[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DNFDXH5CEBT55EY91FH4HM":3,"skill-same:01M7DNFDXH5CEBT55EY91FH4HM":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7DNFDXH5CEBT55EY91FH4HM","vscode-dev-workbench",null,"Use when the user wants to run the vscode.dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local `microsoft\u002Fvscode` sources. Covers starting the dev server, the `vscode-quality=dev` URL, browser-driven interaction patterns, and optionally wiring up a local mock agent host for the Agents window.","DragonBallerZ\u002Fdragon-ide","DragonBallerZ","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F199459338?v=4","01M7DN83GSDPNQH3ACEV21SKTQ","Z McDragon","01M7DN83HDR4KMJAMTCB5S4DCJ",12,"MIT","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fvscode-dev-workbench\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vscode-dev-workbench\ndescription: Use when the user wants to run the vscode.dev server locally and exercise the VS Code workbench or Agents window in the integrated browser against the local `microsoft\u002Fvscode` sources. Covers starting the dev server, the `vscode-quality=dev` URL, browser-driven interaction patterns, and optionally wiring up a local mock agent host for the Agents window.\n---\n\n# Running vscode.dev Against Local VS Code Sources\n\nThe `vscode-dev` repo is the `vscode.dev` server. When run locally with `?vscode-quality=dev`, it serves the VS Code web workbench (or Agents window at `\u002Fagents`) from the **sibling** `microsoft\u002Fvscode` checkout. This is the fastest way to validate web-only changes to the workbench without shipping an Insiders build.\n\n## Layout assumption\n\n`vscode-dev` and `vscode` must be sibling folders:\n\n```\n\u003CworkRoot>\u002F\n  vscode\u002F          # microsoft\u002Fvscode checkout\n  vscode-dev\u002F      # microsoft\u002Fvscode-dev checkout\n```\n\nIf your paths differ, check `server\u002F` in `vscode-dev` for the source root resolution — the `\u002Fvscode-sources\u002F*` route maps to `..\u002Fvscode`.\n\n## Start the dev server\n\n**Critical:** Run `npm run dev` from the **`vscode-dev`** folder, NOT from `vscode`. The `vscode` repo has no `dev` script and will fail with `npm error Missing script: \"dev\"`. Terminal tools that simplify\u002Fstrip leading `cd` into separate commands will silently keep the cwd of a previous terminal — always use an absolute `pushd` or verify with `pwd` before `npm run dev`.\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvscode-dev     # NOT \u002Fpath\u002Fto\u002Fvscode\nnpm run dev                # runs watch + nodemon; serves https:\u002F\u002F127.0.0.1:3000\n```\n\nIf you're driving this through an agent\u002Fterminal tool, prefer:\n\n```bash\npushd \u002Fabsolute\u002Fpath\u002Fto\u002Fvscode-dev >\u002Fdev\u002Fnull && pwd && npm run dev\n```\n\nOn first start you may see one crash like `Cannot find module '.\u002Findexes'` — it's the watcher racing the first build. nodemon restarts automatically once `out\u002F` finishes compiling. The server is ready when `curl -sk -o \u002Fdev\u002Fnull -w \"%{http_code}\" https:\u002F\u002F127.0.0.1:3000\u002F` returns `200`.\n\n## URLs\n\n- `https:\u002F\u002F127.0.0.1:3000\u002F?vscode-quality=dev` — main workbench, local dev sources\n- `https:\u002F\u002F127.0.0.1:3000\u002Fagents?vscode-quality=dev` — Agents window, local dev sources\n- `https:\u002F\u002F127.0.0.1:3000\u002F?vscode-version=\u003Ccommit>` — pinned production commit\n- Add `&vscode-log=trace` for verbose client logging\n\n## Interacting via the integrated browser\n\nUse `open_browser_page` and the standard browser tools.\n\n### Enter inserts a newline in the chat input\n\nThe chat input is a Monaco editor — `page.keyboard.press('Enter')` inserts a newline. To send, click the **Send** button (`a[aria-label^=\"Send\"]`) or use the send keybinding.\n\n### Hard-reloading after a rebuild\n\nThe service worker caches client assets aggressively. A plain reload can still serve stale modules:\n\n```js\nawait page.evaluate(async () => {\n  const regs = await navigator.serviceWorker?.getRegistrations() ?? [];\n  await Promise.all(regs.map(r => r.unregister()));\n  const keys = await caches?.keys() ?? [];\n  await Promise.all(keys.map(k => caches.delete(k)));\n});\nawait page.reload({ waitUntil: 'domcontentloaded' });\n```\n\n### Simulating mobile (only when explicitly requested)\n\nThe integrated browser panel clamps width, so `page.setViewportSize()` and CDP `setDeviceMetricsOverride` narrow the viewport only as far as the panel allows. User-Agent override and touch emulation work fine:\n\n```js\nconst client = await page.context().newCDPSession(page);\nawait client.send('Emulation.setUserAgentOverride', {\n  userAgent: 'Mozilla\u002F5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit\u002F605.1.15 (KHTML, like Gecko) Version\u002F17.0 Mobile\u002F15E148 Safari\u002F604.1',\n  platform: 'iPhone'\n});\nawait client.send('Emulation.setTouchEmulationEnabled', { enabled: true, maxTouchPoints: 5 });\nawait client.send('Emulation.setDeviceMetricsOverride', {\n  width: 393, height: 852, deviceScaleFactor: 3, mobile: true,\n  screenOrientation: { type: 'portraitPrimary', angle: 0 }\n});\nawait page.reload();\n```\n\nFor a true mobile viewport, drive a standalone Playwright script with `devices['iPhone 14 Pro']` instead of the integrated browser. If a mobile-responsive overlay intercepts pointer events during automation, fall back to `{ force: true }` on `click()`.\n\n## Known-noise console messages (ignore)\n\n- `Canceled: Canceled` at `clipboardService.js` — cancelled permission probes on hover.\n- `NotAllowedError: Failed to execute 'write' on 'Clipboard'` — web clipboard requires a user gesture.\n- `[WebTunnelAgentHost] Failed to list tunnels` — only fires when not signed in.\n- `The web worker extension host is started in a same-origin iframe!` — expected in dev.\n- `Unrecognized feature: 'local-network-access'` — dev manifest warning.\n- `[LEAKED DISPOSABLE]` stacks — GC-based tracker; only real if reproducible across reloads.\n\n## Troubleshooting\n\n| Symptom                                                   | Cause                                      | Fix                                                        |\n| --------------------------------------------------------- | ------------------------------------------ | ---------------------------------------------------------- |\n| `Cannot find module '.\u002Findexes'` on first run             | nodemon started before TS compile finished | Wait; it auto-restarts                                     |\n| `Session not found: \u003Cuuid>` when sending chat             | Reopened a cloud\u002Ftunnel-backed session     | Start a fresh session (⌘N) in the Agents window            |\n| Workspace picker opens native dialog and hangs automation | `Select Folder…` needs a real file dialog  | Pick a workspace URL scheme instead, or skip in automation |\n| Stale UI after editing `vscode\u002F` sources                  | Service worker cache                       | Unregister SWs + clear caches (snippet above)              |\n\n## Testing the Agents window against a local mock agent host\n\nIf the scenario touches the Agents window (`\u002Fagents` route), you almost always need the mock agent host running. Without it, the Agents window will sit on the sign-in \u002F tunnel-discovery screen and block any real interaction. Start it **in addition to** the dev server — it's a second terminal, not a replacement.\n\n`vscode-dev` supports a `?mock-agent-host=ws:\u002F\u002F…` URL parameter that short-circuits tunnel discovery and wires the Agents window to a raw WebSocket. Pair it with the mock agent host binary from `microsoft\u002Fvscode`:\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvscode\nnode out\u002Fvs\u002Fplatform\u002FagentHost\u002Fnode\u002FagentHostServerMain.js \\\n  --enable-mock-agent --quiet --without-connection-token --port 8765\n# Listens on ws:\u002F\u002Flocalhost:8765\n```\n\nPrerequisite: `out\u002F` in the `vscode` repo must be populated by the `VS Code - Build` task (or `npm run watch`). If `out\u002Fvs\u002Fplatform\u002FagentHost\u002Fnode\u002FagentHostServerMain.js` is missing, start that task first.\n\n`--enable-mock-agent` registers the `ScriptedMockAgent` from `src\u002Fvs\u002Fplatform\u002FagentHost\u002Ftest\u002Fnode\u002FmockAgent.ts` with one pre-existing session. Seed additional sessions via the `VSCODE_AGENT_HOST_MOCK_SEED_SESSIONS` env var, using a comma-separated list of session URIs (for example, `VSCODE_AGENT_HOST_MOCK_SEED_SESSIONS=mock:\u002F\u002Fpre-1,mock:\u002F\u002Fpre-2`). Scripted prompts include `hello`, `use-tool`, `error`, `permission`, `write-file`, `run-safe-command`, `slow`, `client-tool`, `subagent`, etc. (see `mockAgent.ts` for the full list).\n\nThen open:\n\n```\nhttps:\u002F\u002F127.0.0.1:3000\u002Fagents?vscode-quality=dev&mock-agent-host=ws:\u002F\u002Flocalhost:8765&vscode-log=trace\n```\n\nExpect these logs in order:\n\n- `[MockAgentHost] Using local mock agent host at ws:\u002F\u002Flocalhost:8765\u002F`\n- `[WebTunnelAgentHost] Found 1 tunnel(s) with agent host support`\n- `[WebTunnelAgentHost] Connecting to tunnel 'mock-agent-host' (mock)`\n- `[WebTunnelAgentHost] Protocol handshake completed with tunnel:mock`\n- `[RemoteAgentHost] Registered agent mock from tunnel:mock as remote-tunnel__mock-mock`\n\nThis bypasses GitHub auth and the `\u002Fagents\u002Fapi\u002Fhosts` endpoint entirely, so it works offline. The fake tunnel on the `vscode-dev` side must advertise a `protocolvN` tag ≥ `TUNNEL_MIN_PROTOCOL_VERSION` in `src\u002Fvs\u002Fplatform\u002FagentHost\u002Fcommon\u002FtunnelAgentHost.ts` (currently 5); otherwise `WebTunnelAgentHostService` filters it out and you'll see `Found 0 tunnel(s) with agent host support`.\n","# Running vscode.dev Against Local VS Code Sources\n\nThe `vscode-dev` repo is the `vscode.dev` server. When run locally with `?vscode-quality=dev`, it serves the VS Code web workbench (or Agents window at `\u002Fagents`) from the **sibling** `microsoft\u002Fvscode` checkout. This is the fastest way to validate web-only changes to the workbench without shipping an Insiders build.\n\n## Layout assumption\n\n`vscode-dev` and `vscode` must be sibling folders:\n\n```\n\u003CworkRoot>\u002F\n  vscode\u002F          # microsoft\u002Fvscode checkout\n  vscode-dev\u002F      # microsoft\u002Fvscode-dev checkout\n```\n\nIf your paths differ, check `server\u002F` in `vscode-dev` for the source root resolution — the `\u002Fvscode-sources\u002F*` route maps to `..\u002Fvscode`.\n\n## Start the dev server\n\n**Critical:** Run `npm run dev` from the **`vscode-dev`** folder, NOT from `vscode`. The `vscode` repo has no `dev` script and will fail with `npm error Missing script: \"dev\"`. Terminal tools that simplify\u002Fstrip leading `cd` into separate commands will silently keep the cwd of a previous terminal — always use an absolute `pushd` or verify with `pwd` before `npm run dev`.\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvscode-dev     # NOT \u002Fpath\u002Fto\u002Fvscode\nnpm run dev                # runs watch + nodemon; serves https:\u002F\u002F127.0.0.1:3000\n```\n\nIf you're driving this through an agent\u002Fterminal tool, prefer:\n\n```bash\npushd \u002Fabsolute\u002Fpath\u002Fto\u002Fvscode-dev >\u002Fdev\u002Fnull && pwd && npm run dev\n```\n\nOn first start you may see one crash like `Cannot find module '.\u002Findexes'` — it's the watcher racing the first build. nodemon restarts automatically once `out\u002F` finishes compiling. The server is ready when `curl -sk -o \u002Fdev\u002Fnull -w \"%{http_code}\" https:\u002F\u002F127.0.0.1:3000\u002F` returns `200`.\n\n## URLs\n\n- `https:\u002F\u002F127.0.0.1:3000\u002F?vscode-quality=dev` — main workbench, local dev sources\n- `https:\u002F\u002F127.0.0.1:3000\u002Fagents?vscode-quality=dev` — Agents window, local dev sources\n- `https:\u002F\u002F127.0.0.1:3000\u002F?vscode-version=\u003Ccommit>` — pinned production commit\n- Add `&vscode-log=trace` for verbose client logging\n\n## Interacting via the integrated browser\n\nUse `open_browser_page` and the standard browser tools.\n\n### Enter inserts a newline in the chat input\n\nThe chat input is a Monaco editor — `page.keyboard.press('Enter')` inserts a newline. To send, click the **Send** button (`a[aria-label^=\"Send\"]`) or use the send keybinding.\n\n### Hard-reloading after a rebuild\n\nThe service worker caches client assets aggressively. A plain reload can still serve stale modules:\n\n```js\nawait page.evaluate(async () => {\n  const regs = await navigator.serviceWorker?.getRegistrations() ?? [];\n  await Promise.all(regs.map(r => r.unregister()));\n  const keys = await caches?.keys() ?? [];\n  await Promise.all(keys.map(k => caches.delete(k)));\n});\nawait page.reload({ waitUntil: 'domcontentloaded' });\n```\n\n### Simulating mobile (only when explicitly requested)\n\nThe integrated browser panel clamps width, so `page.setViewportSize()` and CDP `setDeviceMetricsOverride` narrow the viewport only as far as the panel allows. User-Agent override and touch emulation work fine:\n\n```js\nconst client = await page.context().newCDPSession(page);\nawait client.send('Emulation.setUserAgentOverride', {\n  userAgent: 'Mozilla\u002F5.0 (iPhone; CPU iPhone OS 17_0 like Mac OS X) AppleWebKit\u002F605.1.15 (KHTML, like Gecko) Version\u002F17.0 Mobile\u002F15E148 Safari\u002F604.1',\n  platform: 'iPhone'\n});\nawait client.send('Emulation.setTouchEmulationEnabled', { enabled: true, maxTouchPoints: 5 });\nawait client.send('Emulation.setDeviceMetricsOverride', {\n  width: 393, height: 852, deviceScaleFactor: 3, mobile: true,\n  screenOrientation: { type: 'portraitPrimary', angle: 0 }\n});\nawait page.reload();\n```\n\nFor a true mobile viewport, drive a standalone Playwright script with `devices['iPhone 14 Pro']` instead of the integrated browser. If a mobile-responsive overlay intercepts pointer events during automation, fall back to `{ force: true }` on `click()`.\n\n## Known-noise console messages (ignore)\n\n- `Canceled: Canceled` at `clipboardService.js` — cancelled permission probes on hover.\n- `NotAllowedError: Failed to execute 'write' on 'Clipboard'` — web clipboard requires a user gesture.\n- `[WebTunnelAgentHost] Failed to list tunnels` — only fires when not signed in.\n- `The web worker extension host is started in a same-origin iframe!` — expected in dev.\n- `Unrecognized feature: 'local-network-access'` — dev manifest warning.\n- `[LEAKED DISPOSABLE]` stacks — GC-based tracker; only real if reproducible across reloads.\n\n## Troubleshooting\n\n| Symptom                                                   | Cause                                      | Fix                                                        |\n| --------------------------------------------------------- | ------------------------------------------ | ---------------------------------------------------------- |\n| `Cannot find module '.\u002Findexes'` on first run             | nodemon started before TS compile finished | Wait; it auto-restarts                                     |\n| `Session not found: \u003Cuuid>` when sending chat             | Reopened a cloud\u002Ftunnel-backed session     | Start a fresh session (⌘N) in the Agents window            |\n| Workspace picker opens native dialog and hangs automation | `Select Folder…` needs a real file dialog  | Pick a workspace URL scheme instead, or skip in automation |\n| Stale UI after editing `vscode\u002F` sources                  | Service worker cache                       | Unregister SWs + clear caches (snippet above)              |\n\n## Testing the Agents window against a local mock agent host\n\nIf the scenario touches the Agents window (`\u002Fagents` route), you almost always need the mock agent host running. Without it, the Agents window will sit on the sign-in \u002F tunnel-discovery screen and block any real interaction. Start it **in addition to** the dev server — it's a second terminal, not a replacement.\n\n`vscode-dev` supports a `?mock-agent-host=ws:\u002F\u002F…` URL parameter that short-circuits tunnel discovery and wires the Agents window to a raw WebSocket. Pair it with the mock agent host binary from `microsoft\u002Fvscode`:\n\n```bash\ncd \u002Fpath\u002Fto\u002Fvscode\nnode out\u002Fvs\u002Fplatform\u002FagentHost\u002Fnode\u002FagentHostServerMain.js \\\n  --enable-mock-agent --quiet --without-connection-token --port 8765\n# Listens on ws:\u002F\u002Flocalhost:8765\n```\n\nPrerequisite: `out\u002F` in the `vscode` repo must be populated by the `VS Code - Build` task (or `npm run watch`). If `out\u002Fvs\u002Fplatform\u002FagentHost\u002Fnode\u002FagentHostServerMain.js` is missing, start that task first.\n\n`--enable-mock-agent` registers the `ScriptedMockAgent` from `src\u002Fvs\u002Fplatform\u002FagentHost\u002Ftest\u002Fnode\u002FmockAgent.ts` with one pre-existing session. Seed additional sessions via the `VSCODE_AGENT_HOST_MOCK_SEED_SESSIONS` env var, using a comma-separated list of session URIs (for example, `VSCODE_AGENT_HOST_MOCK_SEED_SESSIONS=mock:\u002F\u002Fpre-1,mock:\u002F\u002Fpre-2`). Scripted prompts include `hello`, `use-tool`, `error`, `permission`, `write-file`, `run-safe-command`, `slow`, `client-tool`, `subagent`, etc. (see `mockAgent.ts` for the full list).\n\nThen open:\n\n```\nhttps:\u002F\u002F127.0.0.1:3000\u002Fagents?vscode-quality=dev&mock-agent-host=ws:\u002F\u002Flocalhost:8765&vscode-log=trace\n```\n\nExpect these logs in order:\n\n- `[MockAgentHost] Using local mock agent host at ws:\u002F\u002Flocalhost:8765\u002F`\n- `[WebTunnelAgentHost] Found 1 tunnel(s) with agent host support`\n- `[WebTunnelAgentHost] Connecting to tunnel 'mock-agent-host' (mock)`\n- `[WebTunnelAgentHost] Protocol handshake completed with tunnel:mock`\n- `[RemoteAgentHost] Registered agent mock from tunnel:mock as remote-tunnel__mock-mock`\n\nThis bypasses GitHub auth and the `\u002Fagents\u002Fapi\u002Fhosts` endpoint entirely, so it works offline. The fake tunnel on the `vscode-dev` side must advertise a `protocolvN` tag ≥ `TUNNEL_MIN_PROTOCOL_VERSION` in `src\u002Fvs\u002Fplatform\u002FagentHost\u002Fcommon\u002FtunnelAgentHost.ts` (currently 5); otherwise `WebTunnelAgentHostService` filters it out and you'll see `Found 0 tunnel(s) with agent host support`.\n",{"name":5,"description":7},"main","af285532414d1fa855b4360d86103c12253e6f2f",".github\u002Fskills\u002Fvscode-dev-workbench",0,"https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide","https:\u002F\u002Fgithub.com\u002FDragonBallerZ","https:\u002F\u002Fwww.velloralabs.com","Building Dangerously Disruptive Technology. ","2026-10-23 14:19:51",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add DragonBallerZ\u002Fdragon-ide --skill vscode-dev-workbench",{"tool":39,"command":40},"bunx","bunx skills add DragonBallerZ\u002Fdragon-ide --skill vscode-dev-workbench",{"tool":42,"command":43},"pnpm","pnpm dlx skills add DragonBallerZ\u002Fdragon-ide --skill vscode-dev-workbench","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fvscode-dev-workbench\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DNGQPVJGHW226R8PS3R31F","update-skills","Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says \"learn!\", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fupdate-skills\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DNGP5XJWV3CG63DVS6NR8Y","update-pr","Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fupdate-pr\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DNGJEMNJZR24NBJ7MF5V8R","troubleshoot","Investigate unexpected behavior in the current Copilot agent session by analyzing its event log. Use when the user asks why something happened, why a request was slow, why a tool was or was not used, or why instructions\u002Fskills\u002Fagents did not load.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Ftroubleshoot\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DNGFVCVMFN5J4ZKV27CDR1","sync","Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fsync\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DNGC9GE8EKQED3ZR3KAJ0K","sync-upstream","Update a stale session branch by rebasing onto the latest origin. Use when the upstream has moved significantly and the session needs to catch up, resolving conflicts by preserving upstream changes and adapting session work to fit.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fsync-upstream\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DNG9NJNG1QPJB6C3GFDHVS","merge","Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.","https:\u002F\u002Fgithub.com\u002FDragonBallerZ\u002Fdragon-ide\u002Fblob\u002Fmain\u002Fsrc\u002Fvs\u002Fsessions\u002Fskills\u002Fmerge\u002FSKILL.md",[],[]]