{ "schemaVersion": "1.0", "item": { "slug": "pr-ship", "name": "Pr Ship", "source": "tencent", "type": "skill", "category": "ę•°ę®åˆ†ęž", "sourceUrl": "https://clawhub.ai/Glucksberg/pr-ship", "canonicalUrl": "https://clawhub.ai/Glucksberg/pr-ship", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/pr-ship", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pr-ship", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "package.json", "references/ARCHITECTURE-MAP.md", "references/CURRENT-CONTEXT.md", "references/EXPLORATION-PLAYBOOK.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/pr-ship" }, "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/pr-ship", "agentPageUrl": "https://openagent3.xyz/skills/pr-ship/agent", "manifestUrl": "https://openagent3.xyz/skills/pr-ship/agent.json", "briefUrl": "https://openagent3.xyz/skills/pr-ship/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Overview", "body": "Pre-ship risk report for OpenClaw pull requests.\n\nThis skill is updated frequently to track OpenClaw releases. The version-specific context (gotchas, behavioral changes, active risk areas) is refreshed with each upstream release. Run clawhub update pr-ship periodically to get the latest context.\n\nWhat it does:\n\nDiffs your current branch against main in the OpenClaw repository.\nDynamically investigates each changed module using grep/find/git on the codebase itself.\nProduces a structured risk report with evidence-backed findings scored by severity (šŸŸ¢/šŸŸ”/šŸ”“).\nNo approve/reject gate -- just information for you to decide what to fix before publishing." }, { "title": "Reference Layers", "body": "Load these files from the references/ directory. Each serves a distinct purpose:\n\nSTABLE-PRINCIPLES.md -- Timeless OpenClaw coding standards: testing guide, file naming, safety invariants, common pitfalls, PR practices.\n\n\nARCHITECTURE-MAP.md -- OpenClaw structural context: module hierarchy, risk tier definitions with calibrated thresholds, critical path patterns, cross-module coupling, change impact matrix.\n\n\nCURRENT-CONTEXT.md (optional) -- Version-specific gotchas, recent behavioral changes, and active risk areas. If this file exists, load it. It tracks the current OpenClaw release.\n\n\nEXPLORATION-PLAYBOOK.md -- Dynamic investigation procedures. Read-only commands (grep, find, ls, git) that discover the current state of the OpenClaw codebase.\n\n\nVISION-GUIDELINES.md -- Project vision, contribution policy, and merge guardrails derived from OpenClaw's VISION.md. Covers PR scope rules, security philosophy, plugin/core boundary, skills policy, MCP strategy, and the explicit \"will not merge\" list. Use this to catch policy and architectural misalignment.\n\nSTABLE-PRINCIPLES, ARCHITECTURE-MAP, EXPLORATION-PLAYBOOK, and VISION-GUIDELINES should always be present. CURRENT-CONTEXT is optional -- if missing, the skill still works but without version-specific gotcha awareness." }, { "title": "1. Load reference layers", "body": "Read the four reference files listed above." }, { "title": "2. Collect diff against main", "body": "Get current branch: git branch --show-current\nGather file list: git diff --name-only main...HEAD\nGather patch content: git diff main...HEAD" }, { "title": "3. Classify changed modules", "body": "For each changed file, identify its src// path.\nLook up the module's risk tier in ARCHITECTURE-MAP.md.\nIf the module isn't listed or you want to verify, run the dynamic consumer count from EXPLORATION-PLAYBOOK.md \"Dynamic Risk Classification\" section." }, { "title": "4. Run dynamic exploration per changed module", "body": "Follow EXPLORATION-PLAYBOOK.md \"Blast Radius Discovery\" for each changed file.\nFollow \"Module-Specific Investigation Strategies\" for each changed module type.\nFollow \"Test Discovery\" to identify relevant tests.\nCheck \"Red Flags Table\" against the diff." }, { "title": "5. Evaluate findings", "body": "Compare exploration evidence against:\n\nSafety invariants and common pitfalls from STABLE-PRINCIPLES.md\nVersion-specific gotchas from CURRENT-CONTEXT.md (if loaded)\nArchitecture coupling patterns from ARCHITECTURE-MAP.md\nContribution policy, merge guardrails, and architectural direction from VISION-GUIDELINES.md\n\n\nCheck PR scope against Vision contribution rules (one PR = one topic, size limits, bundling policy).\nCheck for \"will not merge\" category matches from VISION-GUIDELINES.md section 7.\nEvaluate whether new capabilities respect the plugin/core boundary and security philosophy.\nEvery finding must include:\n\nEvidence from the diff (file + snippet)\nExploration evidence (command output showing blast radius, consumers, or pattern match)\nReference to the specific principle, gotcha, or coupling pattern it relates to" }, { "title": "6. Produce report", "body": "Use the report format below.\nDo not output \"approved/rejected\"." }, { "title": "Severity and Alert Scoring", "body": "šŸŸ¢ Low Risk (score 1-2)\nMinor observation, style preference, or informational note. Safe to ship as-is.\n\n\nšŸŸ” Attention Needed (score 3-6)\nPartial mismatch, ambiguity, missing hardening, or non-blocking inconsistency. Worth reviewing but unlikely to cause breakage.\n\n\nšŸ”“ High Risk (score 7-10)\nClear conflict with OpenClaw coding standards, architecture patterns, or version-specific constraints. Likely to cause bugs, regressions, or policy violations.\n\nScoring:\n\nScore each finding individually (1-10).\nfinal_alert_score = max(per_finding_scores). If no findings, final_alert_score = 0." }, { "title": "Report Format", "body": "## pr-ship report\n\n- Branch: ``\n- Base: `main`\n- Files changed: ``\n- Modules touched: ``\n- Findings: ``\n- Final alert score: `<0-10>`\n\n### Module Risk Summary\n\n| Module | Risk Tier | Consumers | Files Changed |\n| --- | --- | --- | --- |\n| | CRITICAL/HIGH/MEDIUM/LOW | | |\n\n### Findings\n\n1. šŸŸ¢/šŸŸ”/šŸ”“ Title\n - Alert: `<1-10>`\n - Reference: ``\n - Evidence in diff: ``\n - Exploration evidence: ``\n - Why this matters: `<1-2 lines>`\n - Suggested fix: `<1-2 concrete actions>`\n\n(repeat)\n\n### Executive summary\n- ``\n- ``" }, { "title": "Constraints", "body": "This skill is for the OpenClaw repository only. Do not use it on other projects.\nReview only the current branch diff against main.\nDo not review unrelated repository history.\nDo not auto-edit code unless explicitly asked.\nDo not convert the report into an approve/reject decision unless explicitly requested.\nExploration commands are read-only (grep, find, ls, git diff). Never execute build, test, or code generation commands -- recommend them to the user in findings instead." }, { "title": "Provenance", "body": "Source: github.com/Glucksberg/pr-ship\nMaintainer: Markus Glucksberg (@Glucksberg)\nUpdate mechanism: CURRENT-CONTEXT.md metadata is refreshed daily via cron when OpenClaw upstream CHANGELOG.md changes. GitHub repo is updated separately by the maintainer.\nVerification: The GitHub repo is the canonical source of truth. To verify your installed copy matches:\n\n# Quick: compare file list + versions\ndiff <(clawhub list | grep pr-ship) <(curl -s https://api.github.com/repos/Glucksberg/pr-ship/contents/package.json | jq -r '.content' | base64 -d | jq -r .version)\n\n# Full: diff your local install against GitHub\nSKILL_DIR=\"$(find ~/.openclaw/skills -maxdepth 1 -name pr-ship -type d 2>/dev/null || echo skills/pr-ship)\"\nfor f in SKILL.md package.json references/CURRENT-CONTEXT.md; do\n diff <(cat \"$SKILL_DIR/$f\") <(curl -s \"https://raw.githubusercontent.com/Glucksberg/pr-ship/main/$f\") && echo \"$f: āœ” match\" || echo \"$f: āœ˜ differs\"\ndone" }, { "title": "Security Notice", "body": "Reports generated by this skill may include diffs and grep output from your local repository. If your config files, environment, or code contain secrets (API keys, tokens, credentials), those values may appear in the report. Do not publish or share generated reports without reviewing them for sensitive data first." }, { "title": "Credits", "body": "Original DEVELOPER-REFERENCE.md format and approach adapted from mudrii's developer reference methodology. The dynamic exploration approach was designed based on feedback from the OpenClaw maintainer community." } ], "body": "pr-ship\nOverview\n\nPre-ship risk report for OpenClaw pull requests.\n\nThis skill is updated frequently to track OpenClaw releases. The version-specific context (gotchas, behavioral changes, active risk areas) is refreshed with each upstream release. Run clawhub update pr-ship periodically to get the latest context.\n\nWhat it does:\n\nDiffs your current branch against main in the OpenClaw repository.\nDynamically investigates each changed module using grep/find/git on the codebase itself.\nProduces a structured risk report with evidence-backed findings scored by severity (šŸŸ¢/šŸŸ”/šŸ”“).\nNo approve/reject gate -- just information for you to decide what to fix before publishing.\nReference Layers\n\nLoad these files from the references/ directory. Each serves a distinct purpose:\n\nSTABLE-PRINCIPLES.md -- Timeless OpenClaw coding standards: testing guide, file naming, safety invariants, common pitfalls, PR practices.\n\nARCHITECTURE-MAP.md -- OpenClaw structural context: module hierarchy, risk tier definitions with calibrated thresholds, critical path patterns, cross-module coupling, change impact matrix.\n\nCURRENT-CONTEXT.md (optional) -- Version-specific gotchas, recent behavioral changes, and active risk areas. If this file exists, load it. It tracks the current OpenClaw release.\n\nEXPLORATION-PLAYBOOK.md -- Dynamic investigation procedures. Read-only commands (grep, find, ls, git) that discover the current state of the OpenClaw codebase.\n\nVISION-GUIDELINES.md -- Project vision, contribution policy, and merge guardrails derived from OpenClaw's VISION.md. Covers PR scope rules, security philosophy, plugin/core boundary, skills policy, MCP strategy, and the explicit \"will not merge\" list. Use this to catch policy and architectural misalignment.\n\nSTABLE-PRINCIPLES, ARCHITECTURE-MAP, EXPLORATION-PLAYBOOK, and VISION-GUIDELINES should always be present. CURRENT-CONTEXT is optional -- if missing, the skill still works but without version-specific gotcha awareness.\n\nWorkflow\n1. Load reference layers\nRead the four reference files listed above.\n2. Collect diff against main\nGet current branch: git branch --show-current\nGather file list: git diff --name-only main...HEAD\nGather patch content: git diff main...HEAD\n3. Classify changed modules\nFor each changed file, identify its src// path.\nLook up the module's risk tier in ARCHITECTURE-MAP.md.\nIf the module isn't listed or you want to verify, run the dynamic consumer count from EXPLORATION-PLAYBOOK.md \"Dynamic Risk Classification\" section.\n4. Run dynamic exploration per changed module\nFollow EXPLORATION-PLAYBOOK.md \"Blast Radius Discovery\" for each changed file.\nFollow \"Module-Specific Investigation Strategies\" for each changed module type.\nFollow \"Test Discovery\" to identify relevant tests.\nCheck \"Red Flags Table\" against the diff.\n5. Evaluate findings\nCompare exploration evidence against:\nSafety invariants and common pitfalls from STABLE-PRINCIPLES.md\nVersion-specific gotchas from CURRENT-CONTEXT.md (if loaded)\nArchitecture coupling patterns from ARCHITECTURE-MAP.md\nContribution policy, merge guardrails, and architectural direction from VISION-GUIDELINES.md\nCheck PR scope against Vision contribution rules (one PR = one topic, size limits, bundling policy).\nCheck for \"will not merge\" category matches from VISION-GUIDELINES.md section 7.\nEvaluate whether new capabilities respect the plugin/core boundary and security philosophy.\nEvery finding must include:\nEvidence from the diff (file + snippet)\nExploration evidence (command output showing blast radius, consumers, or pattern match)\nReference to the specific principle, gotcha, or coupling pattern it relates to\n6. Produce report\nUse the report format below.\nDo not output \"approved/rejected\".\nSeverity and Alert Scoring\n\nšŸŸ¢ Low Risk (score 1-2) Minor observation, style preference, or informational note. Safe to ship as-is.\n\nšŸŸ” Attention Needed (score 3-6) Partial mismatch, ambiguity, missing hardening, or non-blocking inconsistency. Worth reviewing but unlikely to cause breakage.\n\nšŸ”“ High Risk (score 7-10) Clear conflict with OpenClaw coding standards, architecture patterns, or version-specific constraints. Likely to cause bugs, regressions, or policy violations.\n\nScoring:\n\nScore each finding individually (1-10).\nfinal_alert_score = max(per_finding_scores). If no findings, final_alert_score = 0.\nReport Format\n## pr-ship report\n\n- Branch: ``\n- Base: `main`\n- Files changed: ``\n- Modules touched: ``\n- Findings: ``\n- Final alert score: `<0-10>`\n\n### Module Risk Summary\n\n| Module | Risk Tier | Consumers | Files Changed |\n| --- | --- | --- | --- |\n| | CRITICAL/HIGH/MEDIUM/LOW | | |\n\n### Findings\n\n1. šŸŸ¢/šŸŸ”/šŸ”“ Title\n - Alert: `<1-10>`\n - Reference: ``\n - Evidence in diff: ``\n - Exploration evidence: ``\n - Why this matters: `<1-2 lines>`\n - Suggested fix: `<1-2 concrete actions>`\n\n(repeat)\n\n### Executive summary\n- ``\n- ``\n\nConstraints\nThis skill is for the OpenClaw repository only. Do not use it on other projects.\nReview only the current branch diff against main.\nDo not review unrelated repository history.\nDo not auto-edit code unless explicitly asked.\nDo not convert the report into an approve/reject decision unless explicitly requested.\nExploration commands are read-only (grep, find, ls, git diff). Never execute build, test, or code generation commands -- recommend them to the user in findings instead.\nProvenance\nSource: github.com/Glucksberg/pr-ship\nMaintainer: Markus Glucksberg (@Glucksberg)\nUpdate mechanism: CURRENT-CONTEXT.md metadata is refreshed daily via cron when OpenClaw upstream CHANGELOG.md changes. GitHub repo is updated separately by the maintainer.\nVerification: The GitHub repo is the canonical source of truth. To verify your installed copy matches:\n# Quick: compare file list + versions\ndiff <(clawhub list | grep pr-ship) <(curl -s https://api.github.com/repos/Glucksberg/pr-ship/contents/package.json | jq -r '.content' | base64 -d | jq -r .version)\n\n# Full: diff your local install against GitHub\nSKILL_DIR=\"$(find ~/.openclaw/skills -maxdepth 1 -name pr-ship -type d 2>/dev/null || echo skills/pr-ship)\"\nfor f in SKILL.md package.json references/CURRENT-CONTEXT.md; do\n diff <(cat \"$SKILL_DIR/$f\") <(curl -s \"https://raw.githubusercontent.com/Glucksberg/pr-ship/main/$f\") && echo \"$f: āœ” match\" || echo \"$f: āœ˜ differs\"\ndone\n\nSecurity Notice\n\nReports generated by this skill may include diffs and grep output from your local repository. If your config files, environment, or code contain secrets (API keys, tokens, credentials), those values may appear in the report. Do not publish or share generated reports without reviewing them for sensitive data first.\n\nCredits\n\nOriginal DEVELOPER-REFERENCE.md format and approach adapted from mudrii's developer reference methodology. The dynamic exploration approach was designed based on feedback from the OpenClaw maintainer community." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Glucksberg/pr-ship", "publisherUrl": "https://clawhub.ai/Glucksberg/pr-ship", "owner": "Glucksberg", "version": "1.0.13", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/pr-ship", "downloadUrl": "https://openagent3.xyz/downloads/pr-ship", "agentUrl": "https://openagent3.xyz/skills/pr-ship/agent", "manifestUrl": "https://openagent3.xyz/skills/pr-ship/agent.json", "briefUrl": "https://openagent3.xyz/skills/pr-ship/agent.md" } }