[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJ2E9WA9W6EYGGZ28VHDDN":3,"skill-same:01M6MJ2E9WA9W6EYGGZ28VHDDN":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":58,"ownerHtmlUrl":59,"ownerBlogUrl":60,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6MJ2E9WA9W6EYGGZ28VHDDN","kreuzcrawl",null,"Crawl, scrape, and convert websites to Markdown using the local kreuzcrawl CLI and its MCP server. Use when the user wants to fetch a page, follow links across a domain, enumerate URLs, or drive a real browser. Covers installation, the subcommands (scrape, crawl, map, interact, mcp, serve), output formats (JSON + Markdown), browser fallback, and when to prefer the MCP server over shelling out.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fkreuzcrawl\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"fallback","when","formats","links","local","across","map","domain","real browser","crawl","MCP","fetch","page","markdown","scrape","server","browser","dev","mcp server","cli","2026-11-10 10:12:30",false,"---\nname: kreuzcrawl\ndescription: >-\n  Crawl, scrape, and convert websites to Markdown using the local kreuzcrawl\n  CLI and its MCP server. Use when the user wants to fetch a page, follow\n  links across a domain, enumerate URLs, or drive a real browser. Covers\n  installation, the subcommands (scrape, crawl, map, interact, mcp, serve),\n  output formats (JSON + Markdown), browser fallback, and when to prefer the\n  MCP server over shelling out.\nlicense: MIT\nmetadata:\n  author: kreuzberg-dev\n  version: \"0.1.0\"\n  repository: https:\u002F\u002Fgithub.com\u002Fkreuzberg-dev\u002Fkreuzcrawl\n---\n\n# Kreuzcrawl\n\nKreuzcrawl is a Rust-native web crawler and scraper. It fetches static HTML\nwith `reqwest`, falls back to headless Chrome when a page needs JS or trips a\nWAF, and converts every result to clean Markdown via the built-in\nHTML→Markdown engine.\n\nUse this skill when the user wants to:\n\n- Scrape a single URL to Markdown plus structured metadata.\n- Crawl a site following links bounded by depth, page count, and concurrency.\n- Enumerate URLs from sitemaps without paying for rendering.\n- Drive a real browser (click, type, scroll) and capture the resulting DOM.\n- Run the same operations from another agent harness via MCP tools.\n\n## Installation\n\nThe plugin shells out to a `kreuzcrawl` binary on `PATH`. Install one of:\n\n```bash\nbrew install kreuzberg-dev\u002Ftap\u002Fkreuzcrawl\n# or run without a persistent install (the CLI proxy package self-installs the binary):\nnpx @kreuzberg\u002Fkreuzcrawl-cli --help\nuvx --from kreuzcrawl-cli kreuzcrawl --help\n# or build from source:\ncargo install --git https:\u002F\u002Fgithub.com\u002Fkreuzberg-dev\u002Fkreuzcrawl kreuzcrawl-cli --features all\n```\n\nThe `serve` and `mcp` subcommands are gated behind non-default cargo features\n(`api` and `mcp`). The Homebrew tap is built with all features, so both\nsubcommands work out of the box. A from-source build must pass\n`--features mcp` (and `--features api` for `serve`), or `--features all`, to\ninclude them.\n\nVerify:\n\n```bash\nkreuzcrawl --version\n```\n\nHeadless fallback needs Chrome\u002FChromium reachable locally (`chromiumoxide`\nlaunches it on demand). Skip the install if you only plan to use\n`--browser-mode never`.\n\n## Command map\n\n```text\nkreuzcrawl scrape \u003Curl>     # single page → JSON or Markdown\nkreuzcrawl crawl \u003Curl...>   # follow links, BFS, depth-bounded\nkreuzcrawl map \u003Curl>        # enumerate URLs via sitemaps + link extraction\nkreuzcrawl interact \u003Curl>   # browser actions: click, type, scroll\nkreuzcrawl mcp              # MCP server (stdio) — auto-registered (`mcp` feature)\nkreuzcrawl serve            # REST API server (`api` feature)\n```\n\nBatch behaviour is built into `crawl`: pass multiple seed URLs and the engine\nfans out via `batch_crawl` internally.\n\n### Shared flags\n\n| Flag                    | Default  | Notes                                              |\n| ----------------------- | -------- | -------------------------------------------------- |\n| `--format`              | `json`   | `json` or `markdown`.                              |\n| `--timeout`             | `30000`  | Request timeout in milliseconds.                   |\n| `--browser-mode`        | `auto`   | `auto`, `always`, or `never`.                      |\n| `--browser-endpoint`    | —        | Optional CDP `ws:\u002F\u002F` or `wss:\u002F\u002F` URL.              |\n| `--respect-robots-txt`  | off      | Pass to obey `robots.txt`.                         |\n| `--config \u003Cjson>`       | —        | Inline JSON or `@file.json` to override defaults.  |\n\nThe `--config` flag accepts the full `CrawlConfig` schema. Anything you set\nexplicitly on the CLI overrides the corresponding JSON field.\n\n## Scrape a single page\n\n```bash\nkreuzcrawl scrape https:\u002F\u002Fexample.com --format markdown\n```\n\nJSON output (default) carries the rendered Markdown, page metadata\n(`PageMetadata`), links by category, images, feeds, JSON-LD blocks, and\nHTTP response metadata. Use Markdown output when piping into a file the user\nwill read.\n\nSee the `scraping-html-to-markdown` skill for the full flag surface.\n\n## Crawl a site\n\n```bash\nkreuzcrawl crawl https:\u002F\u002Fexample.com \\\n  --depth 3 --max-pages 200 --concurrent 8 --rate-limit 250 \\\n  --stay-on-domain --respect-robots-txt --format markdown\n```\n\nCrawling is BFS by default, bounded by `--depth`, `--max-pages`, and\n`--concurrent`. Per-domain politeness is enforced by `--rate-limit`\n(milliseconds between requests to the same origin).\n\nSee the `crawling-a-site` skill for the recommended defaults and the full\nflag surface.\n\n## Map URLs\n\n```bash\nkreuzcrawl map https:\u002F\u002Fexample.com --limit 500 --search docs --format markdown\n```\n\n`map` reads `sitemap.xml` (and nested sitemaps), then falls back to link\nextraction from the seed page. It does not render pages — use it to plan a\ncrawl or to feed URLs into another tool.\n\n## Browser interaction\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#load-more\"},\n              {\"type\":\"wait\",\"milliseconds\":500},\n              {\"type\":\"scrape\"}]'\n```\n\nAction types are `click`, `type`, `press`, `scroll`, `wait`, `screenshot`,\n`executeJs`, and `scrape` (to wait for an element, use `wait` with a\n`selector` field). The result wraps the final HTML under\n`interaction.final_html`. See the `automating-the-browser` skill for the full\naction schema and limits.\n\n## MCP server\n\nWhen this plugin is installed in a Claude Code \u002F Codex \u002F Cursor \u002F Gemini \u002F\nopencode harness, the MCP server is auto-registered:\n\n```text\nkreuzcrawl mcp\n```\n\n`mcp` is a stdio-transport server and takes no arguments. It requires a binary\nbuilt with the `mcp` feature (see Installation).\n\nPrefer MCP tools over shelling out when both are available:\n\n- Typed schemas surface argument errors before the call.\n- Results stream back as structured tool output instead of stdout text.\n- No `--format` juggling — the harness pulls whatever shape it needs.\n\nFall back to the CLI when you need to script a pipeline, capture stderr, or\nchain with shell tools.\n\n## Headless fallback\n\nIn `--browser-mode auto` (default), the engine:\n\n1. Fetches statically via `reqwest`.\n2. Detects WAF blocks (8 vendors) and JS-only shells.\n3. Re-fetches through headless Chrome with a real fingerprint when needed.\n\nForce the browser path with `--browser-mode always` when you already know\nthe page needs JS. Use `--browser-mode never` for hot loops where the cost\nof a stray Chrome launch is unacceptable.\n\nPoint `--browser-endpoint ws:\u002F\u002Fhost:9222\u002Fdevtools\u002Fbrowser\u002F\u003Cid>` at an\nalready-running Chrome to skip the local launch.\n\nSee the `headless-fallback` skill for symptoms, costs, and external-CDP\npatterns.\n\n## Output formats\n\n| Mode       | Use when                                                |\n| ---------- | ------------------------------------------------------- |\n| `json`     | Downstream consumer needs metadata, links, images, etc. |\n| `markdown` | Human reader or LLM-context payload.                    |\n\nMarkdown output skips metadata. If you need both, run with `--format json`\nand read `result.markdown.content`.\n\n## Robots, rate limits, ethics\n\n- `--respect-robots-txt` is off by default; pass it for any crawl on a host\n  you do not own.\n- The default `--rate-limit 200` already produces a polite cadence; raise it\n  for shared hosts.\n- Identify the crawler honestly via `--user-agent`. Do not impersonate a\n  browser unless the operator has approved it.\n\n## Cross-references\n\n- `skills\u002Fcrawling-a-site\u002FSKILL.md` — multi-page crawl with depth, page\n  caps, concurrency, rate limits, and domain scoping.\n- `skills\u002Fscraping-html-to-markdown\u002FSKILL.md` — single-page rendering, the\n  Markdown output shape, and common pitfalls.\n- `skills\u002Fmapping-urls\u002FSKILL.md` — `map`: sitemap + link URL discovery,\n  filtering, and seeding a crawl.\n- `skills\u002Fautomating-the-browser\u002FSKILL.md` — `interact`: the full scripted\n  action schema, limits, and result shape.\n- `skills\u002Fserving-the-api\u002FSKILL.md` — `serve`: the Firecrawl-v1-compatible\n  REST API server and its endpoints.\n- `skills\u002Fheadless-fallback\u002FSKILL.md` — when and how to force the browser\n  backend.\n","# Kreuzcrawl\n\nKreuzcrawl is a Rust-native web crawler and scraper. It fetches static HTML\nwith `reqwest`, falls back to headless Chrome when a page needs JS or trips a\nWAF, and converts every result to clean Markdown via the built-in\nHTML→Markdown engine.\n\nUse this skill when the user wants to:\n\n- Scrape a single URL to Markdown plus structured metadata.\n- Crawl a site following links bounded by depth, page count, and concurrency.\n- Enumerate URLs from sitemaps without paying for rendering.\n- Drive a real browser (click, type, scroll) and capture the resulting DOM.\n- Run the same operations from another agent harness via MCP tools.\n\n## Installation\n\nThe plugin shells out to a `kreuzcrawl` binary on `PATH`. Install one of:\n\n```bash\nbrew install kreuzberg-dev\u002Ftap\u002Fkreuzcrawl\n# or run without a persistent install (the CLI proxy package self-installs the binary):\nnpx @kreuzberg\u002Fkreuzcrawl-cli --help\nuvx --from kreuzcrawl-cli kreuzcrawl --help\n# or build from source:\ncargo install --git https:\u002F\u002Fgithub.com\u002Fkreuzberg-dev\u002Fkreuzcrawl kreuzcrawl-cli --features all\n```\n\nThe `serve` and `mcp` subcommands are gated behind non-default cargo features\n(`api` and `mcp`). The Homebrew tap is built with all features, so both\nsubcommands work out of the box. A from-source build must pass\n`--features mcp` (and `--features api` for `serve`), or `--features all`, to\ninclude them.\n\nVerify:\n\n```bash\nkreuzcrawl --version\n```\n\nHeadless fallback needs Chrome\u002FChromium reachable locally (`chromiumoxide`\nlaunches it on demand). Skip the install if you only plan to use\n`--browser-mode never`.\n\n## Command map\n\n```text\nkreuzcrawl scrape \u003Curl>     # single page → JSON or Markdown\nkreuzcrawl crawl \u003Curl...>   # follow links, BFS, depth-bounded\nkreuzcrawl map \u003Curl>        # enumerate URLs via sitemaps + link extraction\nkreuzcrawl interact \u003Curl>   # browser actions: click, type, scroll\nkreuzcrawl mcp              # MCP server (stdio) — auto-registered (`mcp` feature)\nkreuzcrawl serve            # REST API server (`api` feature)\n```\n\nBatch behaviour is built into `crawl`: pass multiple seed URLs and the engine\nfans out via `batch_crawl` internally.\n\n### Shared flags\n\n| Flag                    | Default  | Notes                                              |\n| ----------------------- | -------- | -------------------------------------------------- |\n| `--format`              | `json`   | `json` or `markdown`.                              |\n| `--timeout`             | `30000`  | Request timeout in milliseconds.                   |\n| `--browser-mode`        | `auto`   | `auto`, `always`, or `never`.                      |\n| `--browser-endpoint`    | —        | Optional CDP `ws:\u002F\u002F` or `wss:\u002F\u002F` URL.              |\n| `--respect-robots-txt`  | off      | Pass to obey `robots.txt`.                         |\n| `--config \u003Cjson>`       | —        | Inline JSON or `@file.json` to override defaults.  |\n\nThe `--config` flag accepts the full `CrawlConfig` schema. Anything you set\nexplicitly on the CLI overrides the corresponding JSON field.\n\n## Scrape a single page\n\n```bash\nkreuzcrawl scrape https:\u002F\u002Fexample.com --format markdown\n```\n\nJSON output (default) carries the rendered Markdown, page metadata\n(`PageMetadata`), links by category, images, feeds, JSON-LD blocks, and\nHTTP response metadata. Use Markdown output when piping into a file the user\nwill read.\n\nSee the `scraping-html-to-markdown` skill for the full flag surface.\n\n## Crawl a site\n\n```bash\nkreuzcrawl crawl https:\u002F\u002Fexample.com \\\n  --depth 3 --max-pages 200 --concurrent 8 --rate-limit 250 \\\n  --stay-on-domain --respect-robots-txt --format markdown\n```\n\nCrawling is BFS by default, bounded by `--depth`, `--max-pages`, and\n`--concurrent`. Per-domain politeness is enforced by `--rate-limit`\n(milliseconds between requests to the same origin).\n\nSee the `crawling-a-site` skill for the recommended defaults and the full\nflag surface.\n\n## Map URLs\n\n```bash\nkreuzcrawl map https:\u002F\u002Fexample.com --limit 500 --search docs --format markdown\n```\n\n`map` reads `sitemap.xml` (and nested sitemaps), then falls back to link\nextraction from the seed page. It does not render pages — use it to plan a\ncrawl or to feed URLs into another tool.\n\n## Browser interaction\n\n```bash\nkreuzcrawl interact https:\u002F\u002Fexample.com \\\n  --actions '[{\"type\":\"click\",\"selector\":\"#load-more\"},\n              {\"type\":\"wait\",\"milliseconds\":500},\n              {\"type\":\"scrape\"}]'\n```\n\nAction types are `click`, `type`, `press`, `scroll`, `wait`, `screenshot`,\n`executeJs`, and `scrape` (to wait for an element, use `wait` with a\n`selector` field). The result wraps the final HTML under\n`interaction.final_html`. See the `automating-the-browser` skill for the full\naction schema and limits.\n\n## MCP server\n\nWhen this plugin is installed in a Claude Code \u002F Codex \u002F Cursor \u002F Gemini \u002F\nopencode harness, the MCP server is auto-registered:\n\n```text\nkreuzcrawl mcp\n```\n\n`mcp` is a stdio-transport server and takes no arguments. It requires a binary\nbuilt with the `mcp` feature (see Installation).\n\nPrefer MCP tools over shelling out when both are available:\n\n- Typed schemas surface argument errors before the call.\n- Results stream back as structured tool output instead of stdout text.\n- No `--format` juggling — the harness pulls whatever shape it needs.\n\nFall back to the CLI when you need to script a pipeline, capture stderr, or\nchain with shell tools.\n\n## Headless fallback\n\nIn `--browser-mode auto` (default), the engine:\n\n1. Fetches statically via `reqwest`.\n2. Detects WAF blocks (8 vendors) and JS-only shells.\n3. Re-fetches through headless Chrome with a real fingerprint when needed.\n\nForce the browser path with `--browser-mode always` when you already know\nthe page needs JS. Use `--browser-mode never` for hot loops where the cost\nof a stray Chrome launch is unacceptable.\n\nPoint `--browser-endpoint ws:\u002F\u002Fhost:9222\u002Fdevtools\u002Fbrowser\u002F\u003Cid>` at an\nalready-running Chrome to skip the local launch.\n\nSee the `headless-fallback` skill for symptoms, costs, and external-CDP\npatterns.\n\n## Output formats\n\n| Mode       | Use when                                                |\n| ---------- | ------------------------------------------------------- |\n| `json`     | Downstream consumer needs metadata, links, images, etc. |\n| `markdown` | Human reader or LLM-context payload.                    |\n\nMarkdown output skips metadata. If you need both, run with `--format json`\nand read `result.markdown.content`.\n\n## Robots, rate limits, ethics\n\n- `--respect-robots-txt` is off by default; pass it for any crawl on a host\n  you do not own.\n- The default `--rate-limit 200` already produces a polite cadence; raise it\n  for shared hosts.\n- Identify the crawler honestly via `--user-agent`. Do not impersonate a\n  browser unless the operator has approved it.\n\n## Cross-references\n\n- `skills\u002Fcrawling-a-site\u002FSKILL.md` — multi-page crawl with depth, page\n  caps, concurrency, rate limits, and domain scoping.\n- `skills\u002Fscraping-html-to-markdown\u002FSKILL.md` — single-page rendering, the\n  Markdown output shape, and common pitfalls.\n- `skills\u002Fmapping-urls\u002FSKILL.md` — `map`: sitemap + link URL discovery,\n  filtering, and seeding a crawl.\n- `skills\u002Fautomating-the-browser\u002FSKILL.md` — `interact`: the full scripted\n  action schema, limits, and result shape.\n- `skills\u002Fserving-the-api\u002FSKILL.md` — `serve`: the Firecrawl-v1-compatible\n  REST API server and its endpoints.\n- `skills\u002Fheadless-fallback\u002FSKILL.md` — when and how to force the browser\n  backend.\n",{"name":5,"license":15,"metadata":49,"description":7},{"author":50,"version":51,"repository":52},"kreuzberg-dev","0.1.0","https:\u002F\u002Fgithub.com\u002Fkreuzberg-dev\u002Fkreuzcrawl","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fkreuzcrawl",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill kreuzcrawl",{"tool":69,"command":70},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill kreuzcrawl",{"tool":72,"command":73},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill kreuzcrawl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fkreuzberg-dev\u002Fplugins\u002Fplugins\u002Fkreuzcrawl\u002Fskills\u002Fkreuzcrawl\u002FSKILL.md",true,[],[78,87,95,103,111,119],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":86},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":86},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":99,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":86},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":107,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":86},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":115,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":86},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":86},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]