[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7388FQPHB16ZR5CE98PZBVC":3,"skill-same:01M7388FQPHB16ZR5CE98PZBVC":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M7388FQPHB16ZR5CE98PZBVC","design-cli-output",null,"Design terminal output for a CLI tool with chalk colors, Unicode glyphs, multiple verbosity levels (human, verbose, quiet, JSON), and consistent voice rules. Covers color palette selection, status indicator design, reporter function architecture, ceremony\u002Fnarrative output variants, and cross-terminal compatibility. Use when building a new CLI reporter module, adding warm narrative output to an existing tool, standardizing output across multiple commands, or designing machine-readable JSON alongside human-readable text.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fdesign-cli-output\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: design-cli-output\nlocale: caveman-lite\nsource_locale: en\nsource_commit: 82c77053\ntranslator: \"Julius Brussee homage — caveman\"\ntranslation_date: \"2026-04-23\"\ndescription: >\n  Design terminal output for a CLI tool with chalk colors, Unicode glyphs,\n  multiple verbosity levels (human, verbose, quiet, JSON), and consistent\n  voice rules. Covers color palette selection, status indicator design,\n  reporter function architecture, ceremony\u002Fnarrative output variants, and\n  cross-terminal compatibility. Use when building a new CLI reporter module,\n  adding warm narrative output to an existing tool, standardizing output\n  across multiple commands, or designing machine-readable JSON alongside\n  human-readable text.\nlicense: MIT\nallowed-tools: Read Write Edit Bash Grep Glob\nmetadata:\n  author: Philipp Thoss\n  version: \"1.0\"\n  domain: cli\n  complexity: basic\n  language: TypeScript\n  tags:\n    - cli\n    - terminal\n    - ux\n    - chalk\n    - unicode\n---\n\n# Design CLI Output\n\nDesign consistent, multi-level terminal output for a command-line tool.\n\n## When to Use\n\n- Building a new reporter module for a CLI tool\n- Adding warm or narrative output alongside standard transactional output\n- Standardizing output format across multiple commands\n- Designing JSON machine output parallel to human-readable output\n- Choosing colors, glyphs, and verbosity levels for a new terminal tool\n\n## Inputs\n\n- **Required**: CLI tool name and primary audience (developers, operators, end users)\n- **Required**: Commands that need output formatting\n- **Optional**: Whether a \"ceremony\" or narrative output variant is desired\n- **Optional**: Branding constraints (color palette, tone)\n\n## Procedure\n\n### Step 1: Define the Color Palette\n\nUse chalk to create a named palette object:\n\n**Standard palette** (transactional output):\n\n```javascript\nlet chalk;\ntry { chalk = (await import('chalk')).default; }\ncatch { chalk = new Proxy({}, { get: () => (s) => s }); }\n\n\u002F\u002F Status colors\nconst ok = chalk.green;       \u002F\u002F success\nconst fail = chalk.red;       \u002F\u002F errors\nconst warn = chalk.yellow;    \u002F\u002F warnings\nconst info = chalk.cyan;      \u002F\u002F identifiers, names\nconst dim = chalk.dim;        \u002F\u002F secondary info, paths\nconst bold = chalk.bold;      \u002F\u002F headers\n```\n\n**Warm palette** (ceremony\u002Fnarrative output):\n\n```javascript\nconst C = {\n  flame: chalk.hex('#FF6B35'),   \u002F\u002F active elements, fire\n  amber: chalk.hex('#FFB347'),   \u002F\u002F arriving items, warm highlights\n  spark: chalk.hex('#FFF4E0'),   \u002F\u002F individual items (sparks\u002Fskills)\n  ember: chalk.hex('#8B4513'),   \u002F\u002F cold\u002Fdormant states\n  warm:  chalk.hex('#D4A574'),   \u002F\u002F neutral warm text\n  dim:   chalk.dim,              \u002F\u002F background, secondary\n  fail:  chalk.red,              \u002F\u002F errors stay red (honest)\n};\n```\n\nPalette design rules:\n- Always provide a no-color fallback (the Proxy pattern above)\n- Use hex colors for custom palettes (`chalk.hex('#FF6B35')`)\n- Keep the fail\u002Ferror color red regardless of palette theme\n- Name palette entries by semantic role, not visual appearance\n\n**Got:** A palette object with named entries and a no-color fallback.\n\n**If fail:** If chalk is unavailable (piped output, CI), the Proxy fallback returns strings unchanged. Test with `NO_COLOR=1` environment variable.\n\n### Step 2: Choose Status Indicators\n\nSelect Unicode glyphs or ASCII characters for status communication:\n\n**ASCII (maximum compatibility):**\n\n```\n+  created\u002Finstalled (green)\n-  removed\u002Fdeleted (red)\n=  skipped\u002Funchanged (dim)\n!  error\u002Fwarning (red)\n```\n\n**Unicode (richer, needs UTF-8 terminal):**\n\n```\n✦  item\u002Fskill\u002Fpractice (spark)\n◉  active\u002Fburning state\n◎  cooling\u002Fembers state\n○  cold\u002Fdormant state\n◌  available\u002Fnot installed\n✗  failed item\n✓  success (use sparingly — not all terminals render it well)\n```\n\nSelection criteria:\n- ASCII for tools that run in CI or piped contexts\n- Unicode for tools with interactive terminal users\n- Offer both via a `--ascii` flag or `NO_COLOR` detection\n- Test glyphs in: macOS Terminal, Windows Terminal, VS Code terminal, SSH sessions\n\n**Got:** A glyph set that communicates status at a glance without relying on color alone.\n\n**If fail:** If a glyph renders as `?` or a box in testing, replace with the ASCII equivalent. The `+\u002F-\u002F=\u002F!` set works everywhere.\n\n### Step 3: Design Verbosity Levels\n\nEvery command should support four output levels:\n\n| Level | Flag | Audience | Content |\n|-------|------|----------|---------|\n| **Default** | (none) | Human at terminal | Formatted, colored, informative |\n| **Verbose** | `--verbose` or `--ceremonial` | Human wanting detail | Per-item breakdown, arrival sequences |\n| **Quiet** | `--quiet` | Scripts, CI | Minimal lines, status icons, no decoration |\n| **JSON** | `--json` | Machine consumers | Structured, parseable, complete |\n\nImplementation pattern:\n\n```javascript\nfunction output(data, options) {\n  if (options.json) {\n    console.log(JSON.stringify(data, null, 2));\n    return;\n  }\n  if (options.quiet) {\n    for (const item of data.items) {\n      const icon = item.ok ? '+' : '!';\n      console.log(`${icon} ${item.id}`);\n    }\n    return;\n  }\n  \u002F\u002F Default (or verbose) human output\n  printFormatted(data, { verbose: options.verbose });\n}\n```\n\nJSON output rules:\n- Always valid JSON (no mixing with human text)\n- Include all data the human output shows, plus machine-useful fields\n- Use consistent key naming across commands\n- Exit code 0 for success, 1 for errors (regardless of output mode)\n\n**Got:** Four clear output levels with consistent behavior across commands.\n\n**If fail:** If verbose mode is too noisy, make it opt-in (`--ceremonial`) rather than a graduated verbosity level.\n\n### Step 4: Establish Voice Rules\n\nDefine the tone and style that all output functions follow. This prevents inconsistency across commands.\n\nExample voice rules (from the campfire reporter):\n\n1. **Present tense, active voice**: \"mystic arrives\" not \"mystic has been installed\"\n2. **No exclamation marks**: Quiet confidence. The tool doesn't shout.\n3. **Metaphor replaces jargon**: \"practices\" not \"dependencies\" (only for ceremony mode)\n4. **Failures are honest, not catastrophic**: \"A spark was lost\" not \"ERROR: installation failed with exit code 1\"\n5. **Closing line reflects state**: Every operation ends with a status summary\n6. **No emoji**: Unicode glyphs carry visual weight without being decorative\n7. **Every word carries information**: If a word doesn't add understanding, remove it\n\nVoice rules for standard (non-ceremony) output:\n- Concise, factual lines\n- Status icon + item ID + context\n- Summary line with counts\n- Error messages suggest corrective actions\n\n**Got:** A written set of 3-7 voice rules that output functions must follow.\n\n**If fail:** If rules feel arbitrary, test them: write the same output with and without each rule. If removing a rule doesn't change the output quality, the rule isn't needed.\n\n### Step 5: Implement Reporter Functions\n\nOrganize output into a reporter module with focused functions:\n\n```javascript\n\u002F\u002F reporter.js — standard output\nexport function printResults(results) { ... }\nexport function printItemTable(items) { ... }\nexport function printDetections(detections) { ... }\nexport function printAudit(auditResults) { ... }\nexport function printDryRun() { ... }\nexport function warn(msg) { ... }\nexport function error(msg) { ... }\nexport { chalk };\n```\n\nEach function follows the same structure:\n1. Handle empty\u002Fnull input gracefully\n2. Compute layout (column widths, padding)\n3. Output with palette colors\n4. Summary line at the bottom\n\nFor ceremony output, create a separate module:\n\n```javascript\n\u002F\u002F campfire-reporter.js — warm narrative output\nexport function printArrival({ teamId, agents, results, ceremonial }) { ... }\nexport function printScatter({ teamId, agents, results }) { ... }\nexport function printTend(fires) { ... }\nexport function printCampfireList({ teams, state, reg }) { ... }\nexport function printFireSummary({ team, fireData, reg }) { ... }\nexport function printJson(data) { ... }\n```\n\n**Got:** Reporter functions that are independently usable — each handles its own formatting without depending on caller state.\n\n**If fail:** If functions grow beyond ~50 lines, extract helpers. A reporter function should be easy to review in isolation.\n\n### Step 6: Test Output Across Environments\n\nVerify output renders correctly in different contexts:\n\n```bash\n# With colors (interactive terminal)\nnode cli\u002Findex.js list --domains\n\n# Without colors (piped)\nnode cli\u002Findex.js list --domains | cat\n\n# With NO_COLOR environment variable\nNO_COLOR=1 node cli\u002Findex.js list --domains\n\n# JSON mode (parseable)\nnode cli\u002Findex.js campfire --json | jq .\n\n# In CI (typically no TTY)\nCI=true node cli\u002Findex.js audit\n```\n\nCheck for:\n- Colors display correctly in interactive mode\n- No ANSI escape codes leak into piped\u002Fredirected output\n- JSON is valid (pipe to `jq .` to verify)\n- Unicode glyphs render in the target terminals\n- Column alignment holds with varying content widths\n\n**Got:** Output is correct in all five contexts.\n\n**If fail:** If ANSI codes leak, ensure chalk respects `NO_COLOR`. If Unicode breaks, provide an ASCII fallback mode.\n\n## Validation\n\n- [ ] Color palette has a no-color fallback\n- [ ] Status indicators work in both color and no-color modes\n- [ ] All four verbosity levels produce useful output\n- [ ] JSON output is valid and parseable by `jq`\n- [ ] Voice rules are documented and followed consistently\n- [ ] Reporter functions handle empty\u002Fnull input gracefully\n- [ ] Output tested in: terminal, piped, NO_COLOR, CI\n\n## Pitfalls\n\n- **Mixing human text with JSON**: In `--json` mode, output only valid JSON. A single stray line (like \"DRY RUN\") breaks JSON parsers. If the command must show both, separate them clearly or suppress the human text in JSON mode.\n- **Hardcoded column widths**: Content length varies. Use `Math.max(...items.map(i => i.id.length))` to compute padding dynamically.\n- **Color without meaning**: If color is the only way to distinguish success from failure, colorblind users and piped output lose information. Always pair color with a text indicator (`+`, `OK`, `ERR`).\n- **Ceremony in the wrong context**: Warm narrative output is appropriate for interactive terminal sessions. In CI, scripts, or `--quiet` mode, it adds noise. Gate ceremony output behind explicit flags.\n- **Forgetting the summary line**: Users scan the last line first. Every operation should end with a one-line summary (counts of success\u002Ffailure\u002Fskipped).\n\n## Related Skills\n\n- `scaffold-cli-command` — the commands that use this output\n- `test-cli-application` — testing that output matches expectations\n- `build-cli-plugin` — plugins report results through this output system\n","# Design CLI Output\n\nDesign consistent, multi-level terminal output for a command-line tool.\n\n## When to Use\n\n- Building a new reporter module for a CLI tool\n- Adding warm or narrative output alongside standard transactional output\n- Standardizing output format across multiple commands\n- Designing JSON machine output parallel to human-readable output\n- Choosing colors, glyphs, and verbosity levels for a new terminal tool\n\n## Inputs\n\n- **Required**: CLI tool name and primary audience (developers, operators, end users)\n- **Required**: Commands that need output formatting\n- **Optional**: Whether a \"ceremony\" or narrative output variant is desired\n- **Optional**: Branding constraints (color palette, tone)\n\n## Procedure\n\n### Step 1: Define the Color Palette\n\nUse chalk to create a named palette object:\n\n**Standard palette** (transactional output):\n\n```javascript\nlet chalk;\ntry { chalk = (await import('chalk')).default; }\ncatch { chalk = new Proxy({}, { get: () => (s) => s }); }\n\n\u002F\u002F Status colors\nconst ok = chalk.green;       \u002F\u002F success\nconst fail = chalk.red;       \u002F\u002F errors\nconst warn = chalk.yellow;    \u002F\u002F warnings\nconst info = chalk.cyan;      \u002F\u002F identifiers, names\nconst dim = chalk.dim;        \u002F\u002F secondary info, paths\nconst bold = chalk.bold;      \u002F\u002F headers\n```\n\n**Warm palette** (ceremony\u002Fnarrative output):\n\n```javascript\nconst C = {\n  flame: chalk.hex('#FF6B35'),   \u002F\u002F active elements, fire\n  amber: chalk.hex('#FFB347'),   \u002F\u002F arriving items, warm highlights\n  spark: chalk.hex('#FFF4E0'),   \u002F\u002F individual items (sparks\u002Fskills)\n  ember: chalk.hex('#8B4513'),   \u002F\u002F cold\u002Fdormant states\n  warm:  chalk.hex('#D4A574'),   \u002F\u002F neutral warm text\n  dim:   chalk.dim,              \u002F\u002F background, secondary\n  fail:  chalk.red,              \u002F\u002F errors stay red (honest)\n};\n```\n\nPalette design rules:\n- Always provide a no-color fallback (the Proxy pattern above)\n- Use hex colors for custom palettes (`chalk.hex('#FF6B35')`)\n- Keep the fail\u002Ferror color red regardless of palette theme\n- Name palette entries by semantic role, not visual appearance\n\n**Got:** A palette object with named entries and a no-color fallback.\n\n**If fail:** If chalk is unavailable (piped output, CI), the Proxy fallback returns strings unchanged. Test with `NO_COLOR=1` environment variable.\n\n### Step 2: Choose Status Indicators\n\nSelect Unicode glyphs or ASCII characters for status communication:\n\n**ASCII (maximum compatibility):**\n\n```\n+  created\u002Finstalled (green)\n-  removed\u002Fdeleted (red)\n=  skipped\u002Funchanged (dim)\n!  error\u002Fwarning (red)\n```\n\n**Unicode (richer, needs UTF-8 terminal):**\n\n```\n✦  item\u002Fskill\u002Fpractice (spark)\n◉  active\u002Fburning state\n◎  cooling\u002Fembers state\n○  cold\u002Fdormant state\n◌  available\u002Fnot installed\n✗  failed item\n✓  success (use sparingly — not all terminals render it well)\n```\n\nSelection criteria:\n- ASCII for tools that run in CI or piped contexts\n- Unicode for tools with interactive terminal users\n- Offer both via a `--ascii` flag or `NO_COLOR` detection\n- Test glyphs in: macOS Terminal, Windows Terminal, VS Code terminal, SSH sessions\n\n**Got:** A glyph set that communicates status at a glance without relying on color alone.\n\n**If fail:** If a glyph renders as `?` or a box in testing, replace with the ASCII equivalent. The `+\u002F-\u002F=\u002F!` set works everywhere.\n\n### Step 3: Design Verbosity Levels\n\nEvery command should support four output levels:\n\n| Level | Flag | Audience | Content |\n|-------|------|----------|---------|\n| **Default** | (none) | Human at terminal | Formatted, colored, informative |\n| **Verbose** | `--verbose` or `--ceremonial` | Human wanting detail | Per-item breakdown, arrival sequences |\n| **Quiet** | `--quiet` | Scripts, CI | Minimal lines, status icons, no decoration |\n| **JSON** | `--json` | Machine consumers | Structured, parseable, complete |\n\nImplementation pattern:\n\n```javascript\nfunction output(data, options) {\n  if (options.json) {\n    console.log(JSON.stringify(data, null, 2));\n    return;\n  }\n  if (options.quiet) {\n    for (const item of data.items) {\n      const icon = item.ok ? '+' : '!';\n      console.log(`${icon} ${item.id}`);\n    }\n    return;\n  }\n  \u002F\u002F Default (or verbose) human output\n  printFormatted(data, { verbose: options.verbose });\n}\n```\n\nJSON output rules:\n- Always valid JSON (no mixing with human text)\n- Include all data the human output shows, plus machine-useful fields\n- Use consistent key naming across commands\n- Exit code 0 for success, 1 for errors (regardless of output mode)\n\n**Got:** Four clear output levels with consistent behavior across commands.\n\n**If fail:** If verbose mode is too noisy, make it opt-in (`--ceremonial`) rather than a graduated verbosity level.\n\n### Step 4: Establish Voice Rules\n\nDefine the tone and style that all output functions follow. This prevents inconsistency across commands.\n\nExample voice rules (from the campfire reporter):\n\n1. **Present tense, active voice**: \"mystic arrives\" not \"mystic has been installed\"\n2. **No exclamation marks**: Quiet confidence. The tool doesn't shout.\n3. **Metaphor replaces jargon**: \"practices\" not \"dependencies\" (only for ceremony mode)\n4. **Failures are honest, not catastrophic**: \"A spark was lost\" not \"ERROR: installation failed with exit code 1\"\n5. **Closing line reflects state**: Every operation ends with a status summary\n6. **No emoji**: Unicode glyphs carry visual weight without being decorative\n7. **Every word carries information**: If a word doesn't add understanding, remove it\n\nVoice rules for standard (non-ceremony) output:\n- Concise, factual lines\n- Status icon + item ID + context\n- Summary line with counts\n- Error messages suggest corrective actions\n\n**Got:** A written set of 3-7 voice rules that output functions must follow.\n\n**If fail:** If rules feel arbitrary, test them: write the same output with and without each rule. If removing a rule doesn't change the output quality, the rule isn't needed.\n\n### Step 5: Implement Reporter Functions\n\nOrganize output into a reporter module with focused functions:\n\n```javascript\n\u002F\u002F reporter.js — standard output\nexport function printResults(results) { ... }\nexport function printItemTable(items) { ... }\nexport function printDetections(detections) { ... }\nexport function printAudit(auditResults) { ... }\nexport function printDryRun() { ... }\nexport function warn(msg) { ... }\nexport function error(msg) { ... }\nexport { chalk };\n```\n\nEach function follows the same structure:\n1. Handle empty\u002Fnull input gracefully\n2. Compute layout (column widths, padding)\n3. Output with palette colors\n4. Summary line at the bottom\n\nFor ceremony output, create a separate module:\n\n```javascript\n\u002F\u002F campfire-reporter.js — warm narrative output\nexport function printArrival({ teamId, agents, results, ceremonial }) { ... }\nexport function printScatter({ teamId, agents, results }) { ... }\nexport function printTend(fires) { ... }\nexport function printCampfireList({ teams, state, reg }) { ... }\nexport function printFireSummary({ team, fireData, reg }) { ... }\nexport function printJson(data) { ... }\n```\n\n**Got:** Reporter functions that are independently usable — each handles its own formatting without depending on caller state.\n\n**If fail:** If functions grow beyond ~50 lines, extract helpers. A reporter function should be easy to review in isolation.\n\n### Step 6: Test Output Across Environments\n\nVerify output renders correctly in different contexts:\n\n```bash\n# With colors (interactive terminal)\nnode cli\u002Findex.js list --domains\n\n# Without colors (piped)\nnode cli\u002Findex.js list --domains | cat\n\n# With NO_COLOR environment variable\nNO_COLOR=1 node cli\u002Findex.js list --domains\n\n# JSON mode (parseable)\nnode cli\u002Findex.js campfire --json | jq .\n\n# In CI (typically no TTY)\nCI=true node cli\u002Findex.js audit\n```\n\nCheck for:\n- Colors display correctly in interactive mode\n- No ANSI escape codes leak into piped\u002Fredirected output\n- JSON is valid (pipe to `jq .` to verify)\n- Unicode glyphs render in the target terminals\n- Column alignment holds with varying content widths\n\n**Got:** Output is correct in all five contexts.\n\n**If fail:** If ANSI codes leak, ensure chalk respects `NO_COLOR`. If Unicode breaks, provide an ASCII fallback mode.\n\n## Validation\n\n- [ ] Color palette has a no-color fallback\n- [ ] Status indicators work in both color and no-color modes\n- [ ] All four verbosity levels produce useful output\n- [ ] JSON output is valid and parseable by `jq`\n- [ ] Voice rules are documented and followed consistently\n- [ ] Reporter functions handle empty\u002Fnull input gracefully\n- [ ] Output tested in: terminal, piped, NO_COLOR, CI\n\n## Pitfalls\n\n- **Mixing human text with JSON**: In `--json` mode, output only valid JSON. A single stray line (like \"DRY RUN\") breaks JSON parsers. If the command must show both, separate them clearly or suppress the human text in JSON mode.\n- **Hardcoded column widths**: Content length varies. Use `Math.max(...items.map(i => i.id.length))` to compute padding dynamically.\n- **Color without meaning**: If color is the only way to distinguish success from failure, colorblind users and piped output lose information. Always pair color with a text indicator (`+`, `OK`, `ERR`).\n- **Ceremony in the wrong context**: Warm narrative output is appropriate for interactive terminal sessions. In CI, scripts, or `--quiet` mode, it adds noise. Gate ceremony output behind explicit flags.\n- **Forgetting the summary line**: Users scan the last line first. Every operation should end with a one-line summary (counts of success\u002Ffailure\u002Fskipped).\n\n## Related Skills\n\n- `scaffold-cli-command` — the commands that use this output\n- `test-cli-application` — testing that output matches expectations\n- `build-cli-plugin` — plugins report results through this output system\n",{"name":5,"locale":23,"license":14,"metadata":24,"translator":35,"description":36,"allowed-tools":37,"source_commit":38,"source_locale":39,"translation_date":40},"caveman-lite",{"tags":25,"author":31,"domain":26,"version":32,"language":33,"complexity":34},[26,27,28,29,30],"cli","terminal","ux","chalk","unicode","Philipp Thoss","1.0","TypeScript","basic","Julius Brussee homage — caveman","Design terminal output for a CLI tool with chalk colors, Unicode glyphs, multiple verbosity levels (human, verbose, quiet, JSON), and consistent voice rules. Covers color palette selection, status indicator design, reporter function architecture, ceremony\u002Fnarrative output variants, and cross-terminal compatibility. Use when building a new CLI reporter module, adding warm narrative output to an existing tool, standardizing output across multiple commands, or designing machine-readable JSON alongside human-readable text.\n","Read Write Edit Bash Grep Glob","82c77053","en","2026-04-23","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Fdesign-cli-output",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add roohe\u002Fagentic-super-skills --skill design-cli-output",{"tool":55,"command":56},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill design-cli-output",{"tool":58,"command":59},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill design-cli-output","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fdesign-cli-output\u002FSKILL.md",true,[],[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]