[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AWD206HYCTMPNFK30VZH7":3,"skill-same:01M71AWD206HYCTMPNFK30VZH7":88},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":67,"repositoryHtmlUrl":68,"repositoryHomepageUrl":69,"ownerHtmlUrl":70,"ownerBlogUrl":71,"ownerDescription":72,"updatedAt":73,"install":74,"resources":87},"01M71AWD206HYCTMPNFK30VZH7","cli-for-agent",null,"Design or review CLIs so coding agents can run them reliably: non-interactive\nflags first, layered --help with real copy-pasteable examples, stdin\u002Fpipeline\nsupport, fail-fast errors that include a correct invocation, idempotency,\n--dry-run\u002F--yes for destructive actions, and machine-useful success output.\nUse when building a CLI, adding commands or subcommands, writing --help\ntext, or when asked for an \"agent-friendly CLI\". Not for GUIs, TUIs, or\nlibrary APIs (no CLI surface to design).","ariadoss\u002Fsuperskills","ariadoss","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F414341?v=4","01M71AC7383PT6JCRZSQJ4AVTM","Danilo Stern-Sapad","01M71AC73Y7NTBTJ9KQYNENRRE",12,"MIT","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fcli-for-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"for","cli for agent","cli","commands","edit","write","read","run","support","useful","text","dry","review","Bash","when","writing","design","errors","actions","pipeline","2026-11-10 10:12:30",false,"---\nname: cli-for-agent\nversion: 1.0.0\ndescription: |\n  Design or review CLIs so coding agents can run them reliably: non-interactive\n  flags first, layered --help with real copy-pasteable examples, stdin\u002Fpipeline\n  support, fail-fast errors that include a correct invocation, idempotency,\n  --dry-run\u002F--yes for destructive actions, and machine-useful success output.\n  Use when building a CLI, adding commands or subcommands, writing --help\n  text, or when asked for an \"agent-friendly CLI\". Not for GUIs, TUIs, or\n  library APIs (no CLI surface to design).\nmetadata.upstream: https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins (cli-for-agent\u002Fskills\u002Fcli-for-agents, MIT)\ntriggers:\n  - agent-friendly cli\n  - cli for agents\n  - build a cli\n  - add a subcommand\n  - write --help\nallowed-tools:\n  - Bash\n  - Read\n  - Write\n  - Edit\n  - Grep\n  - Glob\n---\n\n# \u002Fcli-for-agent\n\nHuman-oriented CLIs block agents: interactive prompts, huge upfront docs, and\nhelp text without copy-pasteable examples. Prefer patterns that work headlessly\nand compose in pipelines.\n\n## Non-interactive first\n\n- Every input should be expressible as a flag or flag value. Do not require\n  arrow keys, menus, or timed prompts.\n- If flags are missing, **then** fall back to interactive mode — not the other\n  way around.\n\n**Bad:** `mycli deploy` → `? Which environment? (use arrow keys)`\n**Good:** `mycli deploy --env staging`\n\n## Discoverability without dumping context\n\n- Agents discover subcommands incrementally: `mycli`, then `mycli deploy\n  --help`. Do not print the entire manual on every run.\n- Let each subcommand own its documentation so unused commands stay out of\n  context.\n\n## `--help` that works\n\n- Every subcommand has `--help`.\n- Every `--help` includes **Examples** with real invocations. Examples do more\n  than prose for pattern-matching.\n\n```text\nOptions:\n  --env     Target environment (staging, production)\n  --tag     Image tag (default: latest)\n  --force   Skip confirmation\n\nExamples:\n  mycli deploy --env staging\n  mycli deploy --env production --tag v1.2.3\n  mycli deploy --env staging --force\n```\n\n## stdin, flags, and pipelines\n\n- Accept stdin where it makes sense (e.g. `cat config.json | mycli config\n  import --stdin`).\n- Avoid odd positional ordering and avoid falling back to interactive prompts\n  for missing values.\n- Support chaining: `mycli deploy --env staging --tag $(mycli build --output\n  tag-only)`.\n\n## Fail fast with actionable errors\n\n- On missing required flags: exit immediately with a clear message and a\n  **correct example invocation**, not a hang.\n\n```text\nError: No image tag specified.\n  mycli deploy --env staging --tag \u003Cimage-tag>\n  Available tags: mycli build list --output tags\n```\n\n## Idempotency\n\n- Agents retry often. The same successful command run twice should be safe\n  (no-op or explicit \"already done\"), not duplicate side effects.\n\n## Destructive actions\n\n- Add `--dry-run` (or equivalent) so agents can preview plans before\n  committing.\n- Offer `--yes`\u002F`--force` to skip confirmations while keeping the safe default\n  for humans.\n\n## Predictable structure\n\n- Use a consistent pattern everywhere, e.g. `resource` + `verb`: if `mycli\n  service list` exists, `mycli deploy list` and `mycli config list` should\n  follow the same shape.\n\n## Success output\n\n- On success, return machine-useful data: IDs, URLs, durations. Plain text is\n  fine; avoid relying on decorative output alone.\n\n```text\ndeployed v1.2.3 to staging\nurl: https:\u002F\u002Fstaging.myapp.com\ndeploy_id: dep_abc123\nduration: 34s\n```\n\n## When reviewing an existing CLI\n\n- Check: non-interactive path, layered help, examples on `--help`,\n  stdin\u002Fpipeline story, error messages with invocations, idempotency,\n  dry-run, confirmation bypass flags, consistent command structure,\n  structured success output.\n\n---\n\nAdapted from [cursor\u002Fplugins](https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins)\n`cli-for-agent\u002Fskills\u002Fcli-for-agents\u002FSKILL.md` (MIT, © Cursor). Vendored per\nthe superskills imported-skills rule; changes here do not track upstream.\n","# \u002Fcli-for-agent\n\nHuman-oriented CLIs block agents: interactive prompts, huge upfront docs, and\nhelp text without copy-pasteable examples. Prefer patterns that work headlessly\nand compose in pipelines.\n\n## Non-interactive first\n\n- Every input should be expressible as a flag or flag value. Do not require\n  arrow keys, menus, or timed prompts.\n- If flags are missing, **then** fall back to interactive mode — not the other\n  way around.\n\n**Bad:** `mycli deploy` → `? Which environment? (use arrow keys)`\n**Good:** `mycli deploy --env staging`\n\n## Discoverability without dumping context\n\n- Agents discover subcommands incrementally: `mycli`, then `mycli deploy\n  --help`. Do not print the entire manual on every run.\n- Let each subcommand own its documentation so unused commands stay out of\n  context.\n\n## `--help` that works\n\n- Every subcommand has `--help`.\n- Every `--help` includes **Examples** with real invocations. Examples do more\n  than prose for pattern-matching.\n\n```text\nOptions:\n  --env     Target environment (staging, production)\n  --tag     Image tag (default: latest)\n  --force   Skip confirmation\n\nExamples:\n  mycli deploy --env staging\n  mycli deploy --env production --tag v1.2.3\n  mycli deploy --env staging --force\n```\n\n## stdin, flags, and pipelines\n\n- Accept stdin where it makes sense (e.g. `cat config.json | mycli config\n  import --stdin`).\n- Avoid odd positional ordering and avoid falling back to interactive prompts\n  for missing values.\n- Support chaining: `mycli deploy --env staging --tag $(mycli build --output\n  tag-only)`.\n\n## Fail fast with actionable errors\n\n- On missing required flags: exit immediately with a clear message and a\n  **correct example invocation**, not a hang.\n\n```text\nError: No image tag specified.\n  mycli deploy --env staging --tag \u003Cimage-tag>\n  Available tags: mycli build list --output tags\n```\n\n## Idempotency\n\n- Agents retry often. The same successful command run twice should be safe\n  (no-op or explicit \"already done\"), not duplicate side effects.\n\n## Destructive actions\n\n- Add `--dry-run` (or equivalent) so agents can preview plans before\n  committing.\n- Offer `--yes`\u002F`--force` to skip confirmations while keeping the safe default\n  for humans.\n\n## Predictable structure\n\n- Use a consistent pattern everywhere, e.g. `resource` + `verb`: if `mycli\n  service list` exists, `mycli deploy list` and `mycli config list` should\n  follow the same shape.\n\n## Success output\n\n- On success, return machine-useful data: IDs, URLs, durations. Plain text is\n  fine; avoid relying on decorative output alone.\n\n```text\ndeployed v1.2.3 to staging\nurl: https:\u002F\u002Fstaging.myapp.com\ndeploy_id: dep_abc123\nduration: 34s\n```\n\n## When reviewing an existing CLI\n\n- Check: non-interactive path, layered help, examples on `--help`,\n  stdin\u002Fpipeline story, error messages with invocations, idempotency,\n  dry-run, confirmation bypass flags, consistent command structure,\n  structured success output.\n\n---\n\nAdapted from [cursor\u002Fplugins](https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins)\n`cli-for-agent\u002Fskills\u002Fcli-for-agents\u002FSKILL.md` (MIT, © Cursor). Vendored per\nthe superskills imported-skills rule; changes here do not track upstream.\n",{"name":5,"version":49,"triggers":50,"description":56,"allowed-tools":57,"metadata.upstream":63},"1.0.0",[51,52,53,54,55],"agent-friendly cli","cli for agents","build a cli","add a subcommand","write --help","Design or review CLIs so coding agents can run them reliably: non-interactive\nflags first, layered --help with real copy-pasteable examples, stdin\u002Fpipeline\nsupport, fail-fast errors that include a correct invocation, idempotency,\n--dry-run\u002F--yes for destructive actions, and machine-useful success output.\nUse when building a CLI, adding commands or subcommands, writing --help\ntext, or when asked for an \"agent-friendly CLI\". Not for GUIs, TUIs, or\nlibrary APIs (no CLI surface to design).\n",[37,58,59,60,61,62],"Read","Write","Edit","Grep","Glob","https:\u002F\u002Fgithub.com\u002Fcursor\u002Fplugins (cli-for-agent\u002Fskills\u002Fcli-for-agents, MIT)","main","c7ec8d78e5dc37484c2cfe90ab04de163d97dd41","skills\u002Fcli-for-agent",0,"https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills","https:\u002F\u002Fhyperion360.com\u002Fblog\u002Fparallel-ai-agents-engineering-workflow\u002F","https:\u002F\u002Fgithub.com\u002Fariadoss","https:\u002F\u002Fdanilosapad.com\u002F","CEO & Founder of @Hyperion360","2026-11-13 04:11:07",{"source":8,"skillName":5,"commands":75,"prompt":85,"zipAvailable":86},[76,79,82],{"tool":77,"command":78},"npx","npx skills add ariadoss\u002Fsuperskills --skill cli-for-agent",{"tool":80,"command":81},"bunx","bunx skills add ariadoss\u002Fsuperskills --skill cli-for-agent",{"tool":83,"command":84},"pnpm","pnpm dlx skills add ariadoss\u002Fsuperskills --skill cli-for-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fcli-for-agent\u002FSKILL.md",true,[],[89,112,134,153,180,195],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":98,"publishedAt":44},"01M71AZE3MPF891RM354EMRYA1","youtube","Download YouTube video transcripts when user provides a YouTube URL or asks to download\u002Fget\u002Ffetch a transcript from YouTube. Also use when user wants to transcribe or get captions\u002Fsubtitles from a YouTube video.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[91,99,100,101,29,102,103,37,104,38,105,106,107,108,30,109,110,111],"user","download","transcribe","transcript","video transcripts","URL","Captions","get","fetch","Video","use","subtitles","transcripts",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":44},"01M71AZAYR85PW6BJGSQXS4BN2","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY\u002FSOLID\u002FYAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs \u002Fplan-eng-review as an independent double-check before execution.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[119,120,29,35,121,36,122,123,124,38,125,126,127,128,129,24,130,131,132,133],"write plan","plan","verification","tasks","code","you","auto","eng","coverage","complete","section","test plan","target","as","yagni",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":44},"01M71AZ8NDDP5ZMGEE6FSC4FKR","worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fworktrees\u002FSKILL.md",[],[136,141,142,143,109,144,145,146,147,148,149,121,150,38,151,152],"implementation","workspace","with","plans","feature","isolation","git","directory","work","git worktrees","selection","Safety",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":44},"01M71AZ4ZQHTNWFRZVYHKQFP08","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\u002FSKILL.md",[159],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[161,162,163,164,165,166,167,168,169,38,170,171,172,173,174,175,176,177,178,179],"web","perf","web perf","resources","MCP","layout","optimize","documentation","caching","qa","knowledge","devtools","issues","render","re","performance","chrome devtools","vitals","never",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":44},"01M71AZ2KZNWYEGKKRMJH8PYG2","verify","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[182,128,27,187,149,121,188,189,38,190,109,191,192,193,194],"about","claims","output","assertions","claim","prs","evidence","running",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":201,"publishedAt":44},"01M71AZ0ACCK7N1QMWQK1FV2HJ","validate-idea","Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-idea\u002FSKILL.md",[],[202,203,204,205,206,207,208,38,209,109,210],"validate","idea","validate idea","framework","it","minimalist","test","business","before building"]