{ "schemaVersion": "1.0", "item": { "slug": "superclaw", "name": "Superclaw", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/brothaakhee/superclaw", "canonicalUrl": "https://clawhub.ai/brothaakhee/superclaw", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/superclaw", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=superclaw", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "PACKAGE-SUMMARY.md", "README.md", "SKILL.md", "brainstorming/SKILL.md", "executing-plans/SKILL.md", "writing-plans/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. 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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/superclaw" }, "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/superclaw", "agentPageUrl": "https://openagent3.xyz/skills/superclaw/agent", "manifestUrl": "https://openagent3.xyz/skills/superclaw/agent.json", "briefUrl": "https://openagent3.xyz/skills/superclaw/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": "Superclaw ⚔️", "body": "Disciplined software development workflow for OpenClaw agents\n\nBased on obra/superpowers by Jesse Vincent." }, { "title": "What This Skill Package Does", "body": "Superclaw prevents your agent from jumping straight into code. It enforces a three-phase workflow:\n\n🧠 Brainstorming (brainstorming/SKILL.md) — Design before code\n📋 Writing Plans (writing-plans/SKILL.md) — Plan before implementation\n⚙️ Executing Plans (executing-plans/SKILL.md) — Batched execution with checkpoints\n\nAll three skills chain automatically when building software." }, { "title": "Phase 1: Brainstorming (Design Before Code)", "body": "Triggers: When creating features, building components, adding functionality\n\nProcess:\n\nCheck context (MEMORY.md, USER.md, daily logs)\nAsk Socratic questions (requirements, constraints, trade-offs)\nPropose 2-3 approaches with pros/cons\nPresent design\nGet approval\nSave design document to workspace/docs/plans/YYYY-MM-DD--design.md\nAutomatically invoke writing-plans skill\n\nHard Gate: No code until design approved." }, { "title": "Phase 2: Writing Plans (Plan Before Implementation)", "body": "Triggers: When you have an approved design\n\nProcess:\n\nASK about methodology (TDD? Direct implementation?)\nAsk about commit frequency\nBreak work into 2-5 minute tasks\nSave implementation plan to workspace/docs/plans/YYYY-MM-DD--plan.md\nAutomatically invoke executing-plans skill\n\nKey Feature: Questions, not mandates. Respects user preferences and time constraints." }, { "title": "Phase 3: Executing Plans (Batched Execution with Checkpoints)", "body": "Triggers: When you have an implementation plan\n\nProcess:\n\nLoad plan from document\nBatch tasks into groups of 3-5\nExecute batch (using sessions_spawn for isolation)\nReview outputs\nCheckpoint (\"Batch N complete. Continue?\")\nUpdate memory/YYYY-MM-DD.md with progress\nRepeat until complete\n\nHard Gate: Maximum 5 tasks per batch. Checkpoints cannot be skipped." }, { "title": "Why Use Superclaw?", "body": "Without Superclaw:\n\nAgent jumps to code in seconds (no design, no plan)\nErrors compound across many tasks\nNo checkpoints → can't pause/resume\nMental plans disappear\n\nWith Superclaw:\n\nDesign → Plan → Execute (enforced)\nErrors caught early (batching prevents cascades)\nProgress tracked in memory\nResumable, reviewable, auditable" }, { "title": "Installation", "body": "npx clawhub@latest install superclaw\n\nSkills auto-load when relevant tasks are detected." }, { "title": "OpenClaw-Specific Adaptations", "body": "Memory Integration — Checks MEMORY.md, USER.md, daily logs\nMethodology Questions — \"Should we use TDD?\" not \"You must use TDD\"\nSessions_spawn — Fresh subagent per task for isolation\nWorkspace Conventions — Saves to workspace/docs/plans/" }, { "title": "Testing", "body": "All skills pressure-tested with RED-GREEN-REFACTOR methodology:\n\nSkillRED (without skill)GREEN (with skill)BrainstormingCoded in 12sAsked questions, got approvalWriting-PlansCoded in 73sAsked methodology, created planExecuting-Plans10 tasks in 40s4 batches with checkpoints\n\nIntegration test: All 3 skills chained automatically and delivered working CLI ✅" }, { "title": "Example Workflow", "body": "User: \"Build a markdown notes CLI\"\n\n→ Brainstorming skill:\n\nAsks: Storage format? Search needed? Tagging?\nProposes: 3 approaches (flat files vs SQLite vs JSON)\nPresents design, gets approval\nSaves: workspace/docs/plans/2026-02-25-notes-cli-design.md\nInvokes writing-plans\n\n→ Writing-plans skill:\n\nAsks: TDD or direct? Commit frequency?\nCreates plan: 24 tasks, 2-5 min each\nSaves: workspace/docs/plans/2026-02-25-notes-cli-plan.md\nInvokes executing-plans\n\n→ Executing-plans skill:\n\nBatch 1 (tasks 1-5): Project setup → Checkpoint ✓\nBatch 2 (tasks 6-10): Create note feature → Checkpoint ✓\nBatch 3 (tasks 11-15): List notes feature → Checkpoint ✓\n(continues until complete)\n\nResult: Working CLI tool, fully documented, tested, and memory-tracked." }, { "title": "Individual Skill Files", "body": "brainstorming/SKILL.md — 279 lines, full process + rationalization counters\nwriting-plans/SKILL.md — 10KB, methodology questions + task templates\nexecuting-plans/SKILL.md — 9KB, batching logic + sessions_spawn integration\n\nEach skill can be used independently or as part of the complete workflow." }, { "title": "Attribution", "body": "Based on obra/superpowers by Jesse Vincent.\n\nAdapted for OpenClaw's personal assistant architecture with memory integration, methodology questions (not mandates), sessions_spawn workflow, and single workspace model." }, { "title": "License", "body": "MIT (following obra/superpowers)" }, { "title": "Resources", "body": "GitHub: https://github.com/brothaakhee/superclaw (coming soon)\nOriginal Framework: https://github.com/obra/superpowers\nOpenClaw Docs: https://docs.openclaw.ai" } ], "body": "Superclaw ⚔️\n\nDisciplined software development workflow for OpenClaw agents\n\nBased on obra/superpowers by Jesse Vincent.\n\nWhat This Skill Package Does\n\nSuperclaw prevents your agent from jumping straight into code. It enforces a three-phase workflow:\n\n🧠 Brainstorming (brainstorming/SKILL.md) — Design before code\n📋 Writing Plans (writing-plans/SKILL.md) — Plan before implementation\n⚙️ Executing Plans (executing-plans/SKILL.md) — Batched execution with checkpoints\n\nAll three skills chain automatically when building software.\n\nHow It Works\nPhase 1: Brainstorming (Design Before Code)\n\nTriggers: When creating features, building components, adding functionality\n\nProcess:\n\nCheck context (MEMORY.md, USER.md, daily logs)\nAsk Socratic questions (requirements, constraints, trade-offs)\nPropose 2-3 approaches with pros/cons\nPresent design\nGet approval\nSave design document to workspace/docs/plans/YYYY-MM-DD--design.md\nAutomatically invoke writing-plans skill\n\nHard Gate: No code until design approved.\n\nPhase 2: Writing Plans (Plan Before Implementation)\n\nTriggers: When you have an approved design\n\nProcess:\n\nASK about methodology (TDD? Direct implementation?)\nAsk about commit frequency\nBreak work into 2-5 minute tasks\nSave implementation plan to workspace/docs/plans/YYYY-MM-DD--plan.md\nAutomatically invoke executing-plans skill\n\nKey Feature: Questions, not mandates. Respects user preferences and time constraints.\n\nPhase 3: Executing Plans (Batched Execution with Checkpoints)\n\nTriggers: When you have an implementation plan\n\nProcess:\n\nLoad plan from document\nBatch tasks into groups of 3-5\nExecute batch (using sessions_spawn for isolation)\nReview outputs\nCheckpoint (\"Batch N complete. Continue?\")\nUpdate memory/YYYY-MM-DD.md with progress\nRepeat until complete\n\nHard Gate: Maximum 5 tasks per batch. Checkpoints cannot be skipped.\n\nWhy Use Superclaw?\n\nWithout Superclaw:\n\nAgent jumps to code in seconds (no design, no plan)\nErrors compound across many tasks\nNo checkpoints → can't pause/resume\nMental plans disappear\n\nWith Superclaw:\n\nDesign → Plan → Execute (enforced)\nErrors caught early (batching prevents cascades)\nProgress tracked in memory\nResumable, reviewable, auditable\nInstallation\nnpx clawhub@latest install superclaw\n\n\nSkills auto-load when relevant tasks are detected.\n\nOpenClaw-Specific Adaptations\nMemory Integration — Checks MEMORY.md, USER.md, daily logs\nMethodology Questions — \"Should we use TDD?\" not \"You must use TDD\"\nSessions_spawn — Fresh subagent per task for isolation\nWorkspace Conventions — Saves to workspace/docs/plans/\nTesting\n\nAll skills pressure-tested with RED-GREEN-REFACTOR methodology:\n\nSkill\tRED (without skill)\tGREEN (with skill)\nBrainstorming\tCoded in 12s\tAsked questions, got approval\nWriting-Plans\tCoded in 73s\tAsked methodology, created plan\nExecuting-Plans\t10 tasks in 40s\t4 batches with checkpoints\n\nIntegration test: All 3 skills chained automatically and delivered working CLI ✅\n\nExample Workflow\n\nUser: \"Build a markdown notes CLI\"\n\n→ Brainstorming skill:\n\nAsks: Storage format? Search needed? Tagging?\nProposes: 3 approaches (flat files vs SQLite vs JSON)\nPresents design, gets approval\nSaves: workspace/docs/plans/2026-02-25-notes-cli-design.md\nInvokes writing-plans\n\n→ Writing-plans skill:\n\nAsks: TDD or direct? Commit frequency?\nCreates plan: 24 tasks, 2-5 min each\nSaves: workspace/docs/plans/2026-02-25-notes-cli-plan.md\nInvokes executing-plans\n\n→ Executing-plans skill:\n\nBatch 1 (tasks 1-5): Project setup → Checkpoint ✓\nBatch 2 (tasks 6-10): Create note feature → Checkpoint ✓\nBatch 3 (tasks 11-15): List notes feature → Checkpoint ✓\n(continues until complete)\n\nResult: Working CLI tool, fully documented, tested, and memory-tracked.\n\nIndividual Skill Files\nbrainstorming/SKILL.md — 279 lines, full process + rationalization counters\nwriting-plans/SKILL.md — 10KB, methodology questions + task templates\nexecuting-plans/SKILL.md — 9KB, batching logic + sessions_spawn integration\n\nEach skill can be used independently or as part of the complete workflow.\n\nAttribution\n\nBased on obra/superpowers by Jesse Vincent.\n\nAdapted for OpenClaw's personal assistant architecture with memory integration, methodology questions (not mandates), sessions_spawn workflow, and single workspace model.\n\nLicense\n\nMIT (following obra/superpowers)\n\nResources\nGitHub: https://github.com/brothaakhee/superclaw (coming soon)\nOriginal Framework: https://github.com/obra/superpowers\nOpenClaw Docs: https://docs.openclaw.ai" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/brothaakhee/superclaw", "publisherUrl": "https://clawhub.ai/brothaakhee/superclaw", "owner": "brothaakhee", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/superclaw", "downloadUrl": "https://openagent3.xyz/downloads/superclaw", "agentUrl": "https://openagent3.xyz/skills/superclaw/agent", "manifestUrl": "https://openagent3.xyz/skills/superclaw/agent.json", "briefUrl": "https://openagent3.xyz/skills/superclaw/agent.md" } }