[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77S2C1RH4ZCYMTK02AXAXHV":3,"skill-same:01M77S2C1RH4ZCYMTK02AXAXHV":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M77S2C1RH4ZCYMTK02AXAXHV","firecrawl",null,"Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say \"fetch this page\", \"pull the content from\", \"get the page at https:\u002F\u002F\", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Ffirecrawl\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say \\\"fetch this page\\\", \\\"pull the content from\\\", \\\"get the page at https:\u002F\u002F\\\", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.\\n\"\n---\n# Firecrawl CLI\n\nSearch, scrape, and interact with the web. Returns clean markdown optimized for LLM context windows.\n\nRun `firecrawl --help` or `firecrawl \u003Ccommand> --help` for full option details.\n\nIf the task is to integrate Firecrawl into an application, add `FIRECRAWL_API_KEY` to a project, or choose endpoint usage in product code, use the `firecrawl-build` skills. If the task is an outcome workflow such as deep research, SEO audit, QA, lead generation, knowledge-base creation, dashboard reporting, shopping research, or website design-system extraction, use the `firecrawl-workflows` skills. They are already installed alongside this CLI skill when you run `firecrawl init`.\n\n## Prerequisites\n\nMust be installed. Check with `firecrawl --status`.\n\n```\n  🔥 firecrawl cli v1.8.0\n\n  ● Authenticated via FIRECRAWL_API_KEY\n  Concurrency: 0\u002F100 jobs (parallel scrape limit)\n  Credits: 500,000 remaining\n```\n\n- **Concurrency**: Max parallel jobs. Run parallel operations up to this limit.\n- **Credits**: Remaining API credits. Each operation consumes credits.\n\nAuthenticating gives the best results. Prefer a free account via `firecrawl init --browser` (browser login) or a `FIRECRAWL_API_KEY` whenever the human can sign up. If you cannot obtain a key and the human cannot sign up, you can still search, scrape, and interact without an API key on the keyless free tier (rate-limited). See [agent onboarding](https:\u002F\u002Fwww.firecrawl.dev\u002Fagent-onboarding\u002FSKILL.md) for the full set of onboarding paths.\n\nIf not ready, see [rules\u002Finstall.md](rules\u002Finstall.md). For output handling guidelines, see [rules\u002Fsecurity.md](rules\u002Fsecurity.md).\n\nBefore doing real work, verify the setup with one small request:\n\n```bash\nmkdir -p .firecrawl\nfirecrawl scrape \"https:\u002F\u002Ffirecrawl.dev\" -o .firecrawl\u002Finstall-check.md\n```\n\n```bash\nfirecrawl search \"query\" --scrape --limit 3\n```\n\n## Workflow\n\nFollow this escalation pattern:\n\n1. **Search** - No specific URL yet. Find pages, answer questions, discover sources.\n2. **Scrape** - Have a URL. Extract its content directly.\n3. **Map + Scrape** - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.\n4. **Crawl** - Need bulk content from an entire site section (e.g., all \u002Fdocs\u002F).\n5. **Monitor** - Need recurring checks or ongoing alerts. Prefer setting a monitor with `--page` plus `--goal` instead of doing repeated one-off scrapes.\n6. **Interact** - Scrape first, then interact with the page (pagination, modals, form submissions, multi-step navigation).\n\n| Need                        | Command               | When                                                                    |\n| --------------------------- | --------------------- | ----------------------------------------------------------------------- |\n| Find pages on a topic       | `search`              | No specific URL yet                                                     |\n| Find research papers        | `research`            | Biomedical\u002Fclinical\u002Fscientific literature — never scrape PubMed by hand |\n| Get a page's content        | `scrape`              | Have a URL, page is static or JS-rendered                               |\n| Find URLs within a site     | `map`                 | Need to locate a specific subpage                                       |\n| Bulk extract a site section | `crawl`               | Need many pages (e.g., all \u002Fdocs\u002F)                                      |\n| AI-powered data extraction  | `agent`               | Need structured data from complex sites                                 |\n| Interact with a page        | `scrape` + `interact` | Content requires clicks, form fills, pagination, or login               |\n| Download a site to files    | `download`            | Save an entire site as local files                                      |\n| Parse a local file          | `parse`               | File on disk (PDF, DOCX, XLSX, etc.) — not a URL                        |\n| Watch pages for changes     | `monitor`             | Schedule recurring scrapes\u002Fcrawls, diff against snapshots               |\n\nFor detailed command reference, run `firecrawl \u003Ccommand> --help`.\n\n**Scrape vs interact:**\n\n- Use `scrape` first. It handles static pages and JS-rendered SPAs.\n- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.\n- Never use interact for web searches - use `search` instead.\n\n**Monitor:** Schedule recurring scrapes or crawls and diff each result against the last retained snapshot. Bias toward `monitor` when the user's goal is ongoing change detection, alerting, or repeated checks over time. For a single page, default to setting a monitor with `--page \u003Curl>` and `--goal \"...\"`. Use for product pages, docs, blogs, changelogs, competitor sites — any page where changes matter. Each monitor should include a short `goal` describing what changes matter, and each check labels pages as `same`, `new`, `changed`, `removed`, or `error`, with webhook and email notification options.\n\nWhen writing `--goal`, convert the user's monitoring intent into a concise 2-3 sentence monitor goal, similar to the web app setup flow:\n\n- Start with `Alert when ...` and state what should trigger an alert using the user's stated intent.\n- Restate scope the user mentioned, such as top N, price, role type, company, region, topic, status, or a specific entity.\n- Include an `Ignore ...` sentence only for intent-specific exclusions that are obvious from the request, such as points\u002Fcomments for rankings, unrelated marketing copy for pricing, or general company-page updates for jobs.\n- Do not repeat generic noise exclusions in every goal; the judge already handles whitespace, casing, punctuation, encoding, formatting-only changes, request\u002Fsession IDs, cache busters, tracking params, generic metadata noise, and unrelated page chrome.\n- Do not invent page-specific sections, entities, thresholds, exclusions, or business rules unless the user mentioned them.\n- If the user is vague, keep the goal broad rather than guessing exclusions.\n- If the user asks for \"any change\", preserve that and do not add exclusions.\n- If the user mentions noise they do not care about, include that explicitly.\n\nGood goal examples:\n\n- User intent: `top 10 hackernews stories`\n  Goal: `Alert when stories enter, leave, or change rank within the Hacker News top 10. Ignore points, comments, and timestamps. Do not alert on changes outside the top 10.`\n- User intent: `pricing changes`\n  Goal: `Alert when pricing information changes, including prices, plan names, billing periods, tiers, limits, or included features. Ignore unrelated marketing copy, testimonials, and regional currency display changes unless the underlying offer changes.`\n- User intent: `new engineering roles`\n  Goal: `Alert when a new engineering role is posted. Ignore general company-page updates unless they add, remove, or change an engineering role.`\n- User intent: `track this page`\n  Goal: `Alert when substantive visible content on this page changes.`\n- User intent: `any change`\n  Goal: `Alert when any visible page content changes, including copy, numbers, timestamps, counters, links, and layout text.`\n\nSubcommands: `create | list | get | update | delete | run | checks | check`.\n\n```bash\n# create from flags\nfirecrawl monitor create --name \"Blog\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when a new blog post is published.\" \\\n  --page https:\u002F\u002Fexample.com\u002Fblog --email alerts@example.com\n\n# multiple pages\nfirecrawl monitor create --name \"Product pages\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when pricing, docs, or changelog content changes.\" \\\n  --scrape-urls https:\u002F\u002Fexample.com\u002Fpricing,https:\u002F\u002Fexample.com\u002Fdocs,https:\u002F\u002Fexample.com\u002Fchangelog\n\n# webhook notifications\nfirecrawl monitor create --name \"Docs webhook\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when docs content changes.\" \\\n  --page https:\u002F\u002Fexample.com\u002Fdocs \\\n  --webhook-url https:\u002F\u002Fexample.com\u002Fwebhook \\\n  --webhook-events monitor.page,monitor.check.completed\n\n# or from JSON (positional file, or piped stdin)\nfirecrawl monitor create monitor.json\ncat monitor.json | firecrawl monitor create\n\nfirecrawl monitor list --limit 20\nfirecrawl monitor run \u003CmonitorId>             # trigger a check now\nfirecrawl monitor checks \u003CmonitorId>          # list checks\nfirecrawl monitor check \u003CmonitorId> \u003CcheckId> --page-status changed\nfirecrawl monitor update \u003CmonitorId> --state paused\nfirecrawl monitor delete \u003CmonitorId>\n```\n\nSchedules accept cron (`--cron \"*\u002F5 * * * *\"`) or natural language (`--schedule \"every 5 minutes\"`). Minimum interval is 5 minutes. Targets are `--page \u003Curl>` for one page, `--scrape-urls a,b,c` for multiple scrape URLs, or `--crawl-url \u003Curl>` for a whole-site crawl each check. Use `--goal` for flag-based monitor creation, or include `\"goal\": \"...\"` in JSON payloads. Note: `--state` (not `--status`) sets active\u002Fpaused; `--page-status` (not `--status`) filters page results on `check` — avoids collision with the global `--status` flag. Monitoring is not available for zero-data-retention teams.\n\n**JSON-mode change tracking:** By default monitors diff each page's markdown and you get a unified text diff back. When you care about **specific structured fields** (price, headline, in-stock flag, items in a list) instead of the whole page, add a `changeTracking` format with `modes: [\"json\"]` and a JSON schema to the target's `scrapeOptions.formats`. The flag-based form doesn't cover this — pass a JSON body via file or stdin:\n\n```bash\ncat > pricing-monitor.json \u003C\u003C'EOF'\n{\n  \"name\": \"Pricing watch\",\n  \"goal\": \"Alert when plan prices or headline features change\",\n  \"schedule\": { \"text\": \"hourly\", \"timezone\": \"UTC\" },\n  \"targets\": [{\n    \"type\": \"scrape\",\n    \"urls\": [\"https:\u002F\u002Fexample.com\u002Fpricing\"],\n    \"scrapeOptions\": {\n      \"formats\": [{\n        \"type\": \"changeTracking\",\n        \"modes\": [\"json\"],\n        \"prompt\": \"Extract pricing tiers and headline features for each plan.\",\n        \"schema\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"plans\": {\n              \"type\": \"array\",\n              \"items\": {\n                \"type\": \"object\",\n                \"properties\": {\n                  \"name\":     { \"type\": \"string\" },\n                  \"price\":    { \"type\": \"string\" },\n                  \"features\": { \"type\": \"array\", \"items\": { \"type\": \"string\" } }\n                }\n              }\n            }\n          }\n        }\n      }]\n    }\n  }]\n}\nEOF\nfirecrawl monitor create pricing-monitor.json\n```\n\nThe `check` response then carries a per-field diff (paths like `plans[0].price`) and the full extraction at this run, instead of (or in addition to) a markdown diff. Each changed page in `pages[]` looks like:\n\n```json\n{\n  \"url\": \"https:\u002F\u002Fexample.com\u002Fpricing\",\n  \"status\": \"changed\",\n  \"diff\": {\n    \"json\": {\n      \"plans[0].price\": { \"previous\": \"$19\u002Fmo\", \"current\": \"$24\u002Fmo\" },\n      \"plans[1].features[2]\": {\n        \"previous\": \"10 GB storage\",\n        \"current\": \"25 GB storage\"\n      }\n    }\n  },\n  \"snapshot\": {\n    \"json\": {\n      \"plans\": [\n        \u002F* current full extraction *\u002F\n      ]\n    }\n  }\n}\n```\n\nUse `modes: [\"json\", \"git-diff\"]` for **mixed mode**: you get both `diff.json` (per-field) and `diff.text` (markdown sidecar), and the page is marked `changed` whenever either surface changed. For markdown-only monitors, `diff.text` holds the unified diff and `diff.json` is a `parse-diff` AST (`{ files: [...] }`); there is no `snapshot`.\n\n**Avoid redundant fetches:**\n\n- `search --scrape` already fetches full page content. Don't re-scrape those URLs.\n- Check `.firecrawl\u002F` for existing data before fetching again.\n\n## When to Load References\n\n- **Searching the web or finding sources first** -> [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md)\n- **Finding research papers (biomedical, clinical, or scientific literature; PubMed, bioRxiv, medRxiv, arXiv)** -> `firecrawl research search-papers`, documented in [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md). Do not scrape PubMed or Google Scholar by hand, and do not reach for `search --categories research` — that is a website filter, not the paper index.\n- **Scraping a known URL** -> [firecrawl-scrape](..\u002Ffirecrawl-scrape\u002FSKILL.md)\n- **Finding URLs on a known site** -> [firecrawl-map](..\u002Ffirecrawl-map\u002FSKILL.md)\n- **Bulk extraction from a docs section or site** -> [firecrawl-crawl](..\u002Ffirecrawl-crawl\u002FSKILL.md)\n- **AI-powered structured extraction from complex sites** -> [firecrawl-agent](..\u002Ffirecrawl-agent\u002FSKILL.md)\n- **Clicks, forms, login, pagination, or post-scrape browser actions** -> [firecrawl-interact](..\u002Ffirecrawl-interact\u002FSKILL.md)\n- **Downloading a site to local files** -> [firecrawl-download](..\u002Ffirecrawl-download\u002FSKILL.md)\n- **Parsing a local file (PDF, DOCX, XLSX, HTML, etc.)** -> [firecrawl-parse](..\u002Ffirecrawl-parse\u002FSKILL.md)\n- **Detecting content changes on a website and getting notified by webhook or email (pricing, jobs, posts, docs, status pages, anything ongoing)** -> [firecrawl-monitor](..\u002Ffirecrawl-monitor\u002FSKILL.md)\n- **Install, auth, or setup problems** -> [rules\u002Finstall.md](rules\u002Finstall.md)\n- **Output handling and safe file-reading patterns** -> [rules\u002Fsecurity.md](rules\u002Fsecurity.md)\n- **Integrating Firecrawl into an app, adding `FIRECRAWL_API_KEY` to `.env`, or choosing endpoint usage in product code** -> use the `firecrawl-build` skills (already installed alongside this CLI skill)\n- **Producing Firecrawl-powered deliverables such as research briefs, SEO audits, QA reports, lead lists, knowledge bases, or design-system extraction** -> use the `firecrawl-workflows` skills (already installed alongside this CLI skill). These skills infer from context first and ask only short blocking questions when needed.\n\n## Output & Organization\n\nUnless the user specifies to return in context, write results to `.firecrawl\u002F` with `-o`. Add `.firecrawl\u002F` to `.gitignore`. Always quote URLs - shell interprets `?` and `&` as special characters.\n\n```bash\nfirecrawl search \"react hooks\" -o .firecrawl\u002Fsearch-react-hooks.json --json\nfirecrawl scrape \"\u003Curl>\" -o .firecrawl\u002Fpage.md\n```\n\nNaming conventions:\n\n```\n.firecrawl\u002Fsearch-{query}.json\n.firecrawl\u002Fsearch-{query}-scraped.json\n.firecrawl\u002F{site}-{path}.md\n```\n\nNever read entire output files at once. Use `grep`, `head`, or incremental reads:\n\n```bash\nwc -l .firecrawl\u002Ffile.md && head -50 .firecrawl\u002Ffile.md\ngrep -n \"keyword\" .firecrawl\u002Ffile.md\n```\n\nSingle format outputs raw content. Multiple formats (e.g., `--format markdown,links`) output JSON.\n\n## Working with Results\n\nThese patterns are useful when working with file-based output (`-o` flag) for complex tasks:\n\n```bash\n# Extract URLs from search\njq -r '.data.web[].url' .firecrawl\u002Fsearch.json\n\n# Get titles and URLs\njq -r '.data.web[] | \"\\(.title): \\(.url)\"' .firecrawl\u002Fsearch.json\n```\n\n## After search: send feedback (refunds 1 credit)\n\nSearch costs 2 credits per call. **After you finish using a search result**, send structured feedback in the background. The first feedback per search id refunds 1 credit and feeds search-quality improvements.\n\n```bash\nSEARCH_ID=$(jq -r '.id' .firecrawl\u002Fsearch-react-hooks.json)\n\nfirecrawl search-feedback \"$SEARCH_ID\" \\\n  --rating good \\\n  --valuable-sources '[{\"url\":\"https:\u002F\u002Freact.dev\u002Freference\u002Freact\u002Fhooks\",\"reason\":\"Authoritative\"}]' \\\n  --missing-content '[{\"topic\":\"useDeferredValue example\"},{\"topic\":\"Server Components hooks\"}]' \\\n  --query-suggestions \"Boost react.dev for react-hooks queries\" \\\n  --silent &\n```\n\nThe most useful field is `--missing-content`: an _array_ of specific pieces of content you expected to find but didn't. Use one entry per missing topic. Bad\u002Fpartial feedback with detailed `--missing-content` is just as valuable as good feedback.\n\n**Opt out:** `export FIRECRAWL_NO_SEARCH_FEEDBACK=1` makes the CLI skip every feedback call silently. Respect that flag — do not try to work around it. See [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md) for the full pattern.\n\n## Endpoint job feedback\n\nFor non-search endpoint jobs, use `firecrawl feedback \u003Cendpoint> \u003CjobId>` to send concise job-level feedback through `\u002Fv2\u002Ffeedback`. Supported endpoints are `search`, `scrape`, `parse`, and `map`.\n\n```bash\nfirecrawl feedback scrape \"$SCRAPE_ID\" \\\n  --rating partial \\\n  --issues missing_markdown \\\n  --tags docs \\\n  --note \"The pricing table was missing from the markdown output.\" \\\n  --url \"https:\u002F\u002Fexample.com\u002Fpricing\" \\\n  --page-numbers 1 \\\n  --silent &\n```\n\nKeep generic feedback small: issue codes, tags, short notes, URLs, page numbers, and small metadata objects. Do not send raw scrape\u002Fparse outputs or full page contents as feedback.\n\n**Opt out:** `export FIRECRAWL_NO_ENDPOINT_FEEDBACK=1` makes the CLI skip every endpoint feedback call silently. Respect that flag — do not try to work around it.\n\n## Parallelization\n\nRun independent operations in parallel. Check `firecrawl --status` for concurrency limit:\n\n```bash\nfirecrawl scrape \"\u003Curl-1>\" -o .firecrawl\u002F1.md &\nfirecrawl scrape \"\u003Curl-2>\" -o .firecrawl\u002F2.md &\nfirecrawl scrape \"\u003Curl-3>\" -o .firecrawl\u002F3.md &\nwait\n```\n\nFor interact, scrape multiple pages and interact with each independently using their scrape IDs.\n\n## Credit Usage\n\n```bash\nfirecrawl credit-usage\nfirecrawl credit-usage --json --pretty -o .firecrawl\u002Fcredits.json\n```\n","# Firecrawl CLI\n\nSearch, scrape, and interact with the web. Returns clean markdown optimized for LLM context windows.\n\nRun `firecrawl --help` or `firecrawl \u003Ccommand> --help` for full option details.\n\nIf the task is to integrate Firecrawl into an application, add `FIRECRAWL_API_KEY` to a project, or choose endpoint usage in product code, use the `firecrawl-build` skills. If the task is an outcome workflow such as deep research, SEO audit, QA, lead generation, knowledge-base creation, dashboard reporting, shopping research, or website design-system extraction, use the `firecrawl-workflows` skills. They are already installed alongside this CLI skill when you run `firecrawl init`.\n\n## Prerequisites\n\nMust be installed. Check with `firecrawl --status`.\n\n```\n  🔥 firecrawl cli v1.8.0\n\n  ● Authenticated via FIRECRAWL_API_KEY\n  Concurrency: 0\u002F100 jobs (parallel scrape limit)\n  Credits: 500,000 remaining\n```\n\n- **Concurrency**: Max parallel jobs. Run parallel operations up to this limit.\n- **Credits**: Remaining API credits. Each operation consumes credits.\n\nAuthenticating gives the best results. Prefer a free account via `firecrawl init --browser` (browser login) or a `FIRECRAWL_API_KEY` whenever the human can sign up. If you cannot obtain a key and the human cannot sign up, you can still search, scrape, and interact without an API key on the keyless free tier (rate-limited). See [agent onboarding](https:\u002F\u002Fwww.firecrawl.dev\u002Fagent-onboarding\u002FSKILL.md) for the full set of onboarding paths.\n\nIf not ready, see [rules\u002Finstall.md](rules\u002Finstall.md). For output handling guidelines, see [rules\u002Fsecurity.md](rules\u002Fsecurity.md).\n\nBefore doing real work, verify the setup with one small request:\n\n```bash\nmkdir -p .firecrawl\nfirecrawl scrape \"https:\u002F\u002Ffirecrawl.dev\" -o .firecrawl\u002Finstall-check.md\n```\n\n```bash\nfirecrawl search \"query\" --scrape --limit 3\n```\n\n## Workflow\n\nFollow this escalation pattern:\n\n1. **Search** - No specific URL yet. Find pages, answer questions, discover sources.\n2. **Scrape** - Have a URL. Extract its content directly.\n3. **Map + Scrape** - Large site or need a specific subpage. Use `map --search` to find the right URL, then scrape it.\n4. **Crawl** - Need bulk content from an entire site section (e.g., all \u002Fdocs\u002F).\n5. **Monitor** - Need recurring checks or ongoing alerts. Prefer setting a monitor with `--page` plus `--goal` instead of doing repeated one-off scrapes.\n6. **Interact** - Scrape first, then interact with the page (pagination, modals, form submissions, multi-step navigation).\n\n| Need                        | Command               | When                                                                    |\n| --------------------------- | --------------------- | ----------------------------------------------------------------------- |\n| Find pages on a topic       | `search`              | No specific URL yet                                                     |\n| Find research papers        | `research`            | Biomedical\u002Fclinical\u002Fscientific literature — never scrape PubMed by hand |\n| Get a page's content        | `scrape`              | Have a URL, page is static or JS-rendered                               |\n| Find URLs within a site     | `map`                 | Need to locate a specific subpage                                       |\n| Bulk extract a site section | `crawl`               | Need many pages (e.g., all \u002Fdocs\u002F)                                      |\n| AI-powered data extraction  | `agent`               | Need structured data from complex sites                                 |\n| Interact with a page        | `scrape` + `interact` | Content requires clicks, form fills, pagination, or login               |\n| Download a site to files    | `download`            | Save an entire site as local files                                      |\n| Parse a local file          | `parse`               | File on disk (PDF, DOCX, XLSX, etc.) — not a URL                        |\n| Watch pages for changes     | `monitor`             | Schedule recurring scrapes\u002Fcrawls, diff against snapshots               |\n\nFor detailed command reference, run `firecrawl \u003Ccommand> --help`.\n\n**Scrape vs interact:**\n\n- Use `scrape` first. It handles static pages and JS-rendered SPAs.\n- Use `scrape` + `interact` when you need to interact with a page, such as clicking buttons, filling out forms, navigating through a complex site, infinite scroll, or when scrape fails to grab all the content you need.\n- Never use interact for web searches - use `search` instead.\n\n**Monitor:** Schedule recurring scrapes or crawls and diff each result against the last retained snapshot. Bias toward `monitor` when the user's goal is ongoing change detection, alerting, or repeated checks over time. For a single page, default to setting a monitor with `--page \u003Curl>` and `--goal \"...\"`. Use for product pages, docs, blogs, changelogs, competitor sites — any page where changes matter. Each monitor should include a short `goal` describing what changes matter, and each check labels pages as `same`, `new`, `changed`, `removed`, or `error`, with webhook and email notification options.\n\nWhen writing `--goal`, convert the user's monitoring intent into a concise 2-3 sentence monitor goal, similar to the web app setup flow:\n\n- Start with `Alert when ...` and state what should trigger an alert using the user's stated intent.\n- Restate scope the user mentioned, such as top N, price, role type, company, region, topic, status, or a specific entity.\n- Include an `Ignore ...` sentence only for intent-specific exclusions that are obvious from the request, such as points\u002Fcomments for rankings, unrelated marketing copy for pricing, or general company-page updates for jobs.\n- Do not repeat generic noise exclusions in every goal; the judge already handles whitespace, casing, punctuation, encoding, formatting-only changes, request\u002Fsession IDs, cache busters, tracking params, generic metadata noise, and unrelated page chrome.\n- Do not invent page-specific sections, entities, thresholds, exclusions, or business rules unless the user mentioned them.\n- If the user is vague, keep the goal broad rather than guessing exclusions.\n- If the user asks for \"any change\", preserve that and do not add exclusions.\n- If the user mentions noise they do not care about, include that explicitly.\n\nGood goal examples:\n\n- User intent: `top 10 hackernews stories`\n  Goal: `Alert when stories enter, leave, or change rank within the Hacker News top 10. Ignore points, comments, and timestamps. Do not alert on changes outside the top 10.`\n- User intent: `pricing changes`\n  Goal: `Alert when pricing information changes, including prices, plan names, billing periods, tiers, limits, or included features. Ignore unrelated marketing copy, testimonials, and regional currency display changes unless the underlying offer changes.`\n- User intent: `new engineering roles`\n  Goal: `Alert when a new engineering role is posted. Ignore general company-page updates unless they add, remove, or change an engineering role.`\n- User intent: `track this page`\n  Goal: `Alert when substantive visible content on this page changes.`\n- User intent: `any change`\n  Goal: `Alert when any visible page content changes, including copy, numbers, timestamps, counters, links, and layout text.`\n\nSubcommands: `create | list | get | update | delete | run | checks | check`.\n\n```bash\n# create from flags\nfirecrawl monitor create --name \"Blog\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when a new blog post is published.\" \\\n  --page https:\u002F\u002Fexample.com\u002Fblog --email alerts@example.com\n\n# multiple pages\nfirecrawl monitor create --name \"Product pages\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when pricing, docs, or changelog content changes.\" \\\n  --scrape-urls https:\u002F\u002Fexample.com\u002Fpricing,https:\u002F\u002Fexample.com\u002Fdocs,https:\u002F\u002Fexample.com\u002Fchangelog\n\n# webhook notifications\nfirecrawl monitor create --name \"Docs webhook\" --schedule \"every 5 minutes\" \\\n  --goal \"Alert when docs content changes.\" \\\n  --page https:\u002F\u002Fexample.com\u002Fdocs \\\n  --webhook-url https:\u002F\u002Fexample.com\u002Fwebhook \\\n  --webhook-events monitor.page,monitor.check.completed\n\n# or from JSON (positional file, or piped stdin)\nfirecrawl monitor create monitor.json\ncat monitor.json | firecrawl monitor create\n\nfirecrawl monitor list --limit 20\nfirecrawl monitor run \u003CmonitorId>             # trigger a check now\nfirecrawl monitor checks \u003CmonitorId>          # list checks\nfirecrawl monitor check \u003CmonitorId> \u003CcheckId> --page-status changed\nfirecrawl monitor update \u003CmonitorId> --state paused\nfirecrawl monitor delete \u003CmonitorId>\n```\n\nSchedules accept cron (`--cron \"*\u002F5 * * * *\"`) or natural language (`--schedule \"every 5 minutes\"`). Minimum interval is 5 minutes. Targets are `--page \u003Curl>` for one page, `--scrape-urls a,b,c` for multiple scrape URLs, or `--crawl-url \u003Curl>` for a whole-site crawl each check. Use `--goal` for flag-based monitor creation, or include `\"goal\": \"...\"` in JSON payloads. Note: `--state` (not `--status`) sets active\u002Fpaused; `--page-status` (not `--status`) filters page results on `check` — avoids collision with the global `--status` flag. Monitoring is not available for zero-data-retention teams.\n\n**JSON-mode change tracking:** By default monitors diff each page's markdown and you get a unified text diff back. When you care about **specific structured fields** (price, headline, in-stock flag, items in a list) instead of the whole page, add a `changeTracking` format with `modes: [\"json\"]` and a JSON schema to the target's `scrapeOptions.formats`. The flag-based form doesn't cover this — pass a JSON body via file or stdin:\n\n```bash\ncat > pricing-monitor.json \u003C\u003C'EOF'\n{\n  \"name\": \"Pricing watch\",\n  \"goal\": \"Alert when plan prices or headline features change\",\n  \"schedule\": { \"text\": \"hourly\", \"timezone\": \"UTC\" },\n  \"targets\": [{\n    \"type\": \"scrape\",\n    \"urls\": [\"https:\u002F\u002Fexample.com\u002Fpricing\"],\n    \"scrapeOptions\": {\n      \"formats\": [{\n        \"type\": \"changeTracking\",\n        \"modes\": [\"json\"],\n        \"prompt\": \"Extract pricing tiers and headline features for each plan.\",\n        \"schema\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"plans\": {\n              \"type\": \"array\",\n              \"items\": {\n                \"type\": \"object\",\n                \"properties\": {\n                  \"name\":     { \"type\": \"string\" },\n                  \"price\":    { \"type\": \"string\" },\n                  \"features\": { \"type\": \"array\", \"items\": { \"type\": \"string\" } }\n                }\n              }\n            }\n          }\n        }\n      }]\n    }\n  }]\n}\nEOF\nfirecrawl monitor create pricing-monitor.json\n```\n\nThe `check` response then carries a per-field diff (paths like `plans[0].price`) and the full extraction at this run, instead of (or in addition to) a markdown diff. Each changed page in `pages[]` looks like:\n\n```json\n{\n  \"url\": \"https:\u002F\u002Fexample.com\u002Fpricing\",\n  \"status\": \"changed\",\n  \"diff\": {\n    \"json\": {\n      \"plans[0].price\": { \"previous\": \"$19\u002Fmo\", \"current\": \"$24\u002Fmo\" },\n      \"plans[1].features[2]\": {\n        \"previous\": \"10 GB storage\",\n        \"current\": \"25 GB storage\"\n      }\n    }\n  },\n  \"snapshot\": {\n    \"json\": {\n      \"plans\": [\n        \u002F* current full extraction *\u002F\n      ]\n    }\n  }\n}\n```\n\nUse `modes: [\"json\", \"git-diff\"]` for **mixed mode**: you get both `diff.json` (per-field) and `diff.text` (markdown sidecar), and the page is marked `changed` whenever either surface changed. For markdown-only monitors, `diff.text` holds the unified diff and `diff.json` is a `parse-diff` AST (`{ files: [...] }`); there is no `snapshot`.\n\n**Avoid redundant fetches:**\n\n- `search --scrape` already fetches full page content. Don't re-scrape those URLs.\n- Check `.firecrawl\u002F` for existing data before fetching again.\n\n## When to Load References\n\n- **Searching the web or finding sources first** -> [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md)\n- **Finding research papers (biomedical, clinical, or scientific literature; PubMed, bioRxiv, medRxiv, arXiv)** -> `firecrawl research search-papers`, documented in [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md). Do not scrape PubMed or Google Scholar by hand, and do not reach for `search --categories research` — that is a website filter, not the paper index.\n- **Scraping a known URL** -> [firecrawl-scrape](..\u002Ffirecrawl-scrape\u002FSKILL.md)\n- **Finding URLs on a known site** -> [firecrawl-map](..\u002Ffirecrawl-map\u002FSKILL.md)\n- **Bulk extraction from a docs section or site** -> [firecrawl-crawl](..\u002Ffirecrawl-crawl\u002FSKILL.md)\n- **AI-powered structured extraction from complex sites** -> [firecrawl-agent](..\u002Ffirecrawl-agent\u002FSKILL.md)\n- **Clicks, forms, login, pagination, or post-scrape browser actions** -> [firecrawl-interact](..\u002Ffirecrawl-interact\u002FSKILL.md)\n- **Downloading a site to local files** -> [firecrawl-download](..\u002Ffirecrawl-download\u002FSKILL.md)\n- **Parsing a local file (PDF, DOCX, XLSX, HTML, etc.)** -> [firecrawl-parse](..\u002Ffirecrawl-parse\u002FSKILL.md)\n- **Detecting content changes on a website and getting notified by webhook or email (pricing, jobs, posts, docs, status pages, anything ongoing)** -> [firecrawl-monitor](..\u002Ffirecrawl-monitor\u002FSKILL.md)\n- **Install, auth, or setup problems** -> [rules\u002Finstall.md](rules\u002Finstall.md)\n- **Output handling and safe file-reading patterns** -> [rules\u002Fsecurity.md](rules\u002Fsecurity.md)\n- **Integrating Firecrawl into an app, adding `FIRECRAWL_API_KEY` to `.env`, or choosing endpoint usage in product code** -> use the `firecrawl-build` skills (already installed alongside this CLI skill)\n- **Producing Firecrawl-powered deliverables such as research briefs, SEO audits, QA reports, lead lists, knowledge bases, or design-system extraction** -> use the `firecrawl-workflows` skills (already installed alongside this CLI skill). These skills infer from context first and ask only short blocking questions when needed.\n\n## Output & Organization\n\nUnless the user specifies to return in context, write results to `.firecrawl\u002F` with `-o`. Add `.firecrawl\u002F` to `.gitignore`. Always quote URLs - shell interprets `?` and `&` as special characters.\n\n```bash\nfirecrawl search \"react hooks\" -o .firecrawl\u002Fsearch-react-hooks.json --json\nfirecrawl scrape \"\u003Curl>\" -o .firecrawl\u002Fpage.md\n```\n\nNaming conventions:\n\n```\n.firecrawl\u002Fsearch-{query}.json\n.firecrawl\u002Fsearch-{query}-scraped.json\n.firecrawl\u002F{site}-{path}.md\n```\n\nNever read entire output files at once. Use `grep`, `head`, or incremental reads:\n\n```bash\nwc -l .firecrawl\u002Ffile.md && head -50 .firecrawl\u002Ffile.md\ngrep -n \"keyword\" .firecrawl\u002Ffile.md\n```\n\nSingle format outputs raw content. Multiple formats (e.g., `--format markdown,links`) output JSON.\n\n## Working with Results\n\nThese patterns are useful when working with file-based output (`-o` flag) for complex tasks:\n\n```bash\n# Extract URLs from search\njq -r '.data.web[].url' .firecrawl\u002Fsearch.json\n\n# Get titles and URLs\njq -r '.data.web[] | \"\\(.title): \\(.url)\"' .firecrawl\u002Fsearch.json\n```\n\n## After search: send feedback (refunds 1 credit)\n\nSearch costs 2 credits per call. **After you finish using a search result**, send structured feedback in the background. The first feedback per search id refunds 1 credit and feeds search-quality improvements.\n\n```bash\nSEARCH_ID=$(jq -r '.id' .firecrawl\u002Fsearch-react-hooks.json)\n\nfirecrawl search-feedback \"$SEARCH_ID\" \\\n  --rating good \\\n  --valuable-sources '[{\"url\":\"https:\u002F\u002Freact.dev\u002Freference\u002Freact\u002Fhooks\",\"reason\":\"Authoritative\"}]' \\\n  --missing-content '[{\"topic\":\"useDeferredValue example\"},{\"topic\":\"Server Components hooks\"}]' \\\n  --query-suggestions \"Boost react.dev for react-hooks queries\" \\\n  --silent &\n```\n\nThe most useful field is `--missing-content`: an _array_ of specific pieces of content you expected to find but didn't. Use one entry per missing topic. Bad\u002Fpartial feedback with detailed `--missing-content` is just as valuable as good feedback.\n\n**Opt out:** `export FIRECRAWL_NO_SEARCH_FEEDBACK=1` makes the CLI skip every feedback call silently. Respect that flag — do not try to work around it. See [firecrawl-search](..\u002Ffirecrawl-search\u002FSKILL.md) for the full pattern.\n\n## Endpoint job feedback\n\nFor non-search endpoint jobs, use `firecrawl feedback \u003Cendpoint> \u003CjobId>` to send concise job-level feedback through `\u002Fv2\u002Ffeedback`. Supported endpoints are `search`, `scrape`, `parse`, and `map`.\n\n```bash\nfirecrawl feedback scrape \"$SCRAPE_ID\" \\\n  --rating partial \\\n  --issues missing_markdown \\\n  --tags docs \\\n  --note \"The pricing table was missing from the markdown output.\" \\\n  --url \"https:\u002F\u002Fexample.com\u002Fpricing\" \\\n  --page-numbers 1 \\\n  --silent &\n```\n\nKeep generic feedback small: issue codes, tags, short notes, URLs, page numbers, and small metadata objects. Do not send raw scrape\u002Fparse outputs or full page contents as feedback.\n\n**Opt out:** `export FIRECRAWL_NO_ENDPOINT_FEEDBACK=1` makes the CLI skip every endpoint feedback call silently. Respect that flag — do not try to work around it.\n\n## Parallelization\n\nRun independent operations in parallel. Check `firecrawl --status` for concurrency limit:\n\n```bash\nfirecrawl scrape \"\u003Curl-1>\" -o .firecrawl\u002F1.md &\nfirecrawl scrape \"\u003Curl-2>\" -o .firecrawl\u002F2.md &\nfirecrawl scrape \"\u003Curl-3>\" -o .firecrawl\u002F3.md &\nwait\n```\n\nFor interact, scrape multiple pages and interact with each independently using their scrape IDs.\n\n## Credit Usage\n\n```bash\nfirecrawl credit-usage\nfirecrawl credit-usage --json --pretty -o .firecrawl\u002Fcredits.json\n```\n",{"description":24},"Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say \"fetch this page\", \"pull the content from\", \"get the page at https:\u002F\u002F\", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.\n","main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Ffirecrawl",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill firecrawl",{"tool":39,"command":40},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill firecrawl",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill firecrawl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Ffirecrawl\u002FSKILL.md",true,[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"rules\u002Finstall.md","REFERENCE","参考文档",2230,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Ffirecrawl\u002Frules\u002Finstall.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"rules\u002Fsecurity.md",1395,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Ffirecrawl\u002Frules\u002Fsecurity.md",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]