{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pull-request",
    "name": "Pull Request",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ivangdavila/pull-request",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/pull-request",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pull-request",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pull-request",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "checklist.md",
      "red-flags.md",
      "repo-context.md",
      "templates.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": "pull-request",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T14:15:59.290Z",
      "expiresAt": "2026-05-14T14:15:59.290Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pull-request",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pull-request",
        "contentDisposition": "attachment; filename=\"pull-request-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "pull-request"
      },
      "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/pull-request"
    },
    "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/pull-request",
    "agentPageUrl": "https://openagent3.xyz/skills/pull-request/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pull-request/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pull-request/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": "When to Use",
        "body": "Before creating or suggesting a pull request to ANY repository. Acts as a quality filter to prevent wasting maintainer time and embarrassing the contributor."
      },
      {
        "title": "Quick Reference",
        "body": "DomainFilePre-submission checklistchecklist.mdRed flags to avoidred-flags.mdRepository context gatheringrepo-context.mdPR description templatestemplates.md"
      },
      {
        "title": "Critical Rules",
        "body": "Read CONTRIBUTING.md first — Adapt to project's workflow, not a fixed pattern\nIssue policy depends on scope — Small fixes may PR directly; features need discussion first\nDisclose AI involvement — Mark AI-assisted PRs in title/description\nRun checks if possible — If you can't run tests, say so explicitly\nMatch existing style — Check for .editorconfig, prettier, eslint configs\nSmall and focused — One logical change per PR\nNo secrets ever — Use <PLACEHOLDER> syntax"
      },
      {
        "title": "Issue Policy (Contextual)",
        "body": "NOT all projects require issues first. Check CONTRIBUTING.md, then:\n\nChange TypeDefault ActionTypo, small bug fixPR directly (unless CONTRIBUTING.md says otherwise)New featureOpen Discussion/Issue first, wait for approvalArchitecture changeRFC or Discussion requiredWhen in doubtAsk in issue before coding"
      },
      {
        "title": "AI-Assisted PRs",
        "body": "If this PR was created with AI assistance:\n\nMark it — Add [AI-assisted] to PR title or note in description\nTesting level — State: untested / lightly tested / fully tested\nInclude context — Prompts or session logs if available and helpful\nConfirm understanding — \"I have reviewed this code and understand what it does\"\nHuman accountable — Link to the human directing the contribution"
      },
      {
        "title": "Rate Limiting (Avoid Spam)",
        "body": "MAX 1 open PR per repo at a time\nWait 24h between PRs to same repo\nIf 2 PRs rejected consecutively → STOP and escalate to human\nCheck repo's PR velocity first (don't flood low-activity projects)"
      },
      {
        "title": "Abandonment Prevention",
        "body": "MUST respond to review feedback within 48h\nIf unable to address feedback, close with: \"I cannot continue; @human please take over or close\"\nNever leave PRs to rot"
      },
      {
        "title": "Scope Boundaries — STOP and Discuss First If:",
        "body": "Change touches >5 files OR >200 lines\nChange modifies public API\nChange involves security, auth, or crypto\nChange is in governance, licensing, or CoC\nMaintainer requested discussion in issue\nYou're unsure if this aligns with project philosophy"
      },
      {
        "title": "Human Escalation Required",
        "body": "Escalate to human when:\n\nReviewer asks clarifying questions about design intent\nCI fails in non-obvious way\nAny pushback beyond \"fix this typo\"\nReviewer seems confused or frustrated\nYou can't run the test suite locally"
      }
    ],
    "body": "When to Use\n\nBefore creating or suggesting a pull request to ANY repository. Acts as a quality filter to prevent wasting maintainer time and embarrassing the contributor.\n\nQuick Reference\nDomain\tFile\nPre-submission checklist\tchecklist.md\nRed flags to avoid\tred-flags.md\nRepository context gathering\trepo-context.md\nPR description templates\ttemplates.md\nCritical Rules\nRead CONTRIBUTING.md first — Adapt to project's workflow, not a fixed pattern\nIssue policy depends on scope — Small fixes may PR directly; features need discussion first\nDisclose AI involvement — Mark AI-assisted PRs in title/description\nRun checks if possible — If you can't run tests, say so explicitly\nMatch existing style — Check for .editorconfig, prettier, eslint configs\nSmall and focused — One logical change per PR\nNo secrets ever — Use <PLACEHOLDER> syntax\nIssue Policy (Contextual)\n\nNOT all projects require issues first. Check CONTRIBUTING.md, then:\n\nChange Type\tDefault Action\nTypo, small bug fix\tPR directly (unless CONTRIBUTING.md says otherwise)\nNew feature\tOpen Discussion/Issue first, wait for approval\nArchitecture change\tRFC or Discussion required\nWhen in doubt\tAsk in issue before coding\nAI-Assisted PRs\n\nIf this PR was created with AI assistance:\n\nMark it — Add [AI-assisted] to PR title or note in description\nTesting level — State: untested / lightly tested / fully tested\nInclude context — Prompts or session logs if available and helpful\nConfirm understanding — \"I have reviewed this code and understand what it does\"\nHuman accountable — Link to the human directing the contribution\nRate Limiting (Avoid Spam)\nMAX 1 open PR per repo at a time\nWait 24h between PRs to same repo\nIf 2 PRs rejected consecutively → STOP and escalate to human\nCheck repo's PR velocity first (don't flood low-activity projects)\nAbandonment Prevention\nMUST respond to review feedback within 48h\nIf unable to address feedback, close with: \"I cannot continue; @human please take over or close\"\nNever leave PRs to rot\nScope Boundaries — STOP and Discuss First If:\nChange touches >5 files OR >200 lines\nChange modifies public API\nChange involves security, auth, or crypto\nChange is in governance, licensing, or CoC\nMaintainer requested discussion in issue\nYou're unsure if this aligns with project philosophy\nHuman Escalation Required\n\nEscalate to human when:\n\nReviewer asks clarifying questions about design intent\nCI fails in non-obvious way\nAny pushback beyond \"fix this typo\"\nReviewer seems confused or frustrated\nYou can't run the test suite locally"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/pull-request",
    "publisherUrl": "https://clawhub.ai/ivangdavila/pull-request",
    "owner": "ivangdavila",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pull-request",
    "downloadUrl": "https://openagent3.xyz/downloads/pull-request",
    "agentUrl": "https://openagent3.xyz/skills/pull-request/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pull-request/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pull-request/agent.md"
  }
}