[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CGRXMQ66FA2CS8EZXH9RCF":3,"skill-same:01M7CGRXMQ66FA2CS8EZXH9RCF":50},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7CGRXMQ66FA2CS8EZXH9RCF","sandbox-migrate-to-next",null,"Migrate Cloudflare Sandbox apps from stable @cloudflare\u002Fsandbox to @cloudflare\u002Fsandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.","harunonsystem\u002Fharunon-harness-slim","harunonsystem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34958457?v=4","01M7CGJNZEEY4GZ845775PPBV1","harunon","01M7CGJP01K9B4N0F5HMNGYC8Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fclaude\u002Fskills\u002Fsandbox-migrate-to-next\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sandbox-migrate-to-next\ndescription: Migrate Cloudflare Sandbox apps from stable @cloudflare\u002Fsandbox to @cloudflare\u002Fsandbox@next (SDK 1.0 preview). Use sandbox-next for apps already on the preview.\n---\n\n# Migrate stable → Sandbox SDK 1.0 preview (`@next`)\n\n**Perform** the port. Follow the steps in order. Depth lives in docs—fetch the linked page when a step needs detail.\n\nHuman guide: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [1.0 preview](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md)\n\n**New projects** should start on `@next` (**`sandbox-next`**), not this skill. **Day-to-day stable work** → **`sandbox-stable`**. Deprecated-API cleanup **without** moving to `@next` → [2026 deprecation guide](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) first if needed.\n\nExisting apps should migrate **when you can**, so you are ready when 1.0 becomes the stable release. Do **not** force production cutover without the user agreeing.\n\n**Prefer installed `@next` types and the migrate doc over memory.**\n\n## Workflow\n\n1. **Review** hard rules and the replacement map  \n2. **Audit** the codebase; list hits and target shapes  \n3. **Clarify** with the user (cutover, bridge, Python image, unclear sites)  \n4. **Upgrade** package, image, and code  \n5. **Validate**  \n\nStop after any step that needs a user decision.\n\n## Hard rules\n\n- Worker package and container image must be the **same** `@next` line.  \n- Production cutover uses **immediate** container rollout. Stable and `@next` control protocols are incompatible both ways; gradual rollout leaves a broken mixed window. In-flight container work can stop.  \n- After cutover, `await sandbox.exec(...)` means process **started**, not command **finished**.  \n- Argv is as-is (no implicit shell). Shell syntax needs an explicit shell binary.  \n- Process handles have **no stdin** → terminals for interactive input.  \n- Observation `timeout` \u002F `AbortSignal` cancel the **wait only**, not the process.  \n- No single retry loop for every error.  \n- Do not invent APIs (`gitCheckout` on core, process stdin, string-exec completion helper).  \n- Self-deployed bridge stays on **stable** (not part of the preview line yet).  \n\n## Replacement map\n\n| Stable | `@next` |\n| ------ | ------- |\n| `SANDBOX_TRANSPORT` \u002F `transport` \u002F `setTransport` | Remove — RPC only |\n| `await sandbox.exec(\"cmd\")` → buffered result | `await sandbox.exec(argv)` → handle, then `output` \u002F waits |\n| `execStream` \u002F `startProcess` | Same handle: `logs`, `waitFor*`, `kill` |\n| Default \u002F named sessions | Gone — `cwd`\u002F`env` per launch, or one shell script |\n| `sandbox.terminal(request)` \u002F session terminal | `createTerminal` + `terminal.connect(request)` |\n| xterm `sessionId` | `terminalId` |\n| Interpreter methods on `Sandbox` | `withInterpreter` → `sandbox.interpreter.*` |\n| `gitCheckout` | argv `git` via `exec` |\n| String kill signals | Numeric only |\n| Files, mounts, backups, ports, tunnels, `proxyToSandbox` | Mostly unchanged (ignore session\u002Ftransport bits on stable pages) |\n\nDepth: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · after port, day-to-day → **`sandbox-next`**\n\n## Audit\n\n```sh\nrg 'SANDBOX_TRANSPORT|transport:|setTransport|enableDefaultSession|createSession|getSession|deleteSession|execStream\\(|startProcess\\(|killProcess\\(|sandbox\\.terminal\\(|sessionId|gitCheckout\\(|SandboxTransport|ExecutionSession'\n```\n\nAlso: string `exec(`, `cd` then a later `exec`, bare `createCodeContext` \u002F `runCode` on `Sandbox`.\n\n## Clarify (ask when needed)\n\n- OK to cut production with `--containers-rollout=immediate` (live processes\u002Fterminals\u002Fstreams may stop)?  \n- Self-deployed bridge? Leave on stable.  \n- Python interpreter → **`-python`** image variant?  \n- Call sites not covered by the map?  \n\n## Upgrade\n\n### Package and image\n\n```sh\nnpm install @cloudflare\u002Fsandbox@next\n```\n\n```dockerfile\nFROM cloudflare\u002Fsandbox:next\n# Python: cloudflare\u002Fsandbox:next-python\n```\n\nSame prerelease tag on Worker and image when not on floating `next`.\n\n### Code by area\n\nApply replacements from the map. For each area, implement from the doc—not from stable habits:\n\n| Area | Doc |\n| ---- | --- |\n| Commands \u002F handles \u002F waits | [Processes](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) · [Processes API](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| `cwd` \u002F `env` \u002F secrets | [Environment](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) · [Outbound traffic](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fguides\u002Foutbound-traffic\u002Findex.md) |\n| Drop sessions | [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [Lifecycle](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Terminals | [Terminals](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Interpreter | [Interpreter](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Errors | [Errors](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Durable job across requests | [Process execution — lifetime \u002F durability](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n\n**Commands (shape):**\n\n```ts\n\u002F\u002F Before (stable)\nconst result = await sandbox.exec(\"npm test\");\n\n\u002F\u002F After (@next)\nconst process = await sandbox.exec([\"\u002Fbin\u002Fbash\", \"-lc\", \"npm test\"]);\nconst result = await process.output({ encoding: \"utf8\" });\n```\n\n```ts\nconst server = await sandbox.exec([\"\u002Fbin\u002Fbash\", \"-lc\", \"npm run dev\"], {\n  cwd: \"\u002Fworkspace\u002Fapp\",\n});\nawait server.waitForPort(3000, { timeout: 60_000 });\nawait server.kill(); \u002F\u002F numeric; default 15\n```\n\n**Terminals (shape):**\n\n```ts\nconst terminal = await sandbox.createTerminal({ command: [\"bash\"], cwd: \"\u002Fworkspace\" });\nconst t = await sandbox.getTerminal(terminal.id);\nif (!t) return new Response(\"terminal gone\", { status: 410 });\nreturn t.connect(request, { cursor, cols, rows });\n```\n\n**Interpreter (shape):**\n\n```ts\nimport { Sandbox as BaseSandbox } from \"@cloudflare\u002Fsandbox\";\nimport { withInterpreter } from \"@cloudflare\u002Fsandbox\u002Finterpreter\";\n\nexport class Sandbox extends BaseSandbox\u003CEnv> {\n  interpreter = withInterpreter(this);\n}\n```\n\n**Git (shape):**\n\n```ts\nconst clone = await sandbox.exec(\n  [\"git\", \"clone\", \"--depth\", \"1\", \"--\", repoUrl, \"\u002Fworkspace\u002Frepo\"],\n  { cwd: \"\u002Fworkspace\" },\n);\nconst result = await clone.output({ encoding: \"utf8\" });\n```\n\nDelete transport settings entirely. Remove session APIs. Isolate users with **separate sandbox IDs**.\n\n### Deploy cutover\n\nStaging\u002Fbranch first. Production is **one** deploy of matching Worker + image:\n\n```sh\nnpx wrangler deploy --containers-rollout=immediate\n```\n\nLeave `rollout_active_grace_period` at default `0` (or set `0` if raised). After cutover, pre-deploy process\u002Fterminal IDs are invalid. Details: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [Container rollouts](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fcontainers\u002Fconfiguration\u002Frollouts\u002Findex.md)\n\n## Validate\n\n1. Lockfile + Dockerfile on the same `@next` line  \n2. Typecheck against `@next`  \n3. Smoke argv `exec` + `output({ encoding: \"utf8\" })`  \n4. Smoke long process \u002F terminal \u002F interpreter if used  \n5. Errors distinguished: unavailable \u002F interrupted-RPC \u002F stale \u002F local wait  \n6. No live secrets in sandbox env  \n7. Grep again for removed APIs  \n8. Production used `--containers-rollout=immediate`  \n\nThen day-to-day work uses **`sandbox-next`**.\n\n## Red flags — stop and fix\n\n- Mixing `@next` Worker with stable image (or reverse)  \n- Gradual container rollout for this cutover  \n- Treating `await exec` as command completion  \n- Assuming `cd` \u002F exports persist across `exec` calls  \n- One retry wrapper for every error  \n- Inventing `gitCheckout`, process stdin, or undocumented APIs  \n- Keeping pre-cutover process\u002Fterminal IDs after deploy  \n- Forcing production cutover without user agreement  \n- Putting live secrets in `setEnvVars` \u002F launch `env`  \n\n## Skill feedback\n\nIf the user reports that this skill gave incorrect or outdated guidance, or is missing information, read [references\u002Fskill-feedback.md](references\u002Fskill-feedback.md).\n","# Migrate stable → Sandbox SDK 1.0 preview (`@next`)\n\n**Perform** the port. Follow the steps in order. Depth lives in docs—fetch the linked page when a step needs detail.\n\nHuman guide: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [1.0 preview](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md)\n\n**New projects** should start on `@next` (**`sandbox-next`**), not this skill. **Day-to-day stable work** → **`sandbox-stable`**. Deprecated-API cleanup **without** moving to `@next` → [2026 deprecation guide](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) first if needed.\n\nExisting apps should migrate **when you can**, so you are ready when 1.0 becomes the stable release. Do **not** force production cutover without the user agreeing.\n\n**Prefer installed `@next` types and the migrate doc over memory.**\n\n## Workflow\n\n1. **Review** hard rules and the replacement map  \n2. **Audit** the codebase; list hits and target shapes  \n3. **Clarify** with the user (cutover, bridge, Python image, unclear sites)  \n4. **Upgrade** package, image, and code  \n5. **Validate**  \n\nStop after any step that needs a user decision.\n\n## Hard rules\n\n- Worker package and container image must be the **same** `@next` line.  \n- Production cutover uses **immediate** container rollout. Stable and `@next` control protocols are incompatible both ways; gradual rollout leaves a broken mixed window. In-flight container work can stop.  \n- After cutover, `await sandbox.exec(...)` means process **started**, not command **finished**.  \n- Argv is as-is (no implicit shell). Shell syntax needs an explicit shell binary.  \n- Process handles have **no stdin** → terminals for interactive input.  \n- Observation `timeout` \u002F `AbortSignal` cancel the **wait only**, not the process.  \n- No single retry loop for every error.  \n- Do not invent APIs (`gitCheckout` on core, process stdin, string-exec completion helper).  \n- Self-deployed bridge stays on **stable** (not part of the preview line yet).  \n\n## Replacement map\n\n| Stable | `@next` |\n| ------ | ------- |\n| `SANDBOX_TRANSPORT` \u002F `transport` \u002F `setTransport` | Remove — RPC only |\n| `await sandbox.exec(\"cmd\")` → buffered result | `await sandbox.exec(argv)` → handle, then `output` \u002F waits |\n| `execStream` \u002F `startProcess` | Same handle: `logs`, `waitFor*`, `kill` |\n| Default \u002F named sessions | Gone — `cwd`\u002F`env` per launch, or one shell script |\n| `sandbox.terminal(request)` \u002F session terminal | `createTerminal` + `terminal.connect(request)` |\n| xterm `sessionId` | `terminalId` |\n| Interpreter methods on `Sandbox` | `withInterpreter` → `sandbox.interpreter.*` |\n| `gitCheckout` | argv `git` via `exec` |\n| String kill signals | Numeric only |\n| Files, mounts, backups, ports, tunnels, `proxyToSandbox` | Mostly unchanged (ignore session\u002Ftransport bits on stable pages) |\n\nDepth: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · after port, day-to-day → **`sandbox-next`**\n\n## Audit\n\n```sh\nrg 'SANDBOX_TRANSPORT|transport:|setTransport|enableDefaultSession|createSession|getSession|deleteSession|execStream\\(|startProcess\\(|killProcess\\(|sandbox\\.terminal\\(|sessionId|gitCheckout\\(|SandboxTransport|ExecutionSession'\n```\n\nAlso: string `exec(`, `cd` then a later `exec`, bare `createCodeContext` \u002F `runCode` on `Sandbox`.\n\n## Clarify (ask when needed)\n\n- OK to cut production with `--containers-rollout=immediate` (live processes\u002Fterminals\u002Fstreams may stop)?  \n- Self-deployed bridge? Leave on stable.  \n- Python interpreter → **`-python`** image variant?  \n- Call sites not covered by the map?  \n\n## Upgrade\n\n### Package and image\n\n```sh\nnpm install @cloudflare\u002Fsandbox@next\n```\n\n```dockerfile\nFROM cloudflare\u002Fsandbox:next\n# Python: cloudflare\u002Fsandbox:next-python\n```\n\nSame prerelease tag on Worker and image when not on floating `next`.\n\n### Code by area\n\nApply replacements from the map. For each area, implement from the doc—not from stable habits:\n\n| Area | Doc |\n| ---- | --- |\n| Commands \u002F handles \u002F waits | [Processes](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) · [Processes API](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| `cwd` \u002F `env` \u002F secrets | [Environment](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) · [Outbound traffic](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fguides\u002Foutbound-traffic\u002Findex.md) |\n| Drop sessions | [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [Lifecycle](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Terminals | [Terminals](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Interpreter | [Interpreter](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Errors | [Errors](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n| Durable job across requests | [Process execution — lifetime \u002F durability](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Findex.md) |\n\n**Commands (shape):**\n\n```ts\n\u002F\u002F Before (stable)\nconst result = await sandbox.exec(\"npm test\");\n\n\u002F\u002F After (@next)\nconst process = await sandbox.exec([\"\u002Fbin\u002Fbash\", \"-lc\", \"npm test\"]);\nconst result = await process.output({ encoding: \"utf8\" });\n```\n\n```ts\nconst server = await sandbox.exec([\"\u002Fbin\u002Fbash\", \"-lc\", \"npm run dev\"], {\n  cwd: \"\u002Fworkspace\u002Fapp\",\n});\nawait server.waitForPort(3000, { timeout: 60_000 });\nawait server.kill(); \u002F\u002F numeric; default 15\n```\n\n**Terminals (shape):**\n\n```ts\nconst terminal = await sandbox.createTerminal({ command: [\"bash\"], cwd: \"\u002Fworkspace\" });\nconst t = await sandbox.getTerminal(terminal.id);\nif (!t) return new Response(\"terminal gone\", { status: 410 });\nreturn t.connect(request, { cursor, cols, rows });\n```\n\n**Interpreter (shape):**\n\n```ts\nimport { Sandbox as BaseSandbox } from \"@cloudflare\u002Fsandbox\";\nimport { withInterpreter } from \"@cloudflare\u002Fsandbox\u002Finterpreter\";\n\nexport class Sandbox extends BaseSandbox\u003CEnv> {\n  interpreter = withInterpreter(this);\n}\n```\n\n**Git (shape):**\n\n```ts\nconst clone = await sandbox.exec(\n  [\"git\", \"clone\", \"--depth\", \"1\", \"--\", repoUrl, \"\u002Fworkspace\u002Frepo\"],\n  { cwd: \"\u002Fworkspace\" },\n);\nconst result = await clone.output({ encoding: \"utf8\" });\n```\n\nDelete transport settings entirely. Remove session APIs. Isolate users with **separate sandbox IDs**.\n\n### Deploy cutover\n\nStaging\u002Fbranch first. Production is **one** deploy of matching Worker + image:\n\n```sh\nnpx wrangler deploy --containers-rollout=immediate\n```\n\nLeave `rollout_active_grace_period` at default `0` (or set `0` if raised). After cutover, pre-deploy process\u002Fterminal IDs are invalid. Details: [Migrate](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fsdk\u002Fmigrate\u002Findex.md) · [Container rollouts](https:\u002F\u002Fdevelopers.cloudflare.com\u002Fcontainers\u002Fconfiguration\u002Frollouts\u002Findex.md)\n\n## Validate\n\n1. Lockfile + Dockerfile on the same `@next` line  \n2. Typecheck against `@next`  \n3. Smoke argv `exec` + `output({ encoding: \"utf8\" })`  \n4. Smoke long process \u002F terminal \u002F interpreter if used  \n5. Errors distinguished: unavailable \u002F interrupted-RPC \u002F stale \u002F local wait  \n6. No live secrets in sandbox env  \n7. Grep again for removed APIs  \n8. Production used `--containers-rollout=immediate`  \n\nThen day-to-day work uses **`sandbox-next`**.\n\n## Red flags — stop and fix\n\n- Mixing `@next` Worker with stable image (or reverse)  \n- Gradual container rollout for this cutover  \n- Treating `await exec` as command completion  \n- Assuming `cd` \u002F exports persist across `exec` calls  \n- One retry wrapper for every error  \n- Inventing `gitCheckout`, process stdin, or undocumented APIs  \n- Keeping pre-cutover process\u002Fterminal IDs after deploy  \n- Forcing production cutover without user agreement  \n- Putting live secrets in `setEnvVars` \u002F launch `env`  \n\n## Skill feedback\n\nIf the user reports that this skill gave incorrect or outdated guidance, or is missing information, read [references\u002Fskill-feedback.md](references\u002Fskill-feedback.md).\n",{"name":5,"description":7},"main","d7d37ad7e79d10fc5b881a8a401979484b6ee1ac","claude\u002Fskills\u002Fsandbox-migrate-to-next","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim","https:\u002F\u002Fgithub.com\u002Fharunonsystem","2026-11-14 07:03:55",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add harunonsystem\u002Fharunon-harness-slim --skill sandbox-migrate-to-next",{"tool":36,"command":37},"bunx","bunx skills add harunonsystem\u002Fharunon-harness-slim --skill sandbox-migrate-to-next",{"tool":39,"command":40},"pnpm","pnpm dlx skills add harunonsystem\u002Fharunon-harness-slim --skill sandbox-migrate-to-next","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fclaude\u002Fskills\u002Fsandbox-migrate-to-next\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Fskill-feedback.md","REFERENCE","参考文档",2826,"https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fclaude\u002Fskills\u002Fsandbox-migrate-to-next\u002Freferences\u002Fskill-feedback.md",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CH39JSS2D4J52SCASDTJ9Q","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"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},"01M7CH36HM1KX4VEFNKNQZ37WP","wrangler","Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fwrangler\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},"01M7CH335A6PP55E1VE1R7EXB1","workflow-modernize","パッケージ\u002FCLI更新時や定期見直し時に、自作スキル・ワークフロー・設定を監査し、不要なworkaroundの撤廃・新機能の適用・プロンプトの簡素化をGrill（壁打ち）と多角比較で提案・修正する。「workflow-modernize」「スキル監査」「ワークフロー改善」「パッケージ更新後の見直し」「モダナイズ」で起動。","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fworkflow-modernize\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},"01M7CH303YN7MP9VCSFAB7KSG7","workers-best-practices","Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fworkers-best-practices\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},"01M7CH2XJPDFMHNRBKZXQD16S0","web-perf","Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fweb-perf\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},"01M7CH2V3AFZB7F055Y9KAFXZ3","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fharunonsystem\u002Fharunon-harness-slim\u002Fblob\u002Fmain\u002Fshared-agents\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[]]