{ "schemaVersion": "1.0", "item": { "slug": "mini-piv", "name": "Mini PIV - Lightweight Feature Builder", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/SmokeAlot420/mini-piv", "canonicalUrl": "https://clawhub.ai/SmokeAlot420/mini-piv", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/mini-piv", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mini-piv", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "assets/prp_base.md", "references/codebase-analysis.md", "references/execute-prp.md", "references/generate-prp.md", "references/piv-debugger.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": "2026-04-23T16:43:11.935Z", "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/mini-piv" }, "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/mini-piv", "agentPageUrl": "https://openagent3.xyz/skills/mini-piv/agent", "manifestUrl": "https://openagent3.xyz/skills/mini-piv/agent.json", "briefUrl": "https://openagent3.xyz/skills/mini-piv/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": "Arguments: $ARGUMENTS", "body": "Parse arguments:\n\nFEATURE_NAME = $ARGUMENTS[0] or null (will ask user during discovery)\nPROJECT_PATH = $ARGUMENTS[1] or current working directory" }, { "title": "Philosophy: Quick & Quality", "body": "\"When you just want to build something without writing a PRD first.\"\n\nSame quality pipeline (Execute → Validate → Debug), but starts from a quick conversation instead of a PRD.\n\nYou are the orchestrator - stay lean, spawn fresh sub-agents for heavy lifting.\n\nSub-agent spawning: Use the sessions_spawn tool to create fresh sub-agent sessions. Each spawn is non-blocking — you'll receive results via an announce step. Wait for each agent's results before proceeding to the next step." }, { "title": "Required Reading by Role", "body": "RoleInstructionsOrchestratorThis file onlyResearch Agent{baseDir}/references/codebase-analysis.md + {baseDir}/references/generate-prp.mdExecutor{baseDir}/references/piv-executor.md + {baseDir}/references/execute-prp.mdValidator{baseDir}/references/piv-validator.mdDebugger{baseDir}/references/piv-debugger.md" }, { "title": "Visual Workflow", "body": "┌──────────────────────────────────────────────────────────┐\n│ 1. DISCOVERY → Ask 3-5 questions │\n│ 2. RESEARCH & PRP → Codebase analysis + PRP generation │\n│ 3. EXECUTE → Implement PRP │\n│ 4. VALIDATE → PASS / GAPS_FOUND / HUMAN_NEEDED │\n│ 5. DEBUG LOOP → Fix gaps (max 3x) │\n│ 6. COMMIT → feat(mini): {description} │\n└──────────────────────────────────────────────────────────┘" }, { "title": "1a. Determine Feature Name", "body": "If not provided: ask user or infer from context. Normalize to kebab-case." }, { "title": "1b. Check for Existing PRP", "body": "ls -la PROJECT_PATH/PRPs/ 2>/dev/null | grep -i \"mini-{FEATURE_NAME}\"\n\nIf exists, ask: \"Overwrite, rename, or skip to execution?\"" }, { "title": "1c. Ask Discovery Questions", "body": "Present in a single conversational message:\n\nI've got a few quick questions so I can build this right:\n\n1. **What does this feature do?** Quick rundown.\n2. **Where in the codebase does it live?** Files, folders, components?\n3. **Any specific libraries, patterns, or existing code to follow?**\n4. **What does \"done\" look like?** 1-3 concrete success criteria.\n5. **Anything explicitly OUT of scope?**\n\nAdapt for feature type (UI, API, contracts, integrations)." }, { "title": "1d. Structure Discovery Answers", "body": "feature:\n name: {FEATURE_NAME}\n scope: {Q1}\n touchpoints: {Q2}\n dependencies: {Q3}\n success_criteria: {Q4}\n out_of_scope: {Q5}" }, { "title": "Step 2: Research & PRP Generation", "body": "Spawn a fresh sub-agent using sessions_spawn:\n\nMINI PIV: RESEARCH & PRP GENERATION\n====================================\n\nProject root: {PROJECT_PATH}\nFeature name: {FEATURE_NAME}\n\n## Discovery Input\n{paste structured YAML}\n\n## Step 1: Codebase Analysis\nRead {baseDir}/references/codebase-analysis.md for the process.\nSave to: {PROJECT_PATH}/PRPs/planning/mini-{FEATURE_NAME}-analysis.md\n\n## Step 2: Generate PRP (analysis context still loaded)\nRead {baseDir}/references/generate-prp.md for the process.\n\n### Discovery → PRP Translation\n| Discovery | PRP Section |\n|-----------|-------------|\n| Scope (Q1) | Goal + What |\n| Touchpoints (Q2) | Implementation task locations |\n| Dependencies (Q3) | Context YAML, Known Gotchas |\n| Success Criteria (Q4) | Success Criteria + Validation |\n| Out of Scope (Q5) | Exclusions in What section |\n\nUse template: PRPs/templates/prp_base.md\nOutput to: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\n\nDo BOTH steps yourself. DO NOT spawn sub-agents.\n\nWait for completion." }, { "title": "Step 3: Spawn EXECUTOR", "body": "Spawn a fresh sub-agent using sessions_spawn:\n\nEXECUTOR MISSION - Mini PIV\n============================\n\nRead {baseDir}/references/piv-executor.md for your role.\nRead {baseDir}/references/execute-prp.md for the execution process.\n\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nProject: {PROJECT_PATH}\n\nFollow: Load PRP → Plan Thoroughly → Execute → Validate → Verify\nOutput EXECUTION SUMMARY." }, { "title": "Validation Sizing Decision", "body": "Before spawning a full validator, assess:\n\n<5 files changed, <100 lines, no external APIs → Quick validation (review changes yourself as orchestrator)\nOtherwise → Spawn full validator sub-agent (Step 4)" }, { "title": "Step 4: Spawn VALIDATOR", "body": "Spawn a fresh sub-agent using sessions_spawn:\n\nVALIDATOR MISSION - Mini PIV\n=============================\n\nRead {baseDir}/references/piv-validator.md for your process.\n\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nProject: {PROJECT_PATH}\nExecutor Summary: {SUMMARY}\n\nVerify ALL requirements independently.\nOutput VERIFICATION REPORT with Grade, Checks, Gaps.\n\nProcess result: PASS → commit | GAPS_FOUND → debugger | HUMAN_NEEDED → ask user" }, { "title": "Step 5: Debug Loop (Max 3 iterations)", "body": "Spawn a fresh sub-agent using sessions_spawn:\n\nDEBUGGER MISSION - Mini PIV - Iteration {I}\n============================================\n\nRead {baseDir}/references/piv-debugger.md for your methodology.\n\nProject: {PROJECT_PATH}\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nGaps: {GAPS}\nErrors: {ERRORS}\n\nFix root causes. Run tests after each fix.\nOutput FIX REPORT.\n\nAfter debugger: re-validate → PASS (commit) or loop (max 3) or escalate." }, { "title": "Step 6: Smart Commit", "body": "cd PROJECT_PATH && git status && git diff --stat\ngit add -A\ngit commit -m \"feat(mini): implement {FEATURE_NAME}\n\n- {bullet 1}\n- {bullet 2}\n\nBuilt via Mini PIV Ralph\n\nBuilt with FTW (First Try Works) - https://github.com/SmokeAlot420/ftw\"" }, { "title": "Completion", "body": "## MINI PIV RALPH COMPLETE\n\nFeature: {FEATURE_NAME}\nProject: {PROJECT_PATH}\n\n### Artifacts\n- PRP: PRPs/mini-{FEATURE_NAME}.md\n- Analysis: PRPs/planning/mini-{FEATURE_NAME}-analysis.md\n\n### Implementation\n- Validation cycles: {N}\n- Debug iterations: {M}\n\n### Files Changed\n{list}\n\nAll requirements verified and passing." }, { "title": "Error Handling", "body": "Executor BLOCKED: Ask user for guidance\nValidator HUMAN_NEEDED: Ask user for guidance\n3 debug cycles exhausted: Escalate with persistent issues list" }, { "title": "Sub-Agent Timeout/Failure", "body": "When a sub-agent times out or fails:\n\nCheck for partial work (files created, tests written)\nRetry once with a simplified, shorter prompt\nIf retry fails, escalate to user with what was accomplished" }, { "title": "Quick Reference", "body": "ScenarioUse ThisSmall/medium feature, no PRDMini PIVLarge feature with phasesFull PIV (/piv)" }, { "title": "File Naming", "body": "PRPs/mini-{feature-name}.md # PRP\nPRPs/planning/mini-{feature-name}-analysis.md # Analysis" } ], "body": "Mini PIV Ralph - Lightweight Feature Builder\nArguments: $ARGUMENTS\n\nParse arguments:\n\nFEATURE_NAME = $ARGUMENTS[0] or null (will ask user during discovery)\nPROJECT_PATH = $ARGUMENTS[1] or current working directory\n\nPhilosophy: Quick & Quality\n\n\"When you just want to build something without writing a PRD first.\"\n\nSame quality pipeline (Execute → Validate → Debug), but starts from a quick conversation instead of a PRD.\n\nYou are the orchestrator - stay lean, spawn fresh sub-agents for heavy lifting.\n\nSub-agent spawning: Use the sessions_spawn tool to create fresh sub-agent sessions. Each spawn is non-blocking — you'll receive results via an announce step. Wait for each agent's results before proceeding to the next step.\n\nRequired Reading by Role\nRole\tInstructions\nOrchestrator\tThis file only\nResearch Agent\t{baseDir}/references/codebase-analysis.md + {baseDir}/references/generate-prp.md\nExecutor\t{baseDir}/references/piv-executor.md + {baseDir}/references/execute-prp.md\nValidator\t{baseDir}/references/piv-validator.md\nDebugger\t{baseDir}/references/piv-debugger.md\nVisual Workflow\n┌──────────────────────────────────────────────────────────┐\n│ 1. DISCOVERY → Ask 3-5 questions │\n│ 2. RESEARCH & PRP → Codebase analysis + PRP generation │\n│ 3. EXECUTE → Implement PRP │\n│ 4. VALIDATE → PASS / GAPS_FOUND / HUMAN_NEEDED │\n│ 5. DEBUG LOOP → Fix gaps (max 3x) │\n│ 6. COMMIT → feat(mini): {description} │\n└──────────────────────────────────────────────────────────┘\n\nStep 1: Discovery Phase\n1a. Determine Feature Name\n\nIf not provided: ask user or infer from context. Normalize to kebab-case.\n\n1b. Check for Existing PRP\nls -la PROJECT_PATH/PRPs/ 2>/dev/null | grep -i \"mini-{FEATURE_NAME}\"\n\n\nIf exists, ask: \"Overwrite, rename, or skip to execution?\"\n\n1c. Ask Discovery Questions\n\nPresent in a single conversational message:\n\nI've got a few quick questions so I can build this right:\n\n1. **What does this feature do?** Quick rundown.\n2. **Where in the codebase does it live?** Files, folders, components?\n3. **Any specific libraries, patterns, or existing code to follow?**\n4. **What does \"done\" look like?** 1-3 concrete success criteria.\n5. **Anything explicitly OUT of scope?**\n\n\nAdapt for feature type (UI, API, contracts, integrations).\n\n1d. Structure Discovery Answers\nfeature:\n name: {FEATURE_NAME}\n scope: {Q1}\n touchpoints: {Q2}\n dependencies: {Q3}\n success_criteria: {Q4}\n out_of_scope: {Q5}\n\nStep 2: Research & PRP Generation\n\nSpawn a fresh sub-agent using sessions_spawn:\n\nMINI PIV: RESEARCH & PRP GENERATION\n====================================\n\nProject root: {PROJECT_PATH}\nFeature name: {FEATURE_NAME}\n\n## Discovery Input\n{paste structured YAML}\n\n## Step 1: Codebase Analysis\nRead {baseDir}/references/codebase-analysis.md for the process.\nSave to: {PROJECT_PATH}/PRPs/planning/mini-{FEATURE_NAME}-analysis.md\n\n## Step 2: Generate PRP (analysis context still loaded)\nRead {baseDir}/references/generate-prp.md for the process.\n\n### Discovery → PRP Translation\n| Discovery | PRP Section |\n|-----------|-------------|\n| Scope (Q1) | Goal + What |\n| Touchpoints (Q2) | Implementation task locations |\n| Dependencies (Q3) | Context YAML, Known Gotchas |\n| Success Criteria (Q4) | Success Criteria + Validation |\n| Out of Scope (Q5) | Exclusions in What section |\n\nUse template: PRPs/templates/prp_base.md\nOutput to: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\n\nDo BOTH steps yourself. DO NOT spawn sub-agents.\n\n\nWait for completion.\n\nStep 3: Spawn EXECUTOR\n\nSpawn a fresh sub-agent using sessions_spawn:\n\nEXECUTOR MISSION - Mini PIV\n============================\n\nRead {baseDir}/references/piv-executor.md for your role.\nRead {baseDir}/references/execute-prp.md for the execution process.\n\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nProject: {PROJECT_PATH}\n\nFollow: Load PRP → Plan Thoroughly → Execute → Validate → Verify\nOutput EXECUTION SUMMARY.\n\nValidation Sizing Decision\n\nBefore spawning a full validator, assess:\n\n<5 files changed, <100 lines, no external APIs → Quick validation (review changes yourself as orchestrator)\nOtherwise → Spawn full validator sub-agent (Step 4)\nStep 4: Spawn VALIDATOR\n\nSpawn a fresh sub-agent using sessions_spawn:\n\nVALIDATOR MISSION - Mini PIV\n=============================\n\nRead {baseDir}/references/piv-validator.md for your process.\n\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nProject: {PROJECT_PATH}\nExecutor Summary: {SUMMARY}\n\nVerify ALL requirements independently.\nOutput VERIFICATION REPORT with Grade, Checks, Gaps.\n\n\nProcess result: PASS → commit | GAPS_FOUND → debugger | HUMAN_NEEDED → ask user\n\nStep 5: Debug Loop (Max 3 iterations)\n\nSpawn a fresh sub-agent using sessions_spawn:\n\nDEBUGGER MISSION - Mini PIV - Iteration {I}\n============================================\n\nRead {baseDir}/references/piv-debugger.md for your methodology.\n\nProject: {PROJECT_PATH}\nPRP: {PROJECT_PATH}/PRPs/mini-{FEATURE_NAME}.md\nGaps: {GAPS}\nErrors: {ERRORS}\n\nFix root causes. Run tests after each fix.\nOutput FIX REPORT.\n\n\nAfter debugger: re-validate → PASS (commit) or loop (max 3) or escalate.\n\nStep 6: Smart Commit\ncd PROJECT_PATH && git status && git diff --stat\ngit add -A\ngit commit -m \"feat(mini): implement {FEATURE_NAME}\n\n- {bullet 1}\n- {bullet 2}\n\nBuilt via Mini PIV Ralph\n\nBuilt with FTW (First Try Works) - https://github.com/SmokeAlot420/ftw\"\n\nCompletion\n## MINI PIV RALPH COMPLETE\n\nFeature: {FEATURE_NAME}\nProject: {PROJECT_PATH}\n\n### Artifacts\n- PRP: PRPs/mini-{FEATURE_NAME}.md\n- Analysis: PRPs/planning/mini-{FEATURE_NAME}-analysis.md\n\n### Implementation\n- Validation cycles: {N}\n- Debug iterations: {M}\n\n### Files Changed\n{list}\n\nAll requirements verified and passing.\n\nError Handling\nExecutor BLOCKED: Ask user for guidance\nValidator HUMAN_NEEDED: Ask user for guidance\n3 debug cycles exhausted: Escalate with persistent issues list\nSub-Agent Timeout/Failure\n\nWhen a sub-agent times out or fails:\n\nCheck for partial work (files created, tests written)\nRetry once with a simplified, shorter prompt\nIf retry fails, escalate to user with what was accomplished\nQuick Reference\nScenario\tUse This\nSmall/medium feature, no PRD\tMini PIV\nLarge feature with phases\tFull PIV (/piv)\nFile Naming\nPRPs/mini-{feature-name}.md # PRP\nPRPs/planning/mini-{feature-name}-analysis.md # Analysis" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/SmokeAlot420/mini-piv", "publisherUrl": "https://clawhub.ai/SmokeAlot420/mini-piv", "owner": "SmokeAlot420", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/mini-piv", "downloadUrl": "https://openagent3.xyz/downloads/mini-piv", "agentUrl": "https://openagent3.xyz/skills/mini-piv/agent", "manifestUrl": "https://openagent3.xyz/skills/mini-piv/agent.json", "briefUrl": "https://openagent3.xyz/skills/mini-piv/agent.md" } }