[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M781AS90WR9CK2VH7YVVJNP2":3,"skill-same:01M781AS90WR9CK2VH7YVVJNP2":67},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M781AS90WR9CK2VH7YVVJNP2","actionbook",null,"Browser action engine. Provides up-to-date action manuals for the modern web — operate any website instantly, one tab or dozens, concurrently.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_actionbook_actionbook_actionbook\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: actionbook\ndescription: Browser action engine. Provides up-to-date action manuals for the modern web — operate any website instantly, one tab or dozens, concurrently.\nversion: 1.5.0\nlicense: MIT\nplatforms: [macos, linux, windows]\nmetadata:\n  hermes:\n    tags: [browser-automation, web-automation, scraping, e2e-testing]\n    requires_toolsets: [terminal]\nrequired_environment_variables:\n  - name: ACTIONBOOK_API_KEY\n    prompt: \"Actionbook API key\"\n    help: \"Create one at https:\u002F\u002Factionbook.dev\u002Fdashboard — skill works without it, but requests are rate-limited\"\n    required_for: \"unlimited requests (without a key, public rate limits apply)\"\n    optional: true\n---\n\n## When to Use This Skill\n\nActivate when the user:\n- Needs to do anything on a website (\"Send a LinkedIn message\", \"Book an Airbnb\", \"Search Google for...\")\n- Asks how to interact with a site (\"How do I post a tweet?\", \"How to apply on LinkedIn?\")\n- Wants to fill out forms, click buttons, navigate, search, filter, or browse on a specific site\n- Wants to take a screenshot of a web page or monitor changes\n- Builds browser-based AI agents, web scrapers, or E2E tests for external websites\n- Automates repetitive web tasks (data entry, form submission, content posting)\n- Needs to operate multiple websites or tabs concurrently\n\n## How It Works\n\nActionbook provides **up-to-date action manuals** for the modern web. Action manuals tell agents exactly what to do on a page — no parsing, no guessing.\n\n**Why this matters:**\n- **10x faster** — action manuals provide selectors and page structure upfront. No snapshot-per-step loop needed.\n- **Accurate** — handles SPAs, streaming components, dropdowns, date pickers, and dynamic content reliably.\n- **Concurrent** — stateless architecture with explicit `--session`\u002F`--tab`. Operate dozens of tabs in parallel.\n\nThe workflow:\n1. **Start** a browser session\n2. **Navigate** to the target page\n3. **Snapshot** to get the page structure with element refs\n4. **Automate** using refs from the snapshot\n\nRun `actionbook \u003Ccommand> --help` for full usage and examples of any command.\n\n## Browser Automation\n\nEvery browser command is **stateless** — pass `--session` and `--tab` explicitly. No \"current tab\" — you can run commands on any session\u002Ftab in parallel.\n\n### Start a session\n\n```bash\nactionbook browser start --set-session-id s1\n```\n\nBoth `--session` and `--set-session-id` are get-or-create: they reuse a Running session with the given ID, or create one if not found. If `--profile` is passed and does not match the session's bound profile, the command fails with `SESSION_PROFILE_MISMATCH`.\n\n### Core workflow: snapshot, act, wait\n\n```bash\nactionbook browser goto \u003Curl> --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1          # Get page structure with refs\nactionbook browser fill @e3 \"text\" --session s1 --tab t1   # Use refs from snapshot\nactionbook browser click @e7 --session s1 --tab t1\nactionbook browser wait navigation --session s1 --tab t1   # Wait for page load\n```\n\n### Snapshot refs\n\n`snapshot` labels every element with a ref (e.g. `@e3`, `@e7`). Use these refs as selectors in any command — they are the recommended way to target elements.\n\nRefs are **stable across snapshots** — if the element stays the same, the ref stays the same. This lets you chain multiple commands without re-snapshotting after every step.\n\n### Command categories\n\nAll commands support `--help` for full usage and examples.\n\n| Category | Key commands | Help |\n|----------|-------------|------|\n| Search | `search` | `actionbook search --help` |\n| Manual | `manual` (alias: `man`) | `actionbook manual --help` |\n| Session | `start`, `close`, `restart`, `list-sessions`, `status` | `actionbook browser start --help` |\n| Tab | `new-tab`, `close-tab`, `list-tabs` | `actionbook browser new-tab --help` |\n| Navigation | `goto`, `back`, `forward`, `reload` | `actionbook browser goto --help` |\n| Observation | `snapshot`, `text`, `html`, `value`, `title`, `url`, `viewport`, `attr`, `attrs`, `box`, `styles`, `describe`, `state`, `inspect-point`, `screenshot`, `pdf` | `actionbook browser snapshot --help` |\n| Interaction | `click`, `fill`, `type`, `press`, `select`, `hover`, `focus`, `scroll`, `drag`, `upload`, `eval`, `mouse-move`, `cursor-position` | `actionbook browser click --help` |\n| Wait | `wait element`, `wait navigation`, `wait network-idle`, `wait condition` | `actionbook browser wait element --help` |\n| Cookies | `cookies list`, `cookies get`, `cookies set`, `cookies delete`, `cookies clear` | `actionbook browser cookies list --help` |\n| Storage | `local-storage list\\|get\\|set\\|delete\\|clear`, `session-storage ...` | `actionbook browser local-storage get --help` |\n| Logs | `logs console`, `logs errors` | `actionbook browser logs console --help` |\n| Network | `network requests`, `network request \u003Cid>`, `network har start`, `network har stop` | `actionbook browser network requests --help` |\n| Query | `query one\\|all\\|nth\\|count` | `actionbook browser query --help` |\n| Batch | `batch-new-tab`, `batch-snapshot`, `batch-click` | `actionbook browser batch-new-tab --help` |\n| Extension | `extension status`, `extension ping`, `extension install`, `extension uninstall`, `extension path` | `actionbook extension status --help` |\n| Daemon | `daemon restart` | `actionbook daemon restart --help` |\n\nFull command reference: [command-reference.md](references\u002Fcommand-reference.md)\n\n### Cloud providers\n\nUse `-p` \u002F `--provider` with `browser start` to run sessions on a remote browser instead of launching local Chrome. Supported providers: `driver`, `hyperbrowser`, `browseruse`. Each reads its own `\u003CPROVIDER>_API_KEY` from the shell env.\n\n```bash\nexport HYPERBROWSER_API_KEY=\"your-key\"\nactionbook browser start -p hyperbrowser --session s1\nactionbook browser goto \"https:\u002F\u002Fexample.com\" --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1\n```\n\nAll browser commands work the same way regardless of mode. `browser restart --session \u003Cid>` mints a fresh remote session while preserving the session_id.\n\n## Example: End-to-End\n\nUser request: \"Find a room next week in SF on Airbnb\"\n\n```bash\nactionbook browser start --set-session-id s1\nactionbook browser goto \"https:\u002F\u002Fairbnb.com\" --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1\nactionbook browser fill @e3 \"San Francisco\" --session s1 --tab t1\nactionbook browser click @e7 --session s1 --tab t1\nactionbook browser wait navigation --session s1 --tab t1\n```\n\n## Eval Input Sources\n\n`browser eval` accepts the expression from three mutually-exclusive sources:\n- **Positional**: `actionbook browser eval \"expr\" ...`\n- **`--file`**: `actionbook browser eval --file script.js ...`\n- **Stdin**: `echo 'expr' | actionbook browser eval - ...`\n\n## Eval Error Handling\n\n`browser eval` returns structured error codes on failure — branch on `error.code` instead of parsing the message:\n\n- `EVAL_RUNTIME_ERROR` — JS exception. Inspect the expression before retrying.\n- `EVAL_CROSS_ORIGIN` — cross-origin fetch or CSP block. Proxy the request server-side.\n- `EVAL_RESPONSE_NOT_JSON` \u002F `EVAL_RESPONSE_NOT_OK` — read `error.details.body_head` (first ≤256 chars of the response body) to distinguish 403 \u002F challenge pages \u002F CORS errors. Do not blindly retry.\n- `EVAL_TIMEOUT` — expression exceeded `--timeout`. Reduce work or raise the timeout.\n- `EVAL_ARGS_CONFLICT` — multiple input sources or none. Provide exactly one.\n- `EVAL_FILE_NOT_FOUND` — `--file` path unreadable. Verify the path.\n- `EVAL_STDIN_TTY` — `-` but stdin is a terminal. Pipe the expression.\n- `EVAL_STDIN_EMPTY` — stdin produced empty input. Verify the upstream pipeline.\n\n## CDP Error Handling\n\nBrowser commands that interact with elements, navigate, or communicate via CDP return structured error codes — branch on `error.code`:\n\n- `CDP_NODE_NOT_FOUND` — DOM node is stale. Call `snapshot` to refresh refs then retry.\n- `CDP_NOT_INTERACTABLE` — element exists but can't be acted on. Scroll into view, wait for visibility, or dismiss overlays.\n- `CDP_NAV_TIMEOUT` — navigation timeout. Increase `--timeout` or verify URL reachability. **Retryable.**\n- `CDP_TARGET_CLOSED` — tab navigated away or session torn down mid-command. Start a fresh session. **Retryable.**\n- `CDP_PROTOCOL_ERROR` — CDP response malformed. Inspect `details.reason` and `details.cdp_code`.\n- `CDP_GENERIC` — unclassified CDP error (transport\u002Fparse). No specific remediation.\n\n`CDP_NAV_TIMEOUT` and `CDP_TARGET_CLOSED` are retryable (`error.retryable == true`). All other CDP codes require caller intervention before retrying. When `error.code` is a `CDP_*` code, `error.details` includes `reason` and `cdp_code` when available.\n\n## Selectors\n\nSelectors should come from `actionbook browser snapshot` — not from prior knowledge or memory. Always snapshot first to get current refs, then use those refs to interact with the page.\n\n## Login Page Handling\n\nWhen you hit a login\u002Fauth wall (sign-in page, password prompt, MFA\u002FOTP, CAPTCHA, account chooser):\n\n1. **Pause automation and keep the current browser session open** (same tab\u002Fprofile\u002Fcookies).\n2. **Ask the user to complete login manually** in that same browser window.\n3. After user confirms login is done, **continue in the same session**.\n4. If the post-login page is different, run `actionbook browser snapshot` to get the new page structure before continuing.\n\nDo not switch tools just because a login page appears.\n\n## Session Cleanup\n\n`browser close` is idempotent — closing an unknown or already-closed session returns `ok: true` with a warning in `meta.warnings`, not a fatal error. A typo in the session ID or a session that was already torn down is no longer an error condition.\n\n- Safe to call `browser close` unconditionally during cleanup without checking session existence first.\n- Read `meta.warnings` to distinguish a fresh close from an already-gone session. Do not treat a warning inside an `ok: true` response as a signal that the session is still alive.\n- If another close is already in flight for the same session, the command returns `SESSION_CLOSING` (fatal).\n\n## HAR Recording\n\n`network har start` accepts `--max-entries N` to set the ring-buffer cap (default: 10000). When `har stop` detects dropped entries (`data.dropped > 0`), the envelope includes `meta.truncated = true` and a `HAR_TRUNCATED` warning in `meta.warnings`. Read `data.max_entries` to see the configured cap. Raise `--max-entries` or stop recording sooner to keep the full trace.\n\n## References\n\n| Reference | Description |\n|-----------|-------------|\n| [command-reference.md](references\u002Fcommand-reference.md) | Complete command reference with all flags and options |\n| [authentication.md](references\u002Fauthentication.md) | Login flows, OAuth, 2FA handling, session persistence |\n","## When to Use This Skill\n\nActivate when the user:\n- Needs to do anything on a website (\"Send a LinkedIn message\", \"Book an Airbnb\", \"Search Google for...\")\n- Asks how to interact with a site (\"How do I post a tweet?\", \"How to apply on LinkedIn?\")\n- Wants to fill out forms, click buttons, navigate, search, filter, or browse on a specific site\n- Wants to take a screenshot of a web page or monitor changes\n- Builds browser-based AI agents, web scrapers, or E2E tests for external websites\n- Automates repetitive web tasks (data entry, form submission, content posting)\n- Needs to operate multiple websites or tabs concurrently\n\n## How It Works\n\nActionbook provides **up-to-date action manuals** for the modern web. Action manuals tell agents exactly what to do on a page — no parsing, no guessing.\n\n**Why this matters:**\n- **10x faster** — action manuals provide selectors and page structure upfront. No snapshot-per-step loop needed.\n- **Accurate** — handles SPAs, streaming components, dropdowns, date pickers, and dynamic content reliably.\n- **Concurrent** — stateless architecture with explicit `--session`\u002F`--tab`. Operate dozens of tabs in parallel.\n\nThe workflow:\n1. **Start** a browser session\n2. **Navigate** to the target page\n3. **Snapshot** to get the page structure with element refs\n4. **Automate** using refs from the snapshot\n\nRun `actionbook \u003Ccommand> --help` for full usage and examples of any command.\n\n## Browser Automation\n\nEvery browser command is **stateless** — pass `--session` and `--tab` explicitly. No \"current tab\" — you can run commands on any session\u002Ftab in parallel.\n\n### Start a session\n\n```bash\nactionbook browser start --set-session-id s1\n```\n\nBoth `--session` and `--set-session-id` are get-or-create: they reuse a Running session with the given ID, or create one if not found. If `--profile` is passed and does not match the session's bound profile, the command fails with `SESSION_PROFILE_MISMATCH`.\n\n### Core workflow: snapshot, act, wait\n\n```bash\nactionbook browser goto \u003Curl> --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1          # Get page structure with refs\nactionbook browser fill @e3 \"text\" --session s1 --tab t1   # Use refs from snapshot\nactionbook browser click @e7 --session s1 --tab t1\nactionbook browser wait navigation --session s1 --tab t1   # Wait for page load\n```\n\n### Snapshot refs\n\n`snapshot` labels every element with a ref (e.g. `@e3`, `@e7`). Use these refs as selectors in any command — they are the recommended way to target elements.\n\nRefs are **stable across snapshots** — if the element stays the same, the ref stays the same. This lets you chain multiple commands without re-snapshotting after every step.\n\n### Command categories\n\nAll commands support `--help` for full usage and examples.\n\n| Category | Key commands | Help |\n|----------|-------------|------|\n| Search | `search` | `actionbook search --help` |\n| Manual | `manual` (alias: `man`) | `actionbook manual --help` |\n| Session | `start`, `close`, `restart`, `list-sessions`, `status` | `actionbook browser start --help` |\n| Tab | `new-tab`, `close-tab`, `list-tabs` | `actionbook browser new-tab --help` |\n| Navigation | `goto`, `back`, `forward`, `reload` | `actionbook browser goto --help` |\n| Observation | `snapshot`, `text`, `html`, `value`, `title`, `url`, `viewport`, `attr`, `attrs`, `box`, `styles`, `describe`, `state`, `inspect-point`, `screenshot`, `pdf` | `actionbook browser snapshot --help` |\n| Interaction | `click`, `fill`, `type`, `press`, `select`, `hover`, `focus`, `scroll`, `drag`, `upload`, `eval`, `mouse-move`, `cursor-position` | `actionbook browser click --help` |\n| Wait | `wait element`, `wait navigation`, `wait network-idle`, `wait condition` | `actionbook browser wait element --help` |\n| Cookies | `cookies list`, `cookies get`, `cookies set`, `cookies delete`, `cookies clear` | `actionbook browser cookies list --help` |\n| Storage | `local-storage list\\|get\\|set\\|delete\\|clear`, `session-storage ...` | `actionbook browser local-storage get --help` |\n| Logs | `logs console`, `logs errors` | `actionbook browser logs console --help` |\n| Network | `network requests`, `network request \u003Cid>`, `network har start`, `network har stop` | `actionbook browser network requests --help` |\n| Query | `query one\\|all\\|nth\\|count` | `actionbook browser query --help` |\n| Batch | `batch-new-tab`, `batch-snapshot`, `batch-click` | `actionbook browser batch-new-tab --help` |\n| Extension | `extension status`, `extension ping`, `extension install`, `extension uninstall`, `extension path` | `actionbook extension status --help` |\n| Daemon | `daemon restart` | `actionbook daemon restart --help` |\n\nFull command reference: [command-reference.md](references\u002Fcommand-reference.md)\n\n### Cloud providers\n\nUse `-p` \u002F `--provider` with `browser start` to run sessions on a remote browser instead of launching local Chrome. Supported providers: `driver`, `hyperbrowser`, `browseruse`. Each reads its own `\u003CPROVIDER>_API_KEY` from the shell env.\n\n```bash\nexport HYPERBROWSER_API_KEY=\"your-key\"\nactionbook browser start -p hyperbrowser --session s1\nactionbook browser goto \"https:\u002F\u002Fexample.com\" --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1\n```\n\nAll browser commands work the same way regardless of mode. `browser restart --session \u003Cid>` mints a fresh remote session while preserving the session_id.\n\n## Example: End-to-End\n\nUser request: \"Find a room next week in SF on Airbnb\"\n\n```bash\nactionbook browser start --set-session-id s1\nactionbook browser goto \"https:\u002F\u002Fairbnb.com\" --session s1 --tab t1\nactionbook browser snapshot --session s1 --tab t1\nactionbook browser fill @e3 \"San Francisco\" --session s1 --tab t1\nactionbook browser click @e7 --session s1 --tab t1\nactionbook browser wait navigation --session s1 --tab t1\n```\n\n## Eval Input Sources\n\n`browser eval` accepts the expression from three mutually-exclusive sources:\n- **Positional**: `actionbook browser eval \"expr\" ...`\n- **`--file`**: `actionbook browser eval --file script.js ...`\n- **Stdin**: `echo 'expr' | actionbook browser eval - ...`\n\n## Eval Error Handling\n\n`browser eval` returns structured error codes on failure — branch on `error.code` instead of parsing the message:\n\n- `EVAL_RUNTIME_ERROR` — JS exception. Inspect the expression before retrying.\n- `EVAL_CROSS_ORIGIN` — cross-origin fetch or CSP block. Proxy the request server-side.\n- `EVAL_RESPONSE_NOT_JSON` \u002F `EVAL_RESPONSE_NOT_OK` — read `error.details.body_head` (first ≤256 chars of the response body) to distinguish 403 \u002F challenge pages \u002F CORS errors. Do not blindly retry.\n- `EVAL_TIMEOUT` — expression exceeded `--timeout`. Reduce work or raise the timeout.\n- `EVAL_ARGS_CONFLICT` — multiple input sources or none. Provide exactly one.\n- `EVAL_FILE_NOT_FOUND` — `--file` path unreadable. Verify the path.\n- `EVAL_STDIN_TTY` — `-` but stdin is a terminal. Pipe the expression.\n- `EVAL_STDIN_EMPTY` — stdin produced empty input. Verify the upstream pipeline.\n\n## CDP Error Handling\n\nBrowser commands that interact with elements, navigate, or communicate via CDP return structured error codes — branch on `error.code`:\n\n- `CDP_NODE_NOT_FOUND` — DOM node is stale. Call `snapshot` to refresh refs then retry.\n- `CDP_NOT_INTERACTABLE` — element exists but can't be acted on. Scroll into view, wait for visibility, or dismiss overlays.\n- `CDP_NAV_TIMEOUT` — navigation timeout. Increase `--timeout` or verify URL reachability. **Retryable.**\n- `CDP_TARGET_CLOSED` — tab navigated away or session torn down mid-command. Start a fresh session. **Retryable.**\n- `CDP_PROTOCOL_ERROR` — CDP response malformed. Inspect `details.reason` and `details.cdp_code`.\n- `CDP_GENERIC` — unclassified CDP error (transport\u002Fparse). No specific remediation.\n\n`CDP_NAV_TIMEOUT` and `CDP_TARGET_CLOSED` are retryable (`error.retryable == true`). All other CDP codes require caller intervention before retrying. When `error.code` is a `CDP_*` code, `error.details` includes `reason` and `cdp_code` when available.\n\n## Selectors\n\nSelectors should come from `actionbook browser snapshot` — not from prior knowledge or memory. Always snapshot first to get current refs, then use those refs to interact with the page.\n\n## Login Page Handling\n\nWhen you hit a login\u002Fauth wall (sign-in page, password prompt, MFA\u002FOTP, CAPTCHA, account chooser):\n\n1. **Pause automation and keep the current browser session open** (same tab\u002Fprofile\u002Fcookies).\n2. **Ask the user to complete login manually** in that same browser window.\n3. After user confirms login is done, **continue in the same session**.\n4. If the post-login page is different, run `actionbook browser snapshot` to get the new page structure before continuing.\n\nDo not switch tools just because a login page appears.\n\n## Session Cleanup\n\n`browser close` is idempotent — closing an unknown or already-closed session returns `ok: true` with a warning in `meta.warnings`, not a fatal error. A typo in the session ID or a session that was already torn down is no longer an error condition.\n\n- Safe to call `browser close` unconditionally during cleanup without checking session existence first.\n- Read `meta.warnings` to distinguish a fresh close from an already-gone session. Do not treat a warning inside an `ok: true` response as a signal that the session is still alive.\n- If another close is already in flight for the same session, the command returns `SESSION_CLOSING` (fatal).\n\n## HAR Recording\n\n`network har start` accepts `--max-entries N` to set the ring-buffer cap (default: 10000). When `har stop` detects dropped entries (`data.dropped > 0`), the envelope includes `meta.truncated = true` and a `HAR_TRUNCATED` warning in `meta.warnings`. Read `data.max_entries` to see the configured cap. Raise `--max-entries` or stop recording sooner to keep the full trace.\n\n## References\n\n| Reference | Description |\n|-----------|-------------|\n| [command-reference.md](references\u002Fcommand-reference.md) | Complete command reference with all flags and options |\n| [authentication.md](references\u002Fauthentication.md) | Login flows, OAuth, 2FA handling, session persistence |\n",{"name":5,"license":15,"version":24,"metadata":25,"platforms":34,"description":7,"required_environment_variables":38},"1.5.0",{"hermes":26},{"tags":27,"requires_toolsets":32},[28,29,30,31],"browser-automation","web-automation","scraping","e2e-testing",[33],"terminal",[35,36,37],"macos","linux","windows",[39],{"help":40,"name":41,"prompt":42,"optional":43,"required_for":44},"Create one at https:\u002F\u002Factionbook.dev\u002Fdashboard — skill works without it, but requests are rate-limited","ACTIONBOOK_API_KEY","Actionbook API key",true,"unlimited requests (without a key, public rate limits apply)","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fskills_sh\u002Fs\u002Fskills-sh_actionbook_actionbook_actionbook",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":43},[56,59,62],{"tool":57,"command":58},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill actionbook",{"tool":60,"command":61},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill actionbook",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill actionbook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fskills_sh\u002Fs\u002Fskills-sh_actionbook_actionbook_actionbook\u002FSKILL.md",[],[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\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":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]