{ "schemaVersion": "1.0", "item": { "slug": "open-ralph", "name": "open-ralph", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Bderiel/open-ralph", "canonicalUrl": "https://clawhub.ai/Bderiel/open-ralph", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/open-ralph", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=open-ralph", "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", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.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/open-ralph" }, "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/open-ralph", "agentPageUrl": "https://openagent3.xyz/skills/open-ralph/agent", "manifestUrl": "https://openagent3.xyz/skills/open-ralph/agent.json", "briefUrl": "https://openagent3.xyz/skills/open-ralph/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": "What this skill does", "body": "This skill runs an autonomous Ralph Wiggum coding loop using the ralph CLI with OpenCode as the agent provider.\n\nIt repeatedly executes the same coding prompt until:\n\nThe success criteria are met, OR\nThe completion promise is printed, OR\nMax iterations are reached\n\nThe loop is optimized for free OpenCode Zen models and includes a fallback chain in case models are rate-limited, disabled, or removed." }, { "title": "When to use", "body": "Use this skill when you want autonomous coding execution such as:\n\nFixing failing tests\nImplementing scoped features\nRefactoring codebases\nResolving lint/type errors\nRunning build-fix loops\nMulti-iteration debugging\n\nYou MUST be inside a git repository before running Ralph." }, { "title": "Free model fallback order", "body": "Always attempt models in this order:\n\nopencode/kimi-k2.5-free ← Best coding performance (limited time free)\nopencode/minimax-m2.1-free\nopencode/glm-4.7-free\nopencode/big-pickle ← Free stealth model fallback\n\nIf a model fails due to availability or quota, immediately retry using the next model without changing the prompt or loop parameters." }, { "title": "Failure triggers for fallback", "body": "Fallback if you encounter errors like:\n\nmodel disabled\nmodel not found\ninsufficient quota\nquota exceeded\npayment required\nrate limit\nprovider unavailable" }, { "title": "Attempt #1 (primary model)", "body": "Run:\n\nralph \"\n\nSuccess criteria:\n\n\n\nBuild passes\nTests pass\n\nCompletion promise:\nCOMPLETE\" \n--agent opencode \n--model opencode/kimi-k2.5-free \n--completion-promise \"COMPLETE\" \n--max-iterations 20" }, { "title": "Attempt #2 (fallback)", "body": "If attempt #1 fails due to model issues, rerun with:\n\n--model opencode/minimax-m2.1-free" }, { "title": "Attempt #3 (fallback)", "body": "If attempt #2 fails:\n\n--model opencode/glm-4.7-free" }, { "title": "Attempt #4 (final fallback)", "body": "If attempt #3 fails:\n\n--model opencode/big-pickle" }, { "title": "Tasks mode (for large projects)", "body": "For multi-step execution:\n\nralph \"\" \n--agent opencode \n--model opencode/kimi-k2.5-free \n--tasks \n--max-iterations 50\n\nFallback model order still applies." }, { "title": "Plugin troubleshooting", "body": "If OpenCode plugins interfere with loop execution, rerun with:\n\n--no-plugins" }, { "title": "Sanity check available Zen models", "body": "If free model availability changes, check:\n\nhttps://opencode.ai/zen/v1/models\n\nUpdate fallback order if needed." }, { "title": "Safety notes", "body": "Always run inside a git repo\nSet iteration limits to avoid runaway loops\nEnsure prompts contain verifiable success criteria\nReview diffs before merging autonomous changes" }, { "title": "Example usage", "body": "Fix failing TypeScript errors:\n\nralph \"Fix all TypeScript errors in the repo.\n\nSuccess criteria:\n\ntsc passes\nBuild succeeds\n\nCompletion promise:\nCOMPLETE\" \n--agent opencode \n--model opencode/kimi-k2.5-free \n--completion-promise \"COMPLETE\" \n--max-iterations 20" } ], "body": "What this skill does\n\nThis skill runs an autonomous Ralph Wiggum coding loop using the ralph CLI with OpenCode as the agent provider.\n\nIt repeatedly executes the same coding prompt until:\n\nThe success criteria are met, OR\nThe completion promise is printed, OR\nMax iterations are reached\n\nThe loop is optimized for free OpenCode Zen models and includes a fallback chain in case models are rate-limited, disabled, or removed.\n\nWhen to use\n\nUse this skill when you want autonomous coding execution such as:\n\nFixing failing tests\nImplementing scoped features\nRefactoring codebases\nResolving lint/type errors\nRunning build-fix loops\nMulti-iteration debugging\n\nYou MUST be inside a git repository before running Ralph.\n\nFree model fallback order\n\nAlways attempt models in this order:\n\nopencode/kimi-k2.5-free ← Best coding performance (limited time free)\nopencode/minimax-m2.1-free\nopencode/glm-4.7-free\nopencode/big-pickle ← Free stealth model fallback\n\nIf a model fails due to availability or quota, immediately retry using the next model without changing the prompt or loop parameters.\n\nFailure triggers for fallback\n\nFallback if you encounter errors like:\n\nmodel disabled\nmodel not found\ninsufficient quota\nquota exceeded\npayment required\nrate limit\nprovider unavailable\nHow to run the loop\nAttempt #1 (primary model)\n\nRun:\n\nralph \"\n\nSuccess criteria:\n\n\nBuild passes\nTests pass\n\nCompletion promise: COMPLETE\"\n--agent opencode\n--model opencode/kimi-k2.5-free\n--completion-promise \"COMPLETE\"\n--max-iterations 20\n\nAttempt #2 (fallback)\n\nIf attempt #1 fails due to model issues, rerun with:\n\n--model opencode/minimax-m2.1-free\n\nAttempt #3 (fallback)\n\nIf attempt #2 fails:\n\n--model opencode/glm-4.7-free\n\nAttempt #4 (final fallback)\n\nIf attempt #3 fails:\n\n--model opencode/big-pickle\n\nTasks mode (for large projects)\n\nFor multi-step execution:\n\nralph \"\"\n--agent opencode\n--model opencode/kimi-k2.5-free\n--tasks\n--max-iterations 50\n\nFallback model order still applies.\n\nPlugin troubleshooting\n\nIf OpenCode plugins interfere with loop execution, rerun with:\n\n--no-plugins\n\nSanity check available Zen models\n\nIf free model availability changes, check:\n\nhttps://opencode.ai/zen/v1/models\n\nUpdate fallback order if needed.\n\nSafety notes\nAlways run inside a git repo\nSet iteration limits to avoid runaway loops\nEnsure prompts contain verifiable success criteria\nReview diffs before merging autonomous changes\nExample usage\n\nFix failing TypeScript errors:\n\nralph \"Fix all TypeScript errors in the repo.\n\nSuccess criteria:\n\ntsc passes\nBuild succeeds\n\nCompletion promise: COMPLETE\"\n--agent opencode\n--model opencode/kimi-k2.5-free\n--completion-promise \"COMPLETE\"\n--max-iterations 20" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Bderiel/open-ralph", "publisherUrl": "https://clawhub.ai/Bderiel/open-ralph", "owner": "Bderiel", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/open-ralph", "downloadUrl": "https://openagent3.xyz/downloads/open-ralph", "agentUrl": "https://openagent3.xyz/skills/open-ralph/agent", "manifestUrl": "https://openagent3.xyz/skills/open-ralph/agent.json", "briefUrl": "https://openagent3.xyz/skills/open-ralph/agent.md" } }