[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D97VC54S76FFX13G539PXK":3,"skill-same:01M7D97VC54S76FFX13G539PXK":78},{"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":56,"commitSha":57,"skillDirectory":58,"forksCount":14,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M7D97VC54S76FFX13G539PXK","Playwright test.step & Reporting",null,"Teaches the agent to structure tests with test.step, attach evidence and annotations via test.info, use soft assertions, and produce readable, debuggable Playwright HTML reports.","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"MIT","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fplaywright-test-step\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: Playwright test.step & Reporting\ndescription: Teaches the agent to structure tests with test.step, attach evidence and annotations via test.info, use soft assertions, and produce readable, debuggable Playwright HTML reports.\nversion: 1.0.0\nauthor: thetestingacademy\nlicense: MIT\ntags: [playwright, test-step, reporting, annotations, attachments, soft-assertions, test-info, traceability]\ntestingTypes: [e2e, integration]\nframeworks: [playwright]\nlanguages: [typescript]\ndomains: [web]\nagents: [claude-code, cursor, github-copilot, windsurf, codex, aider, continue, cline, zed, bolt, gemini-cli, amp]\n---\n\n# Playwright test.step & Reporting\n\nThis skill makes the agent produce tests that *explain themselves in the report*. Instead of a flat wall of actions, the agent groups logical phases with `test.step`, attaches screenshots\u002FJSON\u002Fdiffs via `testInfo.attach`, records `annotations` for traceability, and uses `expect.soft` to collect multiple failures in one run. When a test fails in CI, a human should understand what happened from the HTML report alone.\n\nUse this skill when writing non-trivial flows, when a test is hard to debug from its output, or when the user mentions reports, steps, annotations, attachments, or issue traceability.\n\n## Core Principles\n\n1. **Every logical phase is a `test.step`.** Steps appear as a collapsible tree in the HTML report with timings, turning a failure into \"which step failed\" instead of \"which line number.\"\n2. **Attach evidence, do not just log it.** `console.log` is invisible in the report; `testInfo.attach` puts screenshots, JSON, and text into the report next to the step.\n3. **Use `expect.soft` to gather multiple defects** in one execution, but end critical paths with a hard assertion or `expect.poll` so the test still fails.\n4. **Annotate for traceability.** Link tests to issues\u002Frequirements with `annotation`, and use `test.info().annotations` to surface skips\u002Fknown-issues in the report.\n5. **Steps should be named like a test plan** — imperative, business-readable (\"Add Pro plan to cart\"), not \"click button #3\".\n6. **Box internal helper steps** so a failure points at the caller, not deep inside the helper.\n\n## Workflow \u002F Patterns\n\n### Pattern 1 — Structure a flow with `test.step`\n\nSteps nest and report their own duration. Return values from a step to chain them.\n\n```typescript\nimport { test, expect } from '@playwright\u002Ftest';\n\ntest('checkout flow', async ({ page }) => {\n  await test.step('Sign in', async () => {\n    await page.goto('https:\u002F\u002Fshop.example.com\u002Flogin');\n    await page.getByLabel('Email').fill('buyer@example.com');\n    await page.getByLabel('Password').fill('Secret123!');\n    await page.getByRole('button', { name: 'Sign in' }).click();\n    await expect(page.getByText('Welcome back')).toBeVisible();\n  });\n\n  const orderId = await test.step('Place order for Pro plan', async () => {\n    await page.getByRole('link', { name: 'Pro plan' }).click();\n    await page.getByRole('button', { name: 'Buy now' }).click();\n    await page.getByRole('button', { name: 'Confirm purchase' }).click();\n    const id = await page.getByTestId('order-id').textContent();\n    return id!.trim();\n  });\n\n  await test.step(`Verify order ${orderId} in history`, async () => {\n    await page.goto('https:\u002F\u002Fshop.example.com\u002Forders');\n    await expect(page.getByText(orderId)).toBeVisible();\n  });\n});\n```\n\n### Pattern 2 — Attach evidence with `testInfo.attach`\n\nAttachments render inline in the HTML report. Attach a screenshot, the API response, or a computed diff at the moment it matters.\n\n```typescript\ntest('attaches evidence to the report', async ({ page }, testInfo) => {\n  await page.goto('https:\u002F\u002Fexample.com\u002Fdashboard');\n\n  await test.step('Capture dashboard state', async () => {\n    \u002F\u002F Screenshot attachment (shown inline in the report).\n    await testInfo.attach('dashboard.png', {\n      body: await page.screenshot({ fullPage: true }),\n      contentType: 'image\u002Fpng',\n    });\n\n    \u002F\u002F JSON attachment — the raw API payload behind the screen.\n    const widgets = await page.evaluate(() => (window as any).__WIDGETS__ ?? []);\n    await testInfo.attach('widgets.json', {\n      body: JSON.stringify(widgets, null, 2),\n      contentType: 'application\u002Fjson',\n    });\n\n    \u002F\u002F Plain-text attachment for a human-readable note.\n    await testInfo.attach('environment.txt', {\n      body: `Project: ${testInfo.project.name}\\nBase URL: ${page.url()}`,\n      contentType: 'text\u002Fplain',\n    });\n  });\n});\n```\n\n### Pattern 3 — Soft assertions to collect multiple failures\n\n`expect.soft` records the failure and keeps going. End the test with `expect(test.info().errors).toHaveLength(0)` or a hard check so it still fails — and the report shows *every* problem at once.\n\n```typescript\ntest('validates a form with soft assertions', async ({ page }) => {\n  await page.goto('https:\u002F\u002Fexample.com\u002Fprofile');\n\n  await test.step('Verify all profile fields at once', async () => {\n    await expect.soft(page.getByLabel('Display name')).toHaveValue('Ada Lovelace');\n    await expect.soft(page.getByLabel('Email')).toHaveValue('ada@example.com');\n    await expect.soft(page.getByLabel('Timezone')).toHaveValue('UTC');\n    await expect.soft(page.getByRole('img', { name: 'Avatar' })).toBeVisible();\n  });\n\n  \u002F\u002F Hard gate: fail the test if any soft assertion failed.\n  expect(test.info().errors).toHaveLength(0);\n});\n```\n\n### Pattern 4 — Annotations for traceability and known issues\n\nAnnotations attach metadata to a test; they show up in the report and JSON output. Use them to link issues and to document why something is skipped.\n\n```typescript\ntest('payment retries on gateway 503', async ({ page }) => {\n  test.info().annotations.push(\n    { type: 'issue', description: 'https:\u002F\u002Fgithub.com\u002Facme\u002Fapp\u002Fissues\u002F4821' },\n    { type: 'suite', description: 'payments-regression' },\n  );\n\n  await page.goto('https:\u002F\u002Fexample.com\u002Fpay');\n  await expect(page.getByRole('button', { name: 'Pay' })).toBeEnabled();\n});\n\ntest('legacy export still works', async ({ page }) => {\n  test.skip(process.env.LEGACY !== 'on', 'Legacy export disabled in this env');\n  test.info().annotations.push({ type: 'known-issue', description: 'Slow > 5s, tracked in #5102' });\n  await page.goto('https:\u002F\u002Fexample.com\u002Fexport');\n  await expect(page.getByText('Export ready')).toBeVisible({ timeout: 30_000 });\n});\n```\n\n### Pattern 5 — Box helper steps so failures point at the caller\n\nA `boxed` step collapses its internals in the report; the error is reported at the step call site, not buried in shared helper code.\n\n```typescript\nimport { test, expect, type Page } from '@playwright\u002Ftest';\n\nasync function loginAs(page: Page, email: string, password: string) {\n  await test.step(\n    `Log in as ${email}`,\n    async () => {\n      await page.goto('https:\u002F\u002Fexample.com\u002Flogin');\n      await page.getByLabel('Email').fill(email);\n      await page.getByLabel('Password').fill(password);\n      await page.getByRole('button', { name: 'Sign in' }).click();\n      await expect(page.getByTestId('user-menu')).toBeVisible();\n    },\n    { box: true }, \u002F\u002F failure surfaces at this step, internals collapsed\n  );\n}\n\ntest('admin can open settings', async ({ page }) => {\n  await loginAs(page, 'admin@example.com', 'Admin123!');\n  await page.getByRole('link', { name: 'Settings' }).click();\n  await expect(page.getByRole('heading', { name: 'Settings' })).toBeVisible();\n});\n```\n\n### Pattern 6 — Configure rich reporters\n\nWire up reporters in `playwright.config.ts`. The HTML reporter consumes the steps, attachments, and annotations above; JSON\u002FJUnit feed CI dashboards.\n\n```typescript\nimport { defineConfig } from '@playwright\u002Ftest';\n\nexport default defineConfig({\n  reporter: [\n    ['html', { open: 'never', outputFolder: 'playwright-report' }],\n    ['json', { outputFile: 'test-results\u002Fresults.json' }],\n    ['junit', { outputFile: 'test-results\u002Fjunit.xml' }],\n    ['list'],\n  ],\n  use: {\n    \u002F\u002F Auto-capture trace + screenshot on failure — they attach to the report.\n    trace: 'retain-on-failure',\n    screenshot: 'only-on-failure',\n    video: 'retain-on-failure',\n  },\n});\n```\n\n## Best Practices\n\n1. **Wrap each logical phase in `test.step`** with a business-readable, imperative name — the report becomes a living test plan.\n2. **Attach the artifact that explains the failure** (screenshot, response JSON, diff) at the step where it is relevant, via `testInfo.attach`.\n3. **Set `trace: 'retain-on-failure'` and `screenshot: 'only-on-failure'`** so failing tests carry full debugging context automatically.\n4. **Use `expect.soft` for grouped, independent checks**, then add a hard `expect(test.info().errors).toHaveLength(0)` gate.\n5. **Push `issue`\u002F`known-issue` annotations** to keep traceability between tests and tickets visible in the report.\n6. **Box shared helpers** so a failure inside login\u002Fsetup points at the calling test, not the helper internals.\n7. **Return values from steps** to pass IDs\u002Ftokens forward and keep the flow linear.\n\n## Anti-Patterns\n\n1. **A 60-line test with no steps.** A failure gives a line number and nothing else; reviewers cannot tell which phase broke.\n2. **`console.log` for evidence.** Logs are not in the HTML report. Use `testInfo.attach`.\n3. **`expect.soft` everywhere with no hard gate.** The test goes green while assertions silently failed. Always end with a hard check.\n4. **Steps named after mechanics** (\"click\", \"fill input\") instead of intent (\"Submit signup form\").\n5. **Attaching full-page screenshots on every step of a passing test** — bloats the report. Attach on failure or at key checkpoints.\n6. **Skipping tests with bare `test.skip()` and no reason** — the report shows a skip with no explanation. Always pass a reason string.\n7. **Deep nesting of unnamed anonymous steps** that obscure rather than clarify the flow.\n\n## When to Trigger This Skill\n\n- \"Make my Playwright test report readable \u002F easier to debug\"\n- \"Group my test into steps\" \u002F \"use `test.step`\"\n- \"Attach a screenshot or JSON to the Playwright report\"\n- \"How do I do soft assertions in Playwright?\"\n- \"Add annotations \u002F link tests to Jira or GitHub issues\"\n- \"Why can't I tell which step failed in CI?\"\n- \"Set up the HTML \u002F JUnit \u002F JSON reporter\"\n- \"Capture a trace only when a test fails\"\n","# Playwright test.step & Reporting\n\nThis skill makes the agent produce tests that *explain themselves in the report*. Instead of a flat wall of actions, the agent groups logical phases with `test.step`, attaches screenshots\u002FJSON\u002Fdiffs via `testInfo.attach`, records `annotations` for traceability, and uses `expect.soft` to collect multiple failures in one run. When a test fails in CI, a human should understand what happened from the HTML report alone.\n\nUse this skill when writing non-trivial flows, when a test is hard to debug from its output, or when the user mentions reports, steps, annotations, attachments, or issue traceability.\n\n## Core Principles\n\n1. **Every logical phase is a `test.step`.** Steps appear as a collapsible tree in the HTML report with timings, turning a failure into \"which step failed\" instead of \"which line number.\"\n2. **Attach evidence, do not just log it.** `console.log` is invisible in the report; `testInfo.attach` puts screenshots, JSON, and text into the report next to the step.\n3. **Use `expect.soft` to gather multiple defects** in one execution, but end critical paths with a hard assertion or `expect.poll` so the test still fails.\n4. **Annotate for traceability.** Link tests to issues\u002Frequirements with `annotation`, and use `test.info().annotations` to surface skips\u002Fknown-issues in the report.\n5. **Steps should be named like a test plan** — imperative, business-readable (\"Add Pro plan to cart\"), not \"click button #3\".\n6. **Box internal helper steps** so a failure points at the caller, not deep inside the helper.\n\n## Workflow \u002F Patterns\n\n### Pattern 1 — Structure a flow with `test.step`\n\nSteps nest and report their own duration. Return values from a step to chain them.\n\n```typescript\nimport { test, expect } from '@playwright\u002Ftest';\n\ntest('checkout flow', async ({ page }) => {\n  await test.step('Sign in', async () => {\n    await page.goto('https:\u002F\u002Fshop.example.com\u002Flogin');\n    await page.getByLabel('Email').fill('buyer@example.com');\n    await page.getByLabel('Password').fill('Secret123!');\n    await page.getByRole('button', { name: 'Sign in' }).click();\n    await expect(page.getByText('Welcome back')).toBeVisible();\n  });\n\n  const orderId = await test.step('Place order for Pro plan', async () => {\n    await page.getByRole('link', { name: 'Pro plan' }).click();\n    await page.getByRole('button', { name: 'Buy now' }).click();\n    await page.getByRole('button', { name: 'Confirm purchase' }).click();\n    const id = await page.getByTestId('order-id').textContent();\n    return id!.trim();\n  });\n\n  await test.step(`Verify order ${orderId} in history`, async () => {\n    await page.goto('https:\u002F\u002Fshop.example.com\u002Forders');\n    await expect(page.getByText(orderId)).toBeVisible();\n  });\n});\n```\n\n### Pattern 2 — Attach evidence with `testInfo.attach`\n\nAttachments render inline in the HTML report. Attach a screenshot, the API response, or a computed diff at the moment it matters.\n\n```typescript\ntest('attaches evidence to the report', async ({ page }, testInfo) => {\n  await page.goto('https:\u002F\u002Fexample.com\u002Fdashboard');\n\n  await test.step('Capture dashboard state', async () => {\n    \u002F\u002F Screenshot attachment (shown inline in the report).\n    await testInfo.attach('dashboard.png', {\n      body: await page.screenshot({ fullPage: true }),\n      contentType: 'image\u002Fpng',\n    });\n\n    \u002F\u002F JSON attachment — the raw API payload behind the screen.\n    const widgets = await page.evaluate(() => (window as any).__WIDGETS__ ?? []);\n    await testInfo.attach('widgets.json', {\n      body: JSON.stringify(widgets, null, 2),\n      contentType: 'application\u002Fjson',\n    });\n\n    \u002F\u002F Plain-text attachment for a human-readable note.\n    await testInfo.attach('environment.txt', {\n      body: `Project: ${testInfo.project.name}\\nBase URL: ${page.url()}`,\n      contentType: 'text\u002Fplain',\n    });\n  });\n});\n```\n\n### Pattern 3 — Soft assertions to collect multiple failures\n\n`expect.soft` records the failure and keeps going. End the test with `expect(test.info().errors).toHaveLength(0)` or a hard check so it still fails — and the report shows *every* problem at once.\n\n```typescript\ntest('validates a form with soft assertions', async ({ page }) => {\n  await page.goto('https:\u002F\u002Fexample.com\u002Fprofile');\n\n  await test.step('Verify all profile fields at once', async () => {\n    await expect.soft(page.getByLabel('Display name')).toHaveValue('Ada Lovelace');\n    await expect.soft(page.getByLabel('Email')).toHaveValue('ada@example.com');\n    await expect.soft(page.getByLabel('Timezone')).toHaveValue('UTC');\n    await expect.soft(page.getByRole('img', { name: 'Avatar' })).toBeVisible();\n  });\n\n  \u002F\u002F Hard gate: fail the test if any soft assertion failed.\n  expect(test.info().errors).toHaveLength(0);\n});\n```\n\n### Pattern 4 — Annotations for traceability and known issues\n\nAnnotations attach metadata to a test; they show up in the report and JSON output. Use them to link issues and to document why something is skipped.\n\n```typescript\ntest('payment retries on gateway 503', async ({ page }) => {\n  test.info().annotations.push(\n    { type: 'issue', description: 'https:\u002F\u002Fgithub.com\u002Facme\u002Fapp\u002Fissues\u002F4821' },\n    { type: 'suite', description: 'payments-regression' },\n  );\n\n  await page.goto('https:\u002F\u002Fexample.com\u002Fpay');\n  await expect(page.getByRole('button', { name: 'Pay' })).toBeEnabled();\n});\n\ntest('legacy export still works', async ({ page }) => {\n  test.skip(process.env.LEGACY !== 'on', 'Legacy export disabled in this env');\n  test.info().annotations.push({ type: 'known-issue', description: 'Slow > 5s, tracked in #5102' });\n  await page.goto('https:\u002F\u002Fexample.com\u002Fexport');\n  await expect(page.getByText('Export ready')).toBeVisible({ timeout: 30_000 });\n});\n```\n\n### Pattern 5 — Box helper steps so failures point at the caller\n\nA `boxed` step collapses its internals in the report; the error is reported at the step call site, not buried in shared helper code.\n\n```typescript\nimport { test, expect, type Page } from '@playwright\u002Ftest';\n\nasync function loginAs(page: Page, email: string, password: string) {\n  await test.step(\n    `Log in as ${email}`,\n    async () => {\n      await page.goto('https:\u002F\u002Fexample.com\u002Flogin');\n      await page.getByLabel('Email').fill(email);\n      await page.getByLabel('Password').fill(password);\n      await page.getByRole('button', { name: 'Sign in' }).click();\n      await expect(page.getByTestId('user-menu')).toBeVisible();\n    },\n    { box: true }, \u002F\u002F failure surfaces at this step, internals collapsed\n  );\n}\n\ntest('admin can open settings', async ({ page }) => {\n  await loginAs(page, 'admin@example.com', 'Admin123!');\n  await page.getByRole('link', { name: 'Settings' }).click();\n  await expect(page.getByRole('heading', { name: 'Settings' })).toBeVisible();\n});\n```\n\n### Pattern 6 — Configure rich reporters\n\nWire up reporters in `playwright.config.ts`. The HTML reporter consumes the steps, attachments, and annotations above; JSON\u002FJUnit feed CI dashboards.\n\n```typescript\nimport { defineConfig } from '@playwright\u002Ftest';\n\nexport default defineConfig({\n  reporter: [\n    ['html', { open: 'never', outputFolder: 'playwright-report' }],\n    ['json', { outputFile: 'test-results\u002Fresults.json' }],\n    ['junit', { outputFile: 'test-results\u002Fjunit.xml' }],\n    ['list'],\n  ],\n  use: {\n    \u002F\u002F Auto-capture trace + screenshot on failure — they attach to the report.\n    trace: 'retain-on-failure',\n    screenshot: 'only-on-failure',\n    video: 'retain-on-failure',\n  },\n});\n```\n\n## Best Practices\n\n1. **Wrap each logical phase in `test.step`** with a business-readable, imperative name — the report becomes a living test plan.\n2. **Attach the artifact that explains the failure** (screenshot, response JSON, diff) at the step where it is relevant, via `testInfo.attach`.\n3. **Set `trace: 'retain-on-failure'` and `screenshot: 'only-on-failure'`** so failing tests carry full debugging context automatically.\n4. **Use `expect.soft` for grouped, independent checks**, then add a hard `expect(test.info().errors).toHaveLength(0)` gate.\n5. **Push `issue`\u002F`known-issue` annotations** to keep traceability between tests and tickets visible in the report.\n6. **Box shared helpers** so a failure inside login\u002Fsetup points at the calling test, not the helper internals.\n7. **Return values from steps** to pass IDs\u002Ftokens forward and keep the flow linear.\n\n## Anti-Patterns\n\n1. **A 60-line test with no steps.** A failure gives a line number and nothing else; reviewers cannot tell which phase broke.\n2. **`console.log` for evidence.** Logs are not in the HTML report. Use `testInfo.attach`.\n3. **`expect.soft` everywhere with no hard gate.** The test goes green while assertions silently failed. Always end with a hard check.\n4. **Steps named after mechanics** (\"click\", \"fill input\") instead of intent (\"Submit signup form\").\n5. **Attaching full-page screenshots on every step of a passing test** — bloats the report. Attach on failure or at key checkpoints.\n6. **Skipping tests with bare `test.skip()` and no reason** — the report shows a skip with no explanation. Always pass a reason string.\n7. **Deep nesting of unnamed anonymous steps** that obscure rather than clarify the flow.\n\n## When to Trigger This Skill\n\n- \"Make my Playwright test report readable \u002F easier to debug\"\n- \"Group my test into steps\" \u002F \"use `test.step`\"\n- \"Attach a screenshot or JSON to the Playwright report\"\n- \"How do I do soft assertions in Playwright?\"\n- \"Add annotations \u002F link tests to Jira or GitHub issues\"\n- \"Why can't I tell which step failed in CI?\"\n- \"Set up the HTML \u002F JUnit \u002F JSON reporter\"\n- \"Capture a trace only when a test fails\"\n",{"name":5,"tags":24,"agents":33,"author":46,"domains":47,"license":15,"version":49,"languages":50,"frameworks":52,"description":7,"testingTypes":53},[25,26,27,28,29,30,31,32],"playwright","test-step","reporting","annotations","attachments","soft-assertions","test-info","traceability",[34,35,36,37,38,39,40,41,42,43,44,45],"claude-code","cursor","github-copilot","windsurf","codex","aider","continue","cline","zed","bolt","gemini-cli","amp","thetestingacademy",[48],"web","1.0.0",[51],"typescript",[25],[54,55],"e2e","integration","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Fqa\u002Fplaywright-test-step","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Playwright test.step & Reporting\"",{"tool":70,"command":71},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Playwright test.step & Reporting\"",{"tool":73,"command":74},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Playwright test.step & Reporting\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fplaywright-test-step\u002FSKILL.md",true,[],[79,87,94,101,108,115],{"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":83,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"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":83,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":83,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]