{
  "schemaVersion": "1.0",
  "item": {
    "slug": "superpowers",
    "name": "Superpowers Dev Workflow",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/wlshlad85/superpowers",
    "canonicalUrl": "https://clawhub.ai/wlshlad85/superpowers",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/superpowers",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=superpowers",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/brainstorming.md",
      "references/finishing-branch.md",
      "references/subagent-development.md",
      "references/systematic-debugging.md",
      "references/tdd.md",
      "references/writing-plans.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/superpowers"
    },
    "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/superpowers",
    "agentPageUrl": "https://openagent3.xyz/skills/superpowers/agent",
    "manifestUrl": "https://openagent3.xyz/skills/superpowers/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/superpowers/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": "Superpowers — OpenClaw Edition",
        "body": "Adapted from obra/superpowers. Mandatory workflow — not suggestions."
      },
      {
        "title": "The Pipeline",
        "body": "Idea → Brainstorm → Plan → Subagent-Driven Build (TDD) → Code Review → Finish Branch\n\nEvery coding task follows this pipeline. \"Too simple to need a design\" is always wrong."
      },
      {
        "title": "Phase 1: Brainstorming",
        "body": "Trigger: User wants to build something. Activate before touching any code.\n\nSee: references/brainstorming.md\n\nSummary:\n\nExplore project context (files, docs, recent commits)\nAsk clarifying questions — one at a time, prefer multiple choice\nPropose 2–3 approaches with trade-offs + recommendation\nPresent design in sections, get approval after each\nWrite design doc → docs/plans/YYYY-MM-DD-<topic>-design.md → commit\nHand off to Phase 2: Writing Plans\n\nHARD GATE: Do NOT write any code until user approves design."
      },
      {
        "title": "Phase 2: Writing Plans",
        "body": "Trigger: Design approved. Activated by brainstorming phase.\n\nSee: references/writing-plans.md\n\nSummary:\n\nWrite a detailed task-by-task implementation plan\nEach task = 2–5 minutes: write test → watch fail → implement → watch pass → commit\nSave to docs/plans/YYYY-MM-DD-<feature>.md\nAnnounce: \"I'm using the writing-plans skill to create the implementation plan.\"\nAfter saving, offer two execution modes:\n\nSubagent-driven (current session): sessions_spawn per task + two-stage review\nManual execution: User runs tasks themselves"
      },
      {
        "title": "Phase 3: Subagent-Driven Development",
        "body": "Trigger: Plan exists, user chooses subagent-driven execution.\n\nSee: references/subagent-development.md\n\nPer-task loop (OpenClaw):\n\nsessions_spawn an implementer subagent with task + full plan context\nWait for completion announcement\nsessions_spawn a spec-reviewer subagent → must confirm code matches spec\nsessions_spawn a code-quality reviewer subagent → must approve quality\nFix any issues, re-review if needed\nMark task done, move to next\nFinal: dispatch overall code reviewer → hand off to Phase 5\n\nTDD is mandatory in every task. See references/tdd.md."
      },
      {
        "title": "Phase 4: Systematic Debugging",
        "body": "Trigger: Bug, test failure, unexpected behaviour — any technical issue.\n\nSee: references/systematic-debugging.md\n\nHARD GATE: No fixes without root cause investigation first.\n\nFour phases:\n\nRoot Cause Investigation (read errors, reproduce, check recent changes, trace data flow)\nPattern Analysis (find working examples, compare, identify differences)\nHypothesis + Testing (one hypothesis at a time, test to prove/disprove)\nFix + Verification (fix at root, not symptom; verify fix doesn't break anything)"
      },
      {
        "title": "Phase 5: Finishing a Branch",
        "body": "Trigger: All tasks complete, all tests pass.\n\nSee: references/finishing-branch.md\n\nSummary:\n\nVerify all tests pass\nDetermine base branch\nPresent 4 options: merge locally / push + PR / keep / discard\nExecute choice\nClean up"
      },
      {
        "title": "OpenClaw Subagent Dispatch Pattern",
        "body": "When dispatching implementer or reviewer subagents, use sessions_spawn:\n\nGoal: [one sentence]\nContext: [why it matters, which plan file]\nFiles: [exact paths]\nConstraints: [what NOT to do — no scope creep, TDD only]\nVerify: [how to confirm success — tests pass, specific command]\nTask text: [paste full task from plan]\n\nRun sessions_spawn with the task as a detailed prompt. The sub-agent announces results automatically."
      },
      {
        "title": "Key Principles",
        "body": "One question at a time during brainstorm\nTDD always — write failing test first, delete code written before tests\nYAGNI — remove unnecessary features from all designs\nDRY — no duplication\nSystematic over ad-hoc — follow the process especially under time pressure\nEvidence over claims — verify before declaring success\nFrequent commits — after each green test"
      }
    ],
    "body": "Superpowers — OpenClaw Edition\n\nAdapted from obra/superpowers. Mandatory workflow — not suggestions.\n\nThe Pipeline\nIdea → Brainstorm → Plan → Subagent-Driven Build (TDD) → Code Review → Finish Branch\n\n\nEvery coding task follows this pipeline. \"Too simple to need a design\" is always wrong.\n\nPhase 1: Brainstorming\n\nTrigger: User wants to build something. Activate before touching any code.\n\nSee: references/brainstorming.md\n\nSummary:\n\nExplore project context (files, docs, recent commits)\nAsk clarifying questions — one at a time, prefer multiple choice\nPropose 2–3 approaches with trade-offs + recommendation\nPresent design in sections, get approval after each\nWrite design doc → docs/plans/YYYY-MM-DD-<topic>-design.md → commit\nHand off to Phase 2: Writing Plans\n\nHARD GATE: Do NOT write any code until user approves design.\n\nPhase 2: Writing Plans\n\nTrigger: Design approved. Activated by brainstorming phase.\n\nSee: references/writing-plans.md\n\nSummary:\n\nWrite a detailed task-by-task implementation plan\nEach task = 2–5 minutes: write test → watch fail → implement → watch pass → commit\nSave to docs/plans/YYYY-MM-DD-<feature>.md\nAnnounce: \"I'm using the writing-plans skill to create the implementation plan.\"\nAfter saving, offer two execution modes:\nSubagent-driven (current session): sessions_spawn per task + two-stage review\nManual execution: User runs tasks themselves\nPhase 3: Subagent-Driven Development\n\nTrigger: Plan exists, user chooses subagent-driven execution.\n\nSee: references/subagent-development.md\n\nPer-task loop (OpenClaw):\n\nsessions_spawn an implementer subagent with task + full plan context\nWait for completion announcement\nsessions_spawn a spec-reviewer subagent → must confirm code matches spec\nsessions_spawn a code-quality reviewer subagent → must approve quality\nFix any issues, re-review if needed\nMark task done, move to next\nFinal: dispatch overall code reviewer → hand off to Phase 5\n\nTDD is mandatory in every task. See references/tdd.md.\n\nPhase 4: Systematic Debugging\n\nTrigger: Bug, test failure, unexpected behaviour — any technical issue.\n\nSee: references/systematic-debugging.md\n\nHARD GATE: No fixes without root cause investigation first.\n\nFour phases:\n\nRoot Cause Investigation (read errors, reproduce, check recent changes, trace data flow)\nPattern Analysis (find working examples, compare, identify differences)\nHypothesis + Testing (one hypothesis at a time, test to prove/disprove)\nFix + Verification (fix at root, not symptom; verify fix doesn't break anything)\nPhase 5: Finishing a Branch\n\nTrigger: All tasks complete, all tests pass.\n\nSee: references/finishing-branch.md\n\nSummary:\n\nVerify all tests pass\nDetermine base branch\nPresent 4 options: merge locally / push + PR / keep / discard\nExecute choice\nClean up\nOpenClaw Subagent Dispatch Pattern\n\nWhen dispatching implementer or reviewer subagents, use sessions_spawn:\n\nGoal: [one sentence]\nContext: [why it matters, which plan file]\nFiles: [exact paths]\nConstraints: [what NOT to do — no scope creep, TDD only]\nVerify: [how to confirm success — tests pass, specific command]\nTask text: [paste full task from plan]\n\n\nRun sessions_spawn with the task as a detailed prompt. The sub-agent announces results automatically.\n\nKey Principles\nOne question at a time during brainstorm\nTDD always — write failing test first, delete code written before tests\nYAGNI — remove unnecessary features from all designs\nDRY — no duplication\nSystematic over ad-hoc — follow the process especially under time pressure\nEvidence over claims — verify before declaring success\nFrequent commits — after each green test"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wlshlad85/superpowers",
    "publisherUrl": "https://clawhub.ai/wlshlad85/superpowers",
    "owner": "wlshlad85",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/superpowers",
    "downloadUrl": "https://openagent3.xyz/downloads/superpowers",
    "agentUrl": "https://openagent3.xyz/skills/superpowers/agent",
    "manifestUrl": "https://openagent3.xyz/skills/superpowers/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/superpowers/agent.md"
  }
}