[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M737RXW1GGPXM0FPVJ68YCEC":3,"skill-same:01M737RXW1GGPXM0FPVJ68YCEC":62},{"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":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M737RXW1GGPXM0FPVJ68YCEC","parallel-cli",null,"Agent-native web search, deep research, and enrichment.","ashneil12\u002Fvanilla-hermes-agent-canary","ashneil12","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F49880658?v=4","01M7378BQ9W161EPENEWBYAQNN","01M7378BRDJG8SFS93FG4V6BWY",1,"MIT","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Foptional-skills\u002Fresearch\u002Fparallel-cli\u002FSKILL.md",[],[],"2026-11-11 15:11:14",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":23,"license":14,"version":24,"metadata":25,"platforms":37,"description":7},"Hermes Agent","1.1.0",{"hermes":26},{"tags":27,"related_skills":34},[28,29,30,31,32,33],"Research","Web","Search","Deep-Research","Enrichment","CLI",[35,36],"duckduckgo-search","mcporter",[38,39,40],"linux","macos","windows","main","0905b0264ce5a54908bedc9637e50251543db132","optional-skills\u002Fresearch\u002Fparallel-cli",0,"https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary","https:\u002F\u002Fgithub.com\u002Fashneil12","2026-11-04 08:25:00",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add ashneil12\u002Fvanilla-hermes-agent-canary --skill parallel-cli",{"tool":54,"command":55},"bunx","bunx skills add ashneil12\u002Fvanilla-hermes-agent-canary --skill parallel-cli",{"tool":57,"command":58},"pnpm","pnpm dlx skills add ashneil12\u002Fvanilla-hermes-agent-canary --skill parallel-cli","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Foptional-skills\u002Fresearch\u002Fparallel-cli\u002FSKILL.md",true,[],[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M7380YR13A23353XT9NS6EGR","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7380VZ8P60Q64J3F92D4AMY","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7380QXN6F90R0MH1M3FHRKX","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7380N4BZYT2WRRZN1N9DZ65","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M7380JAEC9ZH5DVPHHK56P97","simplify-code","Parallel 4-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M7380F5MBB7FKWWV3G3TZ193","requesting-code-review","Pre-commit review: security scan, quality gates, auto-fix.","https:\u002F\u002Fgithub.com\u002Fashneil12\u002Fvanilla-hermes-agent-canary\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[],[]]