{
  "schemaVersion": "1.0",
  "item": {
    "slug": "github-copilot-cli",
    "name": "Github Copilot Cli",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/WilsonLe/github-copilot-cli",
    "canonicalUrl": "https://clawhub.ai/WilsonLe/github-copilot-cli",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/github-copilot-cli",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-copilot-cli",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "slug": "github-copilot-cli",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-03T19:24:33.305Z",
      "expiresAt": "2026-05-10T19:24:33.305Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-copilot-cli",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=github-copilot-cli",
        "contentDisposition": "attachment; filename=\"github-copilot-cli-0.1.2.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "github-copilot-cli"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/github-copilot-cli"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/github-copilot-cli",
    "agentPageUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent",
    "manifestUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Frontmatter Linting (Do This First)",
        "body": "YAML frontmatter is strict. A single extra space can break the skill.\n\nBefore committing or publishing:\n\n# Basic sanity check (no output = good)\npython - <<'PY'\nimport yaml,sys\nwith open('SKILL.md') as f:\n    yaml.safe_load(f.read())\nprint('Frontmatter OK')\nPY\n\nRules to remember:\n\nNo leading spaces before keys (name, description)\nUse spaces, not tabs\nKeep frontmatter minimal (only name and description)"
      },
      {
        "title": "Mental Model",
        "body": "Treat Copilot CLI as a team of elite specialists coordinated by you:\n\nOne Copilot instance can act as frontend engineer\nOne as backend engineer\nOne as tester / QA\nOne as infrastructure or refactor specialist\n\nCopilot is excellent at coding and architecture when given clear roles. You act as the CTO / conductor:\n\nDefine goals and constraints\nLet Copilot instances propose solutions\nObserve trade‑offs and conflicts\nEscalate decisions or risks to yourself explicitly"
      },
      {
        "title": "1. Ask questions about a codebase",
        "body": "gh copilot explain \"What does this service do?\" --path src/\n\nUse when orienting yourself or reloading context after a break."
      },
      {
        "title": "2. Generate a focused change (most common)",
        "body": "gh copilot suggest \"Add logging when translation fallback is used\" --path services/translation\n\nBest practice:\n\nPhrase the request as a delta, not a feature\nAlways point it at a specific directory"
      },
      {
        "title": "3. Debug with constraints",
        "body": "gh copilot suggest \"Why might this function return null under load?\" --path src/choreo\n\nFollow up manually by reading the code it points to."
      },
      {
        "title": "4. Tests first, code second",
        "body": "gh copilot suggest \"Write failing tests for punctuation correction on voice transcription\" --path tests/\n\nThen iterate toward the fix yourself."
      },
      {
        "title": "✅ Good prompts (role-aware)",
        "body": "\"As a backend engineer, draft a minimal fix for X\"\n\"As a tester, add guards so Y never happens\"\n\"As infra, refactor this to be safer, not faster\""
      },
      {
        "title": "❌ Bad prompts",
        "body": "\"Implement feature X end-to-end\"\n\"Refactor the whole service\"\n\"Make this production-ready\""
      },
      {
        "title": "Multi‑Copilot Orchestration Loop (Recommended)",
        "body": "Decompose (CTO)\n\nState the goal and constraints\nSplit into FE / BE / QA / Infra concerns\n\n\n\nPropose (Copilot roles)\n\ngh copilot suggest \"As a backend engineer, propose a minimal fix for mixed-language carryover\" --path src/\n\ngh copilot suggest \"As a tester, write failing tests for mixed-language carryover\" --path tests/\n\nCross‑check (Copilot vs Copilot)\n\nCompare proposals\nLook for disagreement or assumptions\n\n\n\nEscalate (to you)\n\nSurface trade‑offs\nHighlight risk\nAsk for decision\n\n\n\nFinalize (with you)\n\nApply changes\nClean up naming\nMerge intentionally"
      },
      {
        "title": "When NOT to Use Copilot CLI",
        "body": "Copilot CLI should not be the final authority in situations where:\n\nProduct or organizational trade‑offs dominate over code correctness\nCross‑repo or cross‑team coordination is required\nSecurity, privacy, or compliance decisions are involved\nAmbiguous state machines where correctness depends on real‑world behavior\n\nIn these cases, Copilot may still propose options, but you must explicitly review and decide."
      },
      {
        "title": "Golden Rule",
        "body": "Copilot is a force multiplier, not a decision owner.\n\nUse Copilot to:\n\nGenerate competing implementations\nSurface assumptions\nStress‑test ideas from multiple angles\n\nYou own:\n\nFinal intent\nRisk acceptance\nMerge decisions\n\nCopilot accelerates thinking — it does not replace judgment."
      }
    ],
    "body": "GitHub Copilot CLI – Efficient Workflow\nFrontmatter Linting (Do This First)\n\nYAML frontmatter is strict. A single extra space can break the skill.\n\nBefore committing or publishing:\n\n# Basic sanity check (no output = good)\npython - <<'PY'\nimport yaml,sys\nwith open('SKILL.md') as f:\n    yaml.safe_load(f.read())\nprint('Frontmatter OK')\nPY\n\n\nRules to remember:\n\nNo leading spaces before keys (name, description)\nUse spaces, not tabs\nKeep frontmatter minimal (only name and description)\nMental Model\n\nTreat Copilot CLI as a team of elite specialists coordinated by you:\n\nOne Copilot instance can act as frontend engineer\nOne as backend engineer\nOne as tester / QA\nOne as infrastructure or refactor specialist\n\nCopilot is excellent at coding and architecture when given clear roles. You act as the CTO / conductor:\n\nDefine goals and constraints\nLet Copilot instances propose solutions\nObserve trade‑offs and conflicts\nEscalate decisions or risks to yourself explicitly\nCore Commands You Should Actually Use\n1. Ask questions about a codebase\ngh copilot explain \"What does this service do?\" --path src/\n\n\nUse when orienting yourself or reloading context after a break.\n\n2. Generate a focused change (most common)\ngh copilot suggest \"Add logging when translation fallback is used\" --path services/translation\n\n\nBest practice:\n\nPhrase the request as a delta, not a feature\nAlways point it at a specific directory\n3. Debug with constraints\ngh copilot suggest \"Why might this function return null under load?\" --path src/choreo\n\n\nFollow up manually by reading the code it points to.\n\n4. Tests first, code second\ngh copilot suggest \"Write failing tests for punctuation correction on voice transcription\" --path tests/\n\n\nThen iterate toward the fix yourself.\n\nPrompting Patterns That Work\n✅ Good prompts (role-aware)\n\"As a backend engineer, draft a minimal fix for X\"\n\"As a tester, add guards so Y never happens\"\n\"As infra, refactor this to be safer, not faster\"\n❌ Bad prompts\n\"Implement feature X end-to-end\"\n\"Refactor the whole service\"\n\"Make this production-ready\"\nMulti‑Copilot Orchestration Loop (Recommended)\n\nDecompose (CTO)\n\nState the goal and constraints\nSplit into FE / BE / QA / Infra concerns\n\nPropose (Copilot roles)\n\ngh copilot suggest \"As a backend engineer, propose a minimal fix for mixed-language carryover\" --path src/\n\ngh copilot suggest \"As a tester, write failing tests for mixed-language carryover\" --path tests/\n\n\nCross‑check (Copilot vs Copilot)\n\nCompare proposals\nLook for disagreement or assumptions\n\nEscalate (to you)\n\nSurface trade‑offs\nHighlight risk\nAsk for decision\n\nFinalize (with you)\n\nApply changes\nClean up naming\nMerge intentionally\nWhen NOT to Use Copilot CLI\n\nCopilot CLI should not be the final authority in situations where:\n\nProduct or organizational trade‑offs dominate over code correctness\nCross‑repo or cross‑team coordination is required\nSecurity, privacy, or compliance decisions are involved\nAmbiguous state machines where correctness depends on real‑world behavior\n\nIn these cases, Copilot may still propose options, but you must explicitly review and decide.\n\nGolden Rule\n\nCopilot is a force multiplier, not a decision owner.\n\nUse Copilot to:\n\nGenerate competing implementations\nSurface assumptions\nStress‑test ideas from multiple angles\n\nYou own:\n\nFinal intent\nRisk acceptance\nMerge decisions\n\nCopilot accelerates thinking — it does not replace judgment."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/WilsonLe/github-copilot-cli",
    "publisherUrl": "https://clawhub.ai/WilsonLe/github-copilot-cli",
    "owner": "WilsonLe",
    "version": "0.1.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/github-copilot-cli",
    "downloadUrl": "https://openagent3.xyz/downloads/github-copilot-cli",
    "agentUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent",
    "manifestUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/github-copilot-cli/agent.md"
  }
}