[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E3JV0QTQ7MWJAFB1TWH2DX":3,"skill-same:01M7E3JV0QTQ7MWJAFB1TWH2DX":71},{"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":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M7E3JV0QTQ7MWJAFB1TWH2DX","kimi-delegate",null,"Delegate coding tasks to the Kimi Code CLI (`kimi`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","Mr-Nobody-Anonymous\u002FAll-skills","Mr-Nobody-Anonymous","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184253119?v=4","01M7AEXFJHKTYQW5R0ZCQQTWFV","anonymous","01M7C00M3GQR4QKP9GZA42GFAK",0,"MIT","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: kimi-delegate\ndescription: Delegate coding tasks to the Kimi Code CLI (`kimi`) only when the user\n  explicitly requests it, while the orchestrator retains review and landing responsibility.\nrisk: critical\ncategory: agent-orchestration\nsource: https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills\nsource_repo: amElnagdy\u002Fdelegate-skills\nsource_type: community\ndate_added: '2026-08-26'\nlicense: MIT\nlicense_source: https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills\u002Fblob\u002Fmaster\u002FLICENSE\nmetadata:\n  version: 0.5.0\n---\n# Kimi Delegate\n\n## When to Use\n\n- You want to delegate a bounded coding task to a separate `kimi` implementer (`Kimi Code`) and then review its diff yourself.\n- The user explicitly asked for delegation to this implementer.\n\nYou are the **orchestrator**. Hand a bounded coding task to a separate **implementer** - the Kimi Code\nCLI - then review what it produced and land it yourself. You write the brief and own the judgment;\nKimi does the typing in its own session; you verify and commit.\n\nThe loop needs only a shell command and file access, so any comparable orchestrator can drive it.\n\n## When NOT to use this\n\n- The task is small enough to do inline; delegation overhead is not worth it.\n- The `kimi` CLI is not installed or authenticated.\n- You need a CLI-enforced read-only implementer. Headless Kimi has no read-only mode.\n\n## Prerequisites (check once)\n\n1. Install Kimi Code with `brew install kimi-code` on macOS\u002FLinux, or use the native installer from\n   the [official Kimi Code documentation](https:\u002F\u002Fmoonshotai.github.io\u002Fkimi-code\u002Fen\u002F).\n2. Authenticate with `kimi login` (device-code flow, no TUI), or use `\u002Flogin` in the TUI.\n3. Confirm `kimi --version` succeeds.\n4. Work in, or point `--cd` at, the target git repository.\n\n## Choose the model alias\n\nKimi uses `default_model` from its `config.toml` when `--model` is omitted. To choose another model\nalias, pass `--model \u003Calias from your kimi config>`. Model aliases are user-defined config keys; use\none the human has configured rather than inventing one.\n\n## The loop\n\nRun these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.\n\n### 1. Write the brief\n\nKimi sees only the text you send plus what it can inspect in the workspace - no chat history or shared\ncontext. Include the goal, current state, what to change, what to leave untouched, the project's\n**actual** gates, and a report contract. Tell Kimi not to commit. Keep one task per brief. See\n[references\u002Fwriting-the-brief.md](references\u002Fwriting-the-brief.md).\n\n### 2. Dispatch\n\nUse the bundled helper. It wraps Kimi's headless prompt mode, captures the structured event stream,\nand writes `result.json`. (`\u003Cskill-dir>` is the installed folder containing this `SKILL.md`.)\n\n```bash\nnode \"\u003Cskill-dir>\u002Fscripts\u002Frelay.mjs\" --brief brief.txt --cd \u002Fpath\u002Fto\u002Frepo\n# choose a configured model alias:       add --model \u003Calias from your kimi config>\n# resume the most recent session:        add --resume-last  (delta brief only)\n# resume a specific session:             add --session \u003Cid> (delta brief only)\n# hard time limit (watchdog):            add --timeout 2h  (the 30m default suits short runs; implementation briefs routinely need 1-2h)\n# see all options:                       node ...\u002Frelay.mjs --help\n```\n\nThe child process's cwd pins the workspace. Use repeatable `--add-dir` flags only for extra workspace\ndirectories. The relay writes artifacts under the system temp dir by default and never commits. See\n[references\u002Fdispatch-and-poll.md](references\u002Fdispatch-and-poll.md).\n\n### 3. Wait for completion\n\nThe helper blocks until Kimi finishes. Run it with the orchestrator's background-command facility, or\nbackground it in the shell and poll for `result.json`. A pre-run usage error exits 2 and writes no\nresult; a missing `kimi` exits 127 and writes `status: \"kimi_unavailable\"`.\n\nTrust process state and the working tree over a progress display. Completion means the process exited\nand `result.json` exists. Kimi's full report is the `finalMessage` field in `result.json` (also printed\nin full on stdout between the report markers).\n\n### 4. Review - do not trust the self-report\n\nTreat Kimi's final message and gate claims as claims:\n\n- Re-run the project's gates yourself.\n- Read the diff against the brief, starting with `touchedFiles`.\n- Run relevant guard skills if installed.\n- Round-trip migrations and grep for dangling references after removals or renames.\n\nSee [references\u002Freview-and-land.md](references\u002Freview-and-land.md).\n\n### 5. Land it\n\nThe implementer edits the working tree; **the orchestrator commits.** Commit only after the gates pass\nand the diff holds. If rework is needed, send a delta brief with `--resume-last` or `--session \u003Cid>`,\nthen review again.\n\n## Autonomy and permissions\n\nIn headless `-p` mode, Kimi always runs in **auto permission mode** and never asks for approval. Kimi\nrejects `--prompt` combined with `--yolo`, `--auto`, or `--plan`, so the relay passes none of them and\noffers no `--read-only` or `--full-access` option. There is no CLI-enforced read-only mode: inspect\n`touchedFiles` and the diff after every run. That diff, not a flag, is the guarantee of what changed.\n\n## Authorization model\n\nDelegation is something the human opts into. Once they have (\"run this queue\", \"proceed\"), committing\nverified, gate-passing work is the agreed contract. Two limits remain: **surface, don't absorb**\n(report Kimi's design decisions, defensible-but-unasked turns, and non-blocking nitpicks) and **stop\nfor scope changes** (if correct completion needs going beyond the brief, ask instead of expanding the\nmandate). See [references\u002Freview-and-land.md](references\u002Freview-and-land.md).\n\n## References\n\n- [references\u002Fwriting-the-brief.md](references\u002Fwriting-the-brief.md) - structure, report contract,\n  real gates, argv delivery, and delta briefs.\n- [references\u002Fdispatch-and-poll.md](references\u002Fdispatch-and-poll.md) - flags, artifacts,\n  `result.json`, polling, and failure recovery.\n- [references\u002Freview-and-land.md](references\u002Freview-and-land.md) - review checklist, commit boundary,\n  and rework through Kimi sessions.\n- [references\u002Fmulti-task-queues.md](references\u002Fmulti-task-queues.md) - sequential queues, constraint\n  carry-forward, progress tracking, and the final coherence pass.\n\n\n## Limitations\n\n- Docs-only import — executable `scripts\u002Frelay.mjs` not included; see upstream for full runtime. Requires `kimi` CLI, Node 18+, git.\n- Relay never commits — it only returns structured result JSON; you review and land the commit.\n\n> Adapted from [amElnagdy\u002Fdelegate-skills](https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills) (MIT) — docs-only, runtime not bundled.\n","# Kimi Delegate\n\n## When to Use\n\n- You want to delegate a bounded coding task to a separate `kimi` implementer (`Kimi Code`) and then review its diff yourself.\n- The user explicitly asked for delegation to this implementer.\n\nYou are the **orchestrator**. Hand a bounded coding task to a separate **implementer** - the Kimi Code\nCLI - then review what it produced and land it yourself. You write the brief and own the judgment;\nKimi does the typing in its own session; you verify and commit.\n\nThe loop needs only a shell command and file access, so any comparable orchestrator can drive it.\n\n## When NOT to use this\n\n- The task is small enough to do inline; delegation overhead is not worth it.\n- The `kimi` CLI is not installed or authenticated.\n- You need a CLI-enforced read-only implementer. Headless Kimi has no read-only mode.\n\n## Prerequisites (check once)\n\n1. Install Kimi Code with `brew install kimi-code` on macOS\u002FLinux, or use the native installer from\n   the [official Kimi Code documentation](https:\u002F\u002Fmoonshotai.github.io\u002Fkimi-code\u002Fen\u002F).\n2. Authenticate with `kimi login` (device-code flow, no TUI), or use `\u002Flogin` in the TUI.\n3. Confirm `kimi --version` succeeds.\n4. Work in, or point `--cd` at, the target git repository.\n\n## Choose the model alias\n\nKimi uses `default_model` from its `config.toml` when `--model` is omitted. To choose another model\nalias, pass `--model \u003Calias from your kimi config>`. Model aliases are user-defined config keys; use\none the human has configured rather than inventing one.\n\n## The loop\n\nRun these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.\n\n### 1. Write the brief\n\nKimi sees only the text you send plus what it can inspect in the workspace - no chat history or shared\ncontext. Include the goal, current state, what to change, what to leave untouched, the project's\n**actual** gates, and a report contract. Tell Kimi not to commit. Keep one task per brief. See\n[references\u002Fwriting-the-brief.md](references\u002Fwriting-the-brief.md).\n\n### 2. Dispatch\n\nUse the bundled helper. It wraps Kimi's headless prompt mode, captures the structured event stream,\nand writes `result.json`. (`\u003Cskill-dir>` is the installed folder containing this `SKILL.md`.)\n\n```bash\nnode \"\u003Cskill-dir>\u002Fscripts\u002Frelay.mjs\" --brief brief.txt --cd \u002Fpath\u002Fto\u002Frepo\n# choose a configured model alias:       add --model \u003Calias from your kimi config>\n# resume the most recent session:        add --resume-last  (delta brief only)\n# resume a specific session:             add --session \u003Cid> (delta brief only)\n# hard time limit (watchdog):            add --timeout 2h  (the 30m default suits short runs; implementation briefs routinely need 1-2h)\n# see all options:                       node ...\u002Frelay.mjs --help\n```\n\nThe child process's cwd pins the workspace. Use repeatable `--add-dir` flags only for extra workspace\ndirectories. The relay writes artifacts under the system temp dir by default and never commits. See\n[references\u002Fdispatch-and-poll.md](references\u002Fdispatch-and-poll.md).\n\n### 3. Wait for completion\n\nThe helper blocks until Kimi finishes. Run it with the orchestrator's background-command facility, or\nbackground it in the shell and poll for `result.json`. A pre-run usage error exits 2 and writes no\nresult; a missing `kimi` exits 127 and writes `status: \"kimi_unavailable\"`.\n\nTrust process state and the working tree over a progress display. Completion means the process exited\nand `result.json` exists. Kimi's full report is the `finalMessage` field in `result.json` (also printed\nin full on stdout between the report markers).\n\n### 4. Review - do not trust the self-report\n\nTreat Kimi's final message and gate claims as claims:\n\n- Re-run the project's gates yourself.\n- Read the diff against the brief, starting with `touchedFiles`.\n- Run relevant guard skills if installed.\n- Round-trip migrations and grep for dangling references after removals or renames.\n\nSee [references\u002Freview-and-land.md](references\u002Freview-and-land.md).\n\n### 5. Land it\n\nThe implementer edits the working tree; **the orchestrator commits.** Commit only after the gates pass\nand the diff holds. If rework is needed, send a delta brief with `--resume-last` or `--session \u003Cid>`,\nthen review again.\n\n## Autonomy and permissions\n\nIn headless `-p` mode, Kimi always runs in **auto permission mode** and never asks for approval. Kimi\nrejects `--prompt` combined with `--yolo`, `--auto`, or `--plan`, so the relay passes none of them and\noffers no `--read-only` or `--full-access` option. There is no CLI-enforced read-only mode: inspect\n`touchedFiles` and the diff after every run. That diff, not a flag, is the guarantee of what changed.\n\n## Authorization model\n\nDelegation is something the human opts into. Once they have (\"run this queue\", \"proceed\"), committing\nverified, gate-passing work is the agreed contract. Two limits remain: **surface, don't absorb**\n(report Kimi's design decisions, defensible-but-unasked turns, and non-blocking nitpicks) and **stop\nfor scope changes** (if correct completion needs going beyond the brief, ask instead of expanding the\nmandate). See [references\u002Freview-and-land.md](references\u002Freview-and-land.md).\n\n## References\n\n- [references\u002Fwriting-the-brief.md](references\u002Fwriting-the-brief.md) - structure, report contract,\n  real gates, argv delivery, and delta briefs.\n- [references\u002Fdispatch-and-poll.md](references\u002Fdispatch-and-poll.md) - flags, artifacts,\n  `result.json`, polling, and failure recovery.\n- [references\u002Freview-and-land.md](references\u002Freview-and-land.md) - review checklist, commit boundary,\n  and rework through Kimi sessions.\n- [references\u002Fmulti-task-queues.md](references\u002Fmulti-task-queues.md) - sequential queues, constraint\n  carry-forward, progress tracking, and the final coherence pass.\n\n\n## Limitations\n\n- Docs-only import — executable `scripts\u002Frelay.mjs` not included; see upstream for full runtime. Requires `kimi` CLI, Node 18+, git.\n- Relay never commits — it only returns structured result JSON; you review and land the commit.\n\n> Adapted from [amElnagdy\u002Fdelegate-skills](https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills) (MIT) — docs-only, runtime not bundled.\n",{"name":5,"risk":24,"source":25,"license":15,"category":26,"metadata":27,"date_added":29,"description":7,"source_repo":30,"source_type":31,"license_source":32},"critical","https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills","agent-orchestration",{"version":28},"0.5.0","2026-08-26","amElnagdy\u002Fdelegate-skills","community","https:\u002F\u002Fgithub.com\u002FamElnagdy\u002Fdelegate-skills\u002Fblob\u002Fmaster\u002FLICENSE","main","2d1750717747097b602acf30bd09a7cbd4b4c6ea","awesome_skills\u002Fagent-orchestration\u002Fkimi-delegate","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous","2026-11-09 11:45:36",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill kimi-delegate",{"tool":45,"command":46},"bunx","bunx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill kimi-delegate",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Mr-Nobody-Anonymous\u002FAll-skills --skill kimi-delegate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002FSKILL.md",true,[53,59,63,67],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fdispatch-and-poll.md","REFERENCE","参考文档",7451,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002Freferences\u002Fdispatch-and-poll.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fmulti-task-queues.md",2314,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002Freferences\u002Fmulti-task-queues.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Freview-and-land.md",4478,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002Freferences\u002Freview-and-land.md",{"path":68,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fwriting-the-brief.md",5588,"https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fagent-orchestration\u002Fkimi-delegate\u002Freferences\u002Fwriting-the-brief.md",[72,80,87,94,101,108],{"skillNo":73,"name":74,"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":79},"01M7FFFZPC2025JQQHPHDX154J","dei-assessment","Assess diversity, equity, and inclusion with metrics. TRIGGERS - Use when user needs help with dei-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-assessment\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"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":79},"01M7FFFWN8H4WA7A6Y398QKB6J","dei-action-plan","Create DEI action plans with goals and initiatives. TRIGGERS - Use when user needs help with dei-action-plan related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fdei-action-plan\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":79},"01M7FFFSHTM0QZRVZ2NRJTJ0PY","culture-fit-assessment","Design culture add assessment processes. TRIGGERS - Use when user needs help with culture-fit-assessment related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fculture-fit-assessment\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":79},"01M7FFFMA12RKEQA38KHJSXXPS","cowork-to-code-bridge","Use an already-installed, independently verified cowork-to-code bridge to run narrowly approved actions on the user's own macOS, Linux, or WSL2 machine through a local file queue.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcowork-to-code-bridge\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":79},"01M7FFFH1F6M8YRGW5V487GH1K","counter-offer-response","Draft counter-offer responses for retention. TRIGGERS - Use when user needs help with counter-offer-response related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcounter-offer-response\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":79},"01M7FFFDGEHV8Y7J9N40HZXW52","continuous-feedback-system","Design continuous feedback systems. TRIGGERS - Use when user needs help with continuous-feedback-system related tasks.","https:\u002F\u002Fgithub.com\u002FMr-Nobody-Anonymous\u002FAll-skills\u002Fblob\u002Fmain\u002Fawesome_skills\u002Fhr-people\u002Fcontinuous-feedback-system\u002FSKILL.md",[],[]]