ BLOCKED**: No handoff file found, or file unreadable\n- **❓ NEEDS_CONTEXT**: Ask via AskUserQuestion\n\n## 3-Strike Rule\nIf you fail to complete a step 3 times: write failure details to `.clade\u002Fblockers.md` and stop.\n\n## Delivery completion\n\nIf this workflow changes files or external state:\n\n- Inspect the real final state before responding, including `git status` for a\n  repository task.\n- Never report `DONE` while task-owned changes are uncommitted. Use or continue\n  `$clade:delivery` and create a repository-compliant checkpoint or preserve\n  the work when committing is unavailable.\n- When the user request or trusted repository policy makes publication,\n  deployment, or live verification part of the task, do not silently downgrade\n  the result to local-only work.\n- If a required delivery transition lacks authority, credentials, a destination,\n  or reachable external state, report `BLOCKED` or `NEEDS_CONTEXT` rather than\n  appending a \"not committed\u002Fpushed\u002Fdeployed\" caveat after `DONE`.\n","# Clade for Codex\n\nThis workflow runs **directly in Codex**. Do not launch the `claude` CLI or\ndelegate the workflow to Clade's MCP bridge.\n\nCodex compatibility rules:\n\n- Plugin skills are namespaced. Invoke this workflow explicitly as\n  `$clade:pickup`; a bare `$name` does not select the installed Clade plugin.\n- Read the nearest `AGENTS.md` files for repository instructions. If a project\n  has only `CLAUDE.md`, treat it as legacy project guidance and read it too.\n- Store new Clade working state under `.clade\u002F` (or `~\u002F.clade\u002F` for personal\n  state). Existing legacy Claude state may be read for migration, but do not\n  create new vendor-specific state.\n- A `\u002Fskill-name` reference means the corresponding Codex\n  `$clade:skill-name` plugin skill, or the same workflow invoked naturally when\n  explicit skill invocation is not available.\n- Use Codex web, file, shell, image, and subagent capabilities when the source\n  workflow names a vendor-specific tool. If a capability is unavailable, use\n  the documented fallback instead of spawning another agent CLI.\n- Paths such as `\u003Cplugin-root>\u002F...` are relative to the installed Clade plugin\n  containing this `SKILL.md`; resolve that root before invoking a helper.\n\n## Canonical Clade workflow\n\n\u003Ccommand-metadata>\nname: pickup\ntrigger: user runs \u002Fpickup at start of new session, or after \u002Fhandoff\ncompletion-status: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\n\u003C\u002Fcommand-metadata>\n\nResume work from the most recent handoff file.\n\n## Shared task pickup\n\nIf Git-common `clade\u002Ftasks\u002Fbinding.json` exists, first load `\u002Ftasks` and read\nits snapshot. A handoff's task reference must match this project and the live\nowner. Use a fresh session ID and claim ready work, or receive an explicit\nholder-guarded handoff; do not reuse the previous session's identity. Preserve\nthe original objective when choosing among ready tasks. A task blocked on a\ndependency is not runnable just because a handoff lists it as the next step.\nAn unavailable task backend blocks new claims, but existing work can still be\ncheckpointed. If no Markdown handoff exists, continue from the shared task\nrecord and acceptance criteria instead of stopping at Step 1.\n\n## Execution Steps\n\n### Step 1: Find Handoff File\n```bash\nls -t .clade\u002Fhandoff-*.md 2>\u002Fdev\u002Fnull | head -5\n```\n\nIf no files found: say \"No handoff file found. Starting fresh.\" and stop.\n\n### Step 2: Read + Parse\nRead the most recent handoff file completely.\n\nParse these sections:\n- **Goal**: the one-sentence objective\n- **Blocked**: check if \"none\" or has real blockers\n- **Hypotheses**: the `current` one with its Evidence and \"Drop it if\" line, the\n  `UNCONFIRMED` ones (not facts), and the `ruled-out` ones (do not re-try them\n  unless new evidence reopens one)\n- **Stop conditions & out of scope**: when the Goal counts as met, which result\n  means re-plan, and what the task must not widen into\n- **Next Steps**: the ordered list of PROPOSED actions — written by a session\n  already committed to its hypothesis, so they are proposals, not orders\n- **Meta**: branch, HEAD, uncommitted status, build status\n\nA v2 handoff (`STRUCTURED HANDOFF v2`) has no Hypotheses or Stop conditions\nsection. Take the assumption Next Steps #1 rests on as the current hypothesis,\nmark it UNCONFIRMED, and re-check it the same way in Step 5.\n\nA v3 handoff whose Hypotheses section is `- none — mechanical work` has no\nhypothesis to re-check. Step 5 still runs check 1 (on the files the Next Steps\nname, since no hypothesis cites any) and check 3 (stop conditions), skips check 2,\nand then acts as **Holds**.\n\n### Step 3: Verify Git State\n```bash\ngit branch --show-current\ngit status -sb\ngit merge-base --is-ancestor \u003CMeta.HEAD> HEAD; echo \"ancestor: $?\"\ngit log --oneline \u003CMeta.HEAD>..HEAD\n```\n\nIf current branch doesn't match handoff Meta.Branch: warn the user but continue.\n\n`\u003CMeta.HEAD>..HEAD` lists every commit since the handoff, however many — a fixed\n`-10` window misses the 11th. Work that landed after the handoff may have moved\nthe ground under its hypothesis; Step 5 checks whether it did, by content.\n\n- **ancestor: 0** — the handoff's HEAD is still in this history; the log is the\n  complete list of what landed since (empty when nothing did).\n- **ancestor: 1** — the commit is in this clone but not in this history (rebased,\n  squash-merged, or another branch), so the log is not a list of what landed.\n  Content still compares: Step 5's check 1 diffs the cited files from Meta.HEAD to\n  HEAD, and a squash merge of the handoff's own branch leaves that diff empty when\n  they are unchanged. A changed history alone is not evidence against the hypothesis.\n- **ancestor: 128** — this clone does not have the commit. If the handoff came\n  from another clone, `git fetch` once and re-run. Still 128: nothing here can say\n  what changed since the handoff, so check 1 cannot run, and Step 5 takes the\n  Cannot-be-checked path unless another check contradicts the hypothesis.\n\nA v2 handoff has no Meta.HEAD: run `git log --oneline -10` instead and compare it\nwith the handoff's Done list.\n\n### Step 4: Display Briefing (max 20 lines)\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nResuming: {handoff date} ({X hours\u002Fdays ago})\nGoal: {Goal section content}\n\nDone: {count of Done ✅ items}\nIn Progress: {In Progress items if any}\nBlocked: {Blocked content OR \"none\"}\nHypothesis: {current hypothesis, one line} [{status in the handoff}]\n\nBranch: {branch}  Build: {passing|failing|unknown}\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nProposed next (re-checked in Step 5):\n→ {Next Steps #1}\n→ {Next Steps #2}\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n### Step 5: Re-check the hypothesis, then resume\n\nExecuting the last session's Next Steps as orders carries its commitment to a\nhypothesis across the reset, even when the evidence has since turned (context\ninertia, Breunig, 2026-10-14). So test the ground under them before the first edit.\n\n**If Blocked has items**: List each blocker clearly. Ask user to resolve before continuing autonomously.\n\n**If handoff is >48 hours old**: Flag the age prominently. Ask user to confirm goal is still current before proceeding.\n\n**Once nothing is blocked (and an old handoff's goal is confirmed), re-check first.** Read-only and a few commands — not a re-investigation:\n1. **Repository**: do the files the current hypothesis cites still say what its\n   Evidence says? `git diff --stat \u003CMeta.HEAD> HEAD -- \u003Ccited paths>` compares them\n   by content, so it answers for ancestor 0 and 1 alike; read any hunk it lists.\n   A v2 handoff: look at the commits from Step 3 that are not in its Done list.\n   If Step 3 still got 128, this check cannot run: say so.\n2. **Verified facts**: re-run the cheapest check its Evidence or \"Drop it if\" line\n   names — one test, one grep, one command. A fact the handoff marks \"inferred\" is\n   not verified. A re-run whose output no longer matches what its Evidence\n   records takes the Contradicted branch, even when its drop condition is not met.\n3. **Stop conditions**: if \"Done when\" is already met, report that and stop — there\n   is nothing to resume. Drop any proposed step that falls under \"Out of scope\".\n\nPrint one line — `Re-check: {H} holds | contradicted | not re-checked — {evidence}`,\nor `Re-check: no hypothesis (mechanical work) — {evidence}` — and act on it.\nContradicted wins: one check that contradicts decides, even when another could not run.\n\n- **Holds** (the check supports it, finds nothing against it, or there is no\n  hypothesis because the work is mechanical): start the first\n  Next Step that still follows from it. Do NOT ask \"shall I proceed?\" — just start.\n- **Contradicted** (a \"Drop it if\" or \"Stop and re-plan if\" condition is met, a\n  cited file no longer says what its Evidence says, or check 2's re-run no longer\n  matches what its Evidence records): do not execute the old Next Steps.\n  Record the hypothesis on the evidence you just saw — ruled-out when its \"Drop it if\"\n  is met, otherwise UNCONFIRMED — so the next \u002Fhandoff carries it. Re-plan from the\n  Goal, the verified facts and the remaining hypotheses, state the new first step in\n  one line and start it — still without asking. Ask only if the re-plan would change\n  the Goal itself or take a destructive step.\n- **Cannot be checked cheaply** (another host, credentials, a long run, or Step 3\n  still got 128): proceed with it UNCONFIRMED, say \"not re-checked: {why}\", and\n  prefer a first step that tests it.\n\n## Completion Status\n\n- **✅ DONE**: Handoff loaded, hypothesis re-checked, and resumed (or blockers presented)\n- **⚠ DONE_WITH_CONCERNS**: Loaded but git state doesn't match, handoff >48h old, or the re-check contradicted the handoff's hypothesis and the plan changed\n- **❌ BLOCKED**: No handoff file found, or file unreadable\n- **❓ NEEDS_CONTEXT**: Ask via AskUserQuestion\n\n## 3-Strike Rule\nIf you fail to complete a step 3 times: write failure details to `.clade\u002Fblockers.md` and stop.\n\n## Delivery completion\n\nIf this workflow changes files or external state:\n\n- Inspect the real final state before responding, including `git status` for a\n  repository task.\n- Never report `DONE` while task-owned changes are uncommitted. Use or continue\n  `$clade:delivery` and create a repository-compliant checkpoint or preserve\n  the work when committing is unavailable.\n- When the user request or trusted repository policy makes publication,\n  deployment, or live verification part of the task, do not silently downgrade\n  the result to local-only work.\n- If a required delivery transition lacks authority, credentials, a destination,\n  or reachable external state, report `BLOCKED` or `NEEDS_CONTEXT` rather than\n  appending a \"not committed\u002Fpushed\u002Fdeployed\" caveat after `DONE`.\n",{"name":5,"description":7},"main","25302dbcb683029b8a4d75325ae7758944b27114","plugins\u002Fclade\u002Fskills\u002Fpickup",6,"https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade","https:\u002F\u002Falexshen.dev\u002Fen\u002Fblog\u002Fclade","https:\u002F\u002Fgithub.com\u002Fshenxingy","https:\u002F\u002Falexshen.dev\u002F","Founding Engineer @ Scam AI | ECE @ Duke University | Data Science @ Duke Kunshan University","2026-11-13 19:38:31",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add shenxingy\u002FClade --skill pickup",{"tool":58,"command":59},"bunx","bunx skills add shenxingy\u002FClade --skill pickup",{"tool":61,"command":62},"pnpm","pnpm dlx skills add shenxingy\u002FClade --skill pickup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fpickup\u002FSKILL.md",true,[],[67,86,118,139,164,179],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":74,"publishedAt":37},"01M6FNPBA3494GF2W7V4MMAKG3","worktree","Create or inspect runtime-adaptive isolated Git workspaces with explicit ownership and delivery routing","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fworktree\u002FSKILL.md",[73],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[69,75,76,77,78,79,80,81,82,83,84,85],"adaptive","inspect","with","ownership","delivery routing","runtime","delivery","workspaces","git","routing","create",{"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":98,"publishedAt":37},"01M6FNP75BY8CS006EWGN29FM0","web-search","Route online research and URL reading to native tools or TinyFish MCP\u002FAPI; prepare targeted requests, handle progress and failures, and check returned evidence. Applies to web search, fetching, and bulk collection; excludes repository\u002Ffile search.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fweb-search\u002FSKILL.md",[92,93],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[99,100,101,102,26,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117],"web search","search","web","repository","research","MCP","requests","collection","reading","URL","native","bulk","progress","file search","route","tinyfish","evidence","check","api",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":125,"publishedAt":37},"01M6FNP2616DRTZRSZJQM3HPHY","verify","Verify project behavior anchors — compilation, tests, and interaction checks after autonomous runs. NOT the Codex built-in \u002Fverify (which runs the app to observe a single change working) — this one walks the AGENTS.md \"Features (Behavior Anchors)\" list.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fverify\u002FSKILL.md",[124],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[120,126,127,128,129,130,131,132,133,134,135,136,137,138],"app","single","features","which","interaction","tests","project","observe","autonomous","behavior","list","change","codex",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":146,"publishedAt":37},"01M6FNNX95R9H29BNERFY15704","tasks","Coordinate dependency-aware project tasks across independent Codex, Codex, Kimi and human sessions using Beads. Use for shared plans, claiming work, task handoffs, acceptance and agent monitoring snapshots.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Ftasks\u002FSKILL.md",[145],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[141,147,148,29,132,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,138],"for","plans","shared","across","human","task","coordinate","kimi","snapshots","agent monitoring","dependency","use","using beads","beads","monitoring","acceptance","sessions",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":37},"01M6FNNTAD1BCZX5Q9TC55MZCH","sync","End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run \u002Fcommit after to commit everything)","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fsync\u002FSKILL.md",[170],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[166,31,25,172,173,174,175,176,111,177,178],"documentation","commit","only","documentation sync","updates","end","todo",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":186,"publishedAt":37},"01M6FNNPTR5H23MD3849E66WYA","status","Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime\u002Fprovider\u002Fmodel, or stuck-work checks.","https:\u002F\u002Fgithub.com\u002Fshenxingy\u002FClade\u002Fblob\u002Fmain\u002Fplugins\u002Fclade\u002Fskills\u002Fstatus\u002FSKILL.md",[185],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[181,80,187,188,147,176,189,190,111,191,81,192,193,158,194,29,195,196,83,197],"running","limits","usage","now","active","show","provider","snapshot","model","execution","identity"]