[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DD8ZTZHTR4EX456DBDECC8":3,"skill-same:01M6DD8ZTZHTR4EX456DBDECC8":104},{"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":26,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6DD8ZTZHTR4EX456DBDECC8","parallel-cli",null,"Agent-native web search, deep research, and enrichment.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F25\u002F255305b5c636feeeef90d41d9d4ffedc1a90b7dedc42489053342772b339f159\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"cli","parallel cli","parallel","deep","macos","hermes agent","hermes","native web search","web search","enrichment","deep research","search","windows","web","research","linux","mcporter","2026-11-10 10:12:30",false,"---\nname: parallel-cli\ndescription: Agent-native web search, deep research, and enrichment.\nversion: 1.1.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [Research, Web, Search, Deep-Research, Enrichment, CLI]\n    related_skills: [duckduckgo-search, mcporter]\n---\n\n# Parallel CLI\n\nUse `parallel-cli` when the user explicitly wants Parallel, or when a terminal-native workflow would benefit from Parallel's vendor-specific stack for web search, extraction, deep research, enrichment, entity discovery, or monitoring.\n\nThis is an optional third-party workflow, not a Hermes core capability.\n\nImportant expectations:\n- Parallel is a paid service with a free tier, not a fully free local tool.\n- It overlaps with Hermes native `web_search` \u002F `web_extract`, so do not prefer it by default for ordinary lookups.\n- Prefer this skill when the user mentions Parallel specifically or needs capabilities like Parallel's enrichment, FindAll, or monitor workflows.\n\n`parallel-cli` is designed for agents:\n- JSON output via `--json`\n- Non-interactive command execution\n- Async long-running jobs with `--no-wait`, `status`, and `poll`\n- Context chaining with `--previous-interaction-id`\n- Search, extract, research, enrichment, entity discovery, and monitoring in one CLI\n\n## When to use it\n\nPrefer this skill when:\n- The user explicitly mentions Parallel or `parallel-cli`\n- The task needs richer workflows than a simple one-shot search\u002Fextract pass\n- You need async deep research jobs that can be launched and polled later\n- You need structured enrichment, FindAll entity discovery, or monitoring\n\nPrefer Hermes native `web_search` \u002F `web_extract` for quick one-off lookups when Parallel is not specifically requested.\n\n## Installation\n\nTry the least invasive install path available for the environment.\n\n### Homebrew\n\n```bash\nbrew install parallel-web\u002Ftap\u002Fparallel-cli\n```\n\n### npm\n\n```bash\nnpm install -g parallel-web-cli\n```\n\n### Python package\n\n```bash\npip install \"parallel-web-tools[cli]\"\n```\n\n### Standalone installer\n\n```bash\ncurl -fsSL https:\u002F\u002Fparallel.ai\u002Finstall.sh | bash\n```\n\nIf you want an isolated Python install, `pipx` can also work:\n\n```bash\npipx install \"parallel-web-tools[cli]\"\npipx ensurepath\n```\n\n## Authentication\n\nInteractive login:\n\n```bash\nparallel-cli login\n```\n\nHeadless \u002F SSH \u002F CI:\n\n```bash\nparallel-cli login --device\n```\n\nAPI key environment variable:\n\n```bash\nexport PARALLEL_API_KEY=\"***\"\n```\n\nVerify current auth status:\n\n```bash\nparallel-cli auth\n```\n\nIf auth requires browser interaction, run with `pty=true`.\n\n## Core rule set\n\n1. Always prefer `--json` when you need machine-readable output.\n2. Prefer explicit arguments and non-interactive flows.\n3. For long-running jobs, use `--no-wait` and then `status` \u002F `poll`.\n4. Cite only URLs returned by the CLI output.\n5. Save large JSON outputs to a temp file when follow-up questions are likely.\n6. Use background processes only for genuinely long-running workflows; otherwise run in foreground.\n7. Prefer Hermes native tools unless the user wants Parallel specifically or needs Parallel-only workflows.\n\n## Quick reference\n\n```text\nparallel-cli\n├── auth\n├── login\n├── logout\n├── search\n├── extract \u002F fetch\n├── research run|status|poll|processors\n├── enrich run|status|poll|plan|suggest|deploy\n├── findall run|ingest|status|poll|result|enrich|extend|schema|cancel\n└── monitor create|list|get|update|delete|events|event-group|simulate\n```\n\n## Common flags and patterns\n\nCommonly useful flags:\n- `--json` for structured output\n- `--no-wait` for async jobs\n- `--previous-interaction-id \u003Cid>` for follow-up tasks that reuse earlier context\n- `--max-results \u003Cn>` for search result count\n- `--mode one-shot|agentic` for search behavior\n- `--include-domains domain1.com,domain2.com`\n- `--exclude-domains domain1.com,domain2.com`\n- `--after-date YYYY-MM-DD`\n\nRead from stdin when convenient:\n\n```bash\necho \"What is the latest funding for Anthropic?\" | parallel-cli search - --json\necho \"Research question\" | parallel-cli research run - --json\n```\n\n## Search\n\nUse for current web lookups with structured results.\n\n```bash\nparallel-cli search \"What is Anthropic's latest AI model?\" --json\nparallel-cli search \"SEC filings for Apple\" --include-domains sec.gov --json\nparallel-cli search \"bitcoin price\" --after-date 2026-01-01 --max-results 10 --json\nparallel-cli search \"latest browser benchmarks\" --mode one-shot --json\nparallel-cli search \"AI coding agent enterprise reviews\" --mode agentic --json\n```\n\nUseful constraints:\n- `--include-domains` to narrow trusted sources\n- `--exclude-domains` to strip noisy domains\n- `--after-date` for recency filtering\n- `--max-results` when you need broader coverage\n\nIf you expect follow-up questions, save output:\n\n```bash\nparallel-cli search \"latest React 19 changes\" --json -o ~\u002F.hermes\u002Fcache\u002Fscratch\u002Freact-19-search.json\n```\n\nWhen summarizing results:\n- lead with the answer\n- include dates, names, and concrete facts\n- cite only returned sources\n- avoid inventing URLs or source titles\n\n## Extraction\n\nUse to pull clean content or markdown from a URL.\n\n```bash\nparallel-cli extract https:\u002F\u002Fexample.com --json\nparallel-cli extract https:\u002F\u002Fcompany.com --objective \"Find pricing info\" --json\nparallel-cli extract https:\u002F\u002Fexample.com --full-content --json\nparallel-cli fetch https:\u002F\u002Fexample.com --json\n```\n\nUse `--objective` when the page is broad and you only need one slice of information.\n\n## Deep research\n\nUse for deeper multi-step research tasks that may take time.\n\nCommon processor tiers:\n- `lite` \u002F `base` for faster, cheaper passes\n- `core` \u002F `pro` for more thorough synthesis\n- `ultra` for the heaviest research jobs\n\n### Synchronous\n\n```bash\nparallel-cli research run \\\n  \"Compare the leading AI coding agents by pricing, model support, and enterprise controls\" \\\n  --processor core \\\n  --json\n```\n\n### Async launch + poll\n\n```bash\nparallel-cli research run \\\n  \"Compare the leading AI coding agents by pricing, model support, and enterprise controls\" \\\n  --processor ultra \\\n  --no-wait \\\n  --json\n\nparallel-cli research status trun_xxx --json\nparallel-cli research poll trun_xxx --json\nparallel-cli research processors --json\n```\n\n### Context chaining \u002F follow-up\n\n```bash\nparallel-cli research run \"What are the top AI coding agents?\" --json\nparallel-cli research run \\\n  \"What enterprise controls does the top-ranked one offer?\" \\\n  --previous-interaction-id trun_xxx \\\n  --json\n```\n\nRecommended Hermes workflow:\n1. launch with `--no-wait --json`\n2. capture the returned run\u002Ftask ID\n3. if the user wants to continue other work, keep moving\n4. later call `status` or `poll`\n5. summarize the final report with citations from the returned sources\n\n## Enrichment\n\nUse when the user has CSV\u002FJSON\u002Ftabular inputs and wants additional columns inferred from web research.\n\n### Suggest columns\n\n```bash\nparallel-cli enrich suggest \"Find the CEO and annual revenue\" --json\n```\n\n### Plan a config\n\n```bash\nparallel-cli enrich plan -o config.yaml\n```\n\n### Inline data\n\n```bash\nparallel-cli enrich run \\\n  --data '[{\"company\": \"Anthropic\"}, {\"company\": \"Mistral\"}]' \\\n  --intent \"Find headquarters and employee count\" \\\n  --json\n```\n\n### Non-interactive file run\n\n```bash\nparallel-cli enrich run \\\n  --source-type csv \\\n  --source companies.csv \\\n  --target enriched.csv \\\n  --source-columns '[{\"name\": \"company\", \"description\": \"Company name\"}]' \\\n  --intent \"Find the CEO and annual revenue\"\n```\n\n### YAML config run\n\n```bash\nparallel-cli enrich run config.yaml\n```\n\n### Status \u002F polling\n\n```bash\nparallel-cli enrich status \u003Ctask_group_id> --json\nparallel-cli enrich poll \u003Ctask_group_id> --json\n```\n\nUse explicit JSON arrays for column definitions when operating non-interactively.\nValidate the output file before reporting success.\n\n## FindAll\n\nUse for web-scale entity discovery when the user wants a discovered dataset rather than a short answer.\n\n```bash\nparallel-cli findall run \"Find AI coding agent startups with enterprise offerings\" --json\nparallel-cli findall run \"AI startups in healthcare\" -n 25 --json\nparallel-cli findall status \u003Crun_id> --json\nparallel-cli findall poll \u003Crun_id> --json\nparallel-cli findall result \u003Crun_id> --json\nparallel-cli findall schema \u003Crun_id> --json\n```\n\nThis is a better fit than ordinary search when the user wants a discovered set of entities that can be reviewed, filtered, or enriched later.\n\n## Monitor\n\nUse for ongoing change detection over time.\n\n```bash\nparallel-cli monitor list --json\nparallel-cli monitor get \u003Cmonitor_id> --json\nparallel-cli monitor events \u003Cmonitor_id> --json\nparallel-cli monitor delete \u003Cmonitor_id> --json\n```\n\nCreation is usually the sensitive part because cadence and delivery matter:\n\n```bash\nparallel-cli monitor create --help\n```\n\nUse this when the user wants recurring tracking of a page or source rather than a one-time fetch.\n\n## Recommended Hermes usage patterns\n\n### Fast answer with citations\n1. Run `parallel-cli search ... --json`\n2. Parse titles, URLs, dates, excerpts\n3. Summarize with inline citations from the returned URLs only\n\n### URL investigation\n1. Run `parallel-cli extract URL --json`\n2. If needed, rerun with `--objective` or `--full-content`\n3. Quote or summarize the extracted markdown\n\n### Long research workflow\n1. Run `parallel-cli research run ... --no-wait --json`\n2. Store the returned ID\n3. Continue other work or periodically poll\n4. Summarize the final report with citations\n\n### Structured enrichment workflow\n1. Inspect the input file and columns\n2. Use `enrich suggest` or provide explicit enriched columns\n3. Run `enrich run`\n4. Poll for completion if needed\n5. Validate the output file before reporting success\n\n## Error handling and exit codes\n\nThe CLI documents these exit codes:\n- `0` success\n- `2` bad input\n- `3` auth error\n- `4` API error\n- `5` timeout\n\nIf you hit auth errors:\n1. check `parallel-cli auth`\n2. confirm `PARALLEL_API_KEY` or run `parallel-cli login` \u002F `parallel-cli login --device`\n3. verify `parallel-cli` is on `PATH`\n\n## Maintenance\n\nCheck current auth \u002F install state:\n\n```bash\nparallel-cli auth\nparallel-cli --help\n```\n\nUpdate commands:\n\n```bash\nparallel-cli update\npip install --upgrade parallel-web-tools\nparallel-cli config auto-update-check off\n```\n\n## Pitfalls\n\n- Do not omit `--json` unless the user explicitly wants human-formatted output.\n- Do not cite sources not present in the CLI output.\n- `login` may require PTY\u002Fbrowser interaction.\n- Prefer foreground execution for short tasks; do not overuse background processes.\n- For large result sets, save JSON to `~\u002F.hermes\u002Fcache\u002Fscratch\u002F*.json` (the Hermes scratch dir) instead of stuffing everything into context.\n- Do not silently choose Parallel when Hermes native tools are already sufficient.\n- Remember this is a vendor workflow that usually requires account auth and paid usage beyond the free tier.\n","# Parallel CLI\n\nUse `parallel-cli` when the user explicitly wants Parallel, or when a terminal-native workflow would benefit from Parallel's vendor-specific stack for web search, extraction, deep research, enrichment, entity discovery, or monitoring.\n\nThis is an optional third-party workflow, not a Hermes core capability.\n\nImportant expectations:\n- Parallel is a paid service with a free tier, not a fully free local tool.\n- It overlaps with Hermes native `web_search` \u002F `web_extract`, so do not prefer it by default for ordinary lookups.\n- Prefer this skill when the user mentions Parallel specifically or needs capabilities like Parallel's enrichment, FindAll, or monitor workflows.\n\n`parallel-cli` is designed for agents:\n- JSON output via `--json`\n- Non-interactive command execution\n- Async long-running jobs with `--no-wait`, `status`, and `poll`\n- Context chaining with `--previous-interaction-id`\n- Search, extract, research, enrichment, entity discovery, and monitoring in one CLI\n\n## When to use it\n\nPrefer this skill when:\n- The user explicitly mentions Parallel or `parallel-cli`\n- The task needs richer workflows than a simple one-shot search\u002Fextract pass\n- You need async deep research jobs that can be launched and polled later\n- You need structured enrichment, FindAll entity discovery, or monitoring\n\nPrefer Hermes native `web_search` \u002F `web_extract` for quick one-off lookups when Parallel is not specifically requested.\n\n## Installation\n\nTry the least invasive install path available for the environment.\n\n### Homebrew\n\n```bash\nbrew install parallel-web\u002Ftap\u002Fparallel-cli\n```\n\n### npm\n\n```bash\nnpm install -g parallel-web-cli\n```\n\n### Python package\n\n```bash\npip install \"parallel-web-tools[cli]\"\n```\n\n### Standalone installer\n\n```bash\ncurl -fsSL https:\u002F\u002Fparallel.ai\u002Finstall.sh | bash\n```\n\nIf you want an isolated Python install, `pipx` can also work:\n\n```bash\npipx install \"parallel-web-tools[cli]\"\npipx ensurepath\n```\n\n## Authentication\n\nInteractive login:\n\n```bash\nparallel-cli login\n```\n\nHeadless \u002F SSH \u002F CI:\n\n```bash\nparallel-cli login --device\n```\n\nAPI key environment variable:\n\n```bash\nexport PARALLEL_API_KEY=\"***\"\n```\n\nVerify current auth status:\n\n```bash\nparallel-cli auth\n```\n\nIf auth requires browser interaction, run with `pty=true`.\n\n## Core rule set\n\n1. Always prefer `--json` when you need machine-readable output.\n2. Prefer explicit arguments and non-interactive flows.\n3. For long-running jobs, use `--no-wait` and then `status` \u002F `poll`.\n4. Cite only URLs returned by the CLI output.\n5. Save large JSON outputs to a temp file when follow-up questions are likely.\n6. Use background processes only for genuinely long-running workflows; otherwise run in foreground.\n7. Prefer Hermes native tools unless the user wants Parallel specifically or needs Parallel-only workflows.\n\n## Quick reference\n\n```text\nparallel-cli\n├── auth\n├── login\n├── logout\n├── search\n├── extract \u002F fetch\n├── research run|status|poll|processors\n├── enrich run|status|poll|plan|suggest|deploy\n├── findall run|ingest|status|poll|result|enrich|extend|schema|cancel\n└── monitor create|list|get|update|delete|events|event-group|simulate\n```\n\n## Common flags and patterns\n\nCommonly useful flags:\n- `--json` for structured output\n- `--no-wait` for async jobs\n- `--previous-interaction-id \u003Cid>` for follow-up tasks that reuse earlier context\n- `--max-results \u003Cn>` for search result count\n- `--mode one-shot|agentic` for search behavior\n- `--include-domains domain1.com,domain2.com`\n- `--exclude-domains domain1.com,domain2.com`\n- `--after-date YYYY-MM-DD`\n\nRead from stdin when convenient:\n\n```bash\necho \"What is the latest funding for Anthropic?\" | parallel-cli search - --json\necho \"Research question\" | parallel-cli research run - --json\n```\n\n## Search\n\nUse for current web lookups with structured results.\n\n```bash\nparallel-cli search \"What is Anthropic's latest AI model?\" --json\nparallel-cli search \"SEC filings for Apple\" --include-domains sec.gov --json\nparallel-cli search \"bitcoin price\" --after-date 2026-01-01 --max-results 10 --json\nparallel-cli search \"latest browser benchmarks\" --mode one-shot --json\nparallel-cli search \"AI coding agent enterprise reviews\" --mode agentic --json\n```\n\nUseful constraints:\n- `--include-domains` to narrow trusted sources\n- `--exclude-domains` to strip noisy domains\n- `--after-date` for recency filtering\n- `--max-results` when you need broader coverage\n\nIf you expect follow-up questions, save output:\n\n```bash\nparallel-cli search \"latest React 19 changes\" --json -o ~\u002F.hermes\u002Fcache\u002Fscratch\u002Freact-19-search.json\n```\n\nWhen summarizing results:\n- lead with the answer\n- include dates, names, and concrete facts\n- cite only returned sources\n- avoid inventing URLs or source titles\n\n## Extraction\n\nUse to pull clean content or markdown from a URL.\n\n```bash\nparallel-cli extract https:\u002F\u002Fexample.com --json\nparallel-cli extract https:\u002F\u002Fcompany.com --objective \"Find pricing info\" --json\nparallel-cli extract https:\u002F\u002Fexample.com --full-content --json\nparallel-cli fetch https:\u002F\u002Fexample.com --json\n```\n\nUse `--objective` when the page is broad and you only need one slice of information.\n\n## Deep research\n\nUse for deeper multi-step research tasks that may take time.\n\nCommon processor tiers:\n- `lite` \u002F `base` for faster, cheaper passes\n- `core` \u002F `pro` for more thorough synthesis\n- `ultra` for the heaviest research jobs\n\n### Synchronous\n\n```bash\nparallel-cli research run \\\n  \"Compare the leading AI coding agents by pricing, model support, and enterprise controls\" \\\n  --processor core \\\n  --json\n```\n\n### Async launch + poll\n\n```bash\nparallel-cli research run \\\n  \"Compare the leading AI coding agents by pricing, model support, and enterprise controls\" \\\n  --processor ultra \\\n  --no-wait \\\n  --json\n\nparallel-cli research status trun_xxx --json\nparallel-cli research poll trun_xxx --json\nparallel-cli research processors --json\n```\n\n### Context chaining \u002F follow-up\n\n```bash\nparallel-cli research run \"What are the top AI coding agents?\" --json\nparallel-cli research run \\\n  \"What enterprise controls does the top-ranked one offer?\" \\\n  --previous-interaction-id trun_xxx \\\n  --json\n```\n\nRecommended Hermes workflow:\n1. launch with `--no-wait --json`\n2. capture the returned run\u002Ftask ID\n3. if the user wants to continue other work, keep moving\n4. later call `status` or `poll`\n5. summarize the final report with citations from the returned sources\n\n## Enrichment\n\nUse when the user has CSV\u002FJSON\u002Ftabular inputs and wants additional columns inferred from web research.\n\n### Suggest columns\n\n```bash\nparallel-cli enrich suggest \"Find the CEO and annual revenue\" --json\n```\n\n### Plan a config\n\n```bash\nparallel-cli enrich plan -o config.yaml\n```\n\n### Inline data\n\n```bash\nparallel-cli enrich run \\\n  --data '[{\"company\": \"Anthropic\"}, {\"company\": \"Mistral\"}]' \\\n  --intent \"Find headquarters and employee count\" \\\n  --json\n```\n\n### Non-interactive file run\n\n```bash\nparallel-cli enrich run \\\n  --source-type csv \\\n  --source companies.csv \\\n  --target enriched.csv \\\n  --source-columns '[{\"name\": \"company\", \"description\": \"Company name\"}]' \\\n  --intent \"Find the CEO and annual revenue\"\n```\n\n### YAML config run\n\n```bash\nparallel-cli enrich run config.yaml\n```\n\n### Status \u002F polling\n\n```bash\nparallel-cli enrich status \u003Ctask_group_id> --json\nparallel-cli enrich poll \u003Ctask_group_id> --json\n```\n\nUse explicit JSON arrays for column definitions when operating non-interactively.\nValidate the output file before reporting success.\n\n## FindAll\n\nUse for web-scale entity discovery when the user wants a discovered dataset rather than a short answer.\n\n```bash\nparallel-cli findall run \"Find AI coding agent startups with enterprise offerings\" --json\nparallel-cli findall run \"AI startups in healthcare\" -n 25 --json\nparallel-cli findall status \u003Crun_id> --json\nparallel-cli findall poll \u003Crun_id> --json\nparallel-cli findall result \u003Crun_id> --json\nparallel-cli findall schema \u003Crun_id> --json\n```\n\nThis is a better fit than ordinary search when the user wants a discovered set of entities that can be reviewed, filtered, or enriched later.\n\n## Monitor\n\nUse for ongoing change detection over time.\n\n```bash\nparallel-cli monitor list --json\nparallel-cli monitor get \u003Cmonitor_id> --json\nparallel-cli monitor events \u003Cmonitor_id> --json\nparallel-cli monitor delete \u003Cmonitor_id> --json\n```\n\nCreation is usually the sensitive part because cadence and delivery matter:\n\n```bash\nparallel-cli monitor create --help\n```\n\nUse this when the user wants recurring tracking of a page or source rather than a one-time fetch.\n\n## Recommended Hermes usage patterns\n\n### Fast answer with citations\n1. Run `parallel-cli search ... --json`\n2. Parse titles, URLs, dates, excerpts\n3. Summarize with inline citations from the returned URLs only\n\n### URL investigation\n1. Run `parallel-cli extract URL --json`\n2. If needed, rerun with `--objective` or `--full-content`\n3. Quote or summarize the extracted markdown\n\n### Long research workflow\n1. Run `parallel-cli research run ... --no-wait --json`\n2. Store the returned ID\n3. Continue other work or periodically poll\n4. Summarize the final report with citations\n\n### Structured enrichment workflow\n1. Inspect the input file and columns\n2. Use `enrich suggest` or provide explicit enriched columns\n3. Run `enrich run`\n4. Poll for completion if needed\n5. Validate the output file before reporting success\n\n## Error handling and exit codes\n\nThe CLI documents these exit codes:\n- `0` success\n- `2` bad input\n- `3` auth error\n- `4` API error\n- `5` timeout\n\nIf you hit auth errors:\n1. check `parallel-cli auth`\n2. confirm `PARALLEL_API_KEY` or run `parallel-cli login` \u002F `parallel-cli login --device`\n3. verify `parallel-cli` is on `PATH`\n\n## Maintenance\n\nCheck current auth \u002F install state:\n\n```bash\nparallel-cli auth\nparallel-cli --help\n```\n\nUpdate commands:\n\n```bash\nparallel-cli update\npip install --upgrade parallel-web-tools\nparallel-cli config auto-update-check off\n```\n\n## Pitfalls\n\n- Do not omit `--json` unless the user explicitly wants human-formatted output.\n- Do not cite sources not present in the CLI output.\n- `login` may require PTY\u002Fbrowser interaction.\n- Prefer foreground execution for short tasks; do not overuse background processes.\n- For large result sets, save JSON to `~\u002F.hermes\u002Fcache\u002Fscratch\u002F*.json` (the Hermes scratch dir) instead of stuffing everything into context.\n- Do not silently choose Parallel when Hermes native tools are already sufficient.\n- Remember this is a vendor workflow that usually requires account auth and paid usage beyond the free tier.\n",{"name":5,"author":49,"license":15,"version":50,"metadata":51,"platforms":62,"description":7},"Hermes Agent","1.1.0",{"hermes":52},{"tags":53,"related_skills":60},[54,55,56,57,58,59],"Research","Web","Search","Deep-Research","Enrichment","CLI",[61,43],"duckduckgo-search",[42,31,39],"main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F25\u002F255305b5c636feeeef90d41d9d4ffedc1a90b7dedc42489053342772b339f159",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add zapabob\u002FSkills --skill parallel-cli",{"tool":77,"command":78},"bunx","bunx skills add zapabob\u002FSkills --skill parallel-cli",{"tool":80,"command":81},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill parallel-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F25\u002F255305b5c636feeeef90d41d9d4ffedc1a90b7dedc42489053342772b339f159\u002FSKILL.md",true,[85,90,96,100],{"path":86,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"LICENSE","许可证",11356,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Flatest-release-devops\u002Fbash-script-generator\u002FLICENSE",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"provenance\u002Foriginal.SKILL.md","REFERENCE","参考文档",6812,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Flatest-release-devops\u002Fbash-script-generator\u002Fprovenance\u002Foriginal.SKILL.md",{"path":97,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":98,"sourceHtmlUrl":99},"provenance\u002Fprior-overlay.SKILL.md",1866,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Flatest-release-devops\u002Fbash-script-generator\u002Fprovenance\u002Fprior-overlay.SKILL.md",{"path":101,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":102,"sourceHtmlUrl":103},"repair.json",1997,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Frepaired\u002Fskills\u002Fby-category\u002Fdevops-cloud-operations\u002Flatest-release-devops\u002Fbash-script-generator\u002Frepair.json",[105,132,167,194,221,238],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":120,"publishedAt":44},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[111,114,115],{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[107,121,31,27,122,42,39,123,38,124,125,126,127,33,32,128,63,129,130,131],"openclaw","github","official","https","social-media","api","Media","twitter","social","via","post",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":149,"publishedAt":44},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[138,141,144,145,146],{"categoryNo":139,"categoryName":140,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},{"categoryNo":147,"categoryName":148,"taxonomyType":118,"taxonomyTypeDesc":119},"01JBSEEDCAT000000000000036","内容创作者",[150,151,152,153,31,154,42,155,39,156,157,158,159,160,161,162,163,164,165,166],"writing","writing plans","plans","design","review","workflow","documentation","tasks","development","code","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":44},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[173],{"categoryNo":174,"categoryName":175,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[169,31,42,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":198,"categories":199,"keywords":203,"publishedAt":44},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[200],{"categoryNo":201,"categoryName":202,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[204,31,205,206,39,207,208,209,210,211,212,184,213,214,215,216,217,218,219,220],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":228,"publishedAt":44},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[227],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[223,31,229,122,42,230,231,232,233,234,235,33,32,236,237],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":242,"categories":243,"keywords":246,"publishedAt":44},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[244,245],{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":116,"categoryName":117,"taxonomyType":118,"taxonomyTypeDesc":119},[247,248,249,42,41,177,250,251,252,180,253,126,254,255,256,257,258,259,260,261],"llms","vLLM","serving llms vllm","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]