{
  "schemaVersion": "1.0",
  "item": {
    "slug": "soulforge",
    "name": "Soulforge",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jamesrp13/soulforge",
    "canonicalUrl": "https://clawhub.ai/jamesrp13/soulforge",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/soulforge",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=soulforge",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/workflow-format.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": "2026-05-07T17:22:31.273Z",
      "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/soulforge"
    },
    "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/soulforge",
    "agentPageUrl": "https://openagent3.xyz/skills/soulforge/agent",
    "manifestUrl": "https://openagent3.xyz/skills/soulforge/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/soulforge/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": "Soulforge (Effective Use Guide)",
        "body": "This is not a full engine reference. This is the operating playbook for getting high-quality autonomous coding outcomes with Soulforge."
      },
      {
        "title": "Core Operating Model",
        "body": "Use Soulforge when you want: plan → implement → verify/test → PR → review/fix loops with minimal babysitting.\n\nPreferred workflows:\n\nfeature-dev for end-to-end feature delivery\nbugfix for diagnose-first, surgical fixes\nreview-loop for tightening an existing PR until clean"
      },
      {
        "title": "Golden Rules (Most Important)",
        "body": "Never run from repo main checkout.\n\nSoulforge now enforces this guardrail.\n\n\nAlways isolate work in worktrees.\n\nDefault base: <repo>/worktrees/\n\n\nKeep tasks tightly scoped.\n\nSpecific issue, explicit acceptance criteria, explicit DO-NOT list.\n\n\nTreat review findings with discipline.\n\nFIX in-scope issues.\nMark genuine extras as SEPARATE.\n\n\nUse callback-exec only.\n\nHTTP callback mode is removed."
      },
      {
        "title": "Workdir / Worktree safety",
        "body": "If --workdir is omitted, Soulforge can auto-provision a worktree under <repo>/worktrees/....\nMain checkout is blocked (including bare+worktree edge cases).\nDirty worktrees are rejected for run start.\nOut-of-base workdirs are blocked unless explicitly overridden."
      },
      {
        "title": "Checkpoint model",
        "body": "approve/reject is gone.\nUse structured completion via soulforge complete ....\nPause checkpoints are type: pause."
      },
      {
        "title": "Callback model",
        "body": "Use --callback-exec.\nTemplate vars include:\n\n{{run_id}}, {{step_id}}, {{step_status}}, {{status}}, {{task}}\n{{callback_message}} (step-level, preferred)\n{{prompt}} remains for backward compatibility in pause scenarios"
      },
      {
        "title": "Feature build",
        "body": "soulforge run feature-dev \"Implement <issue-url>.\nConstraints: max 2 stories. DO NOT refactor unrelated modules.\" \\\n  --workdir /abs/path/to/repo/worktrees/feat-xyz \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'"
      },
      {
        "title": "Bugfix",
        "body": "soulforge run bugfix \"Fix <issue-url> with failing test first; minimal patch only.\" \\\n  --workdir /abs/path/to/repo/worktrees/fix-xyz \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'"
      },
      {
        "title": "Review-only tightening on an existing PR",
        "body": "soulforge run review-loop \"Review PR #123 and fix only in-scope findings.\" \\\n  --workdir /abs/path/to/repo/worktrees/pr-123 \\\n  --var pr_number=123 \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'"
      },
      {
        "title": "1) Give a tight task contract",
        "body": "Include:\n\ntarget issue/PR URL\nexplicit in-scope list\nexplicit out-of-scope list\nobjective success criteria"
      },
      {
        "title": "2) Keep iteration loops short",
        "body": "If a PR loops repeatedly:\n\ncreate/update .soulforge-progress.md in worktree with exact outstanding fixes\nrun review-loop constrained to remaining findings"
      },
      {
        "title": "3) Handle gates like an operator, not a coder",
        "body": "At review gate:\n\nmove in-scope defects to FIX\nseparate unrelated ideas into follow-up issues\navoid “while we’re here” drift"
      },
      {
        "title": "4) Expect long fix steps; optimize signal",
        "body": "Long fix steps are normal for real refactors. Your job is quality control at gates, not interrupting active runs."
      },
      {
        "title": "Practical Triage Heuristic",
        "body": "When code-review returns findings:\n\nHigh/Medium tied to original issue: FIX now\nLow tied to original issue correctness: usually FIX now\nAnything outside scope: SEPARATE"
      },
      {
        "title": "Anti-Patterns (Avoid)",
        "body": "Running multiple workflows in the same checkout\nAllowing scope creep in repeated review-fix loops\nMerging with known Highs because “tests pass”\nTreating this skill as generic Soulforge docs instead of an execution playbook"
      },
      {
        "title": "Minimal Status Workflow for Operator",
        "body": "Start run\nWait for review gate\nTriage with strict scope discipline\nRepeat until pass\nMerge\nPull main + build + npm link + daemon restart (when local runtime should track latest)"
      },
      {
        "title": "Notes",
        "body": "If loops hit max_loops, spawn a fresh constrained review-loop run with a scope lock file.\nFor long-running initiatives, keep a brief run ledger in the channel (run id → PR → status)."
      }
    ],
    "body": "Soulforge (Effective Use Guide)\n\nThis is not a full engine reference. This is the operating playbook for getting high-quality autonomous coding outcomes with Soulforge.\n\nCore Operating Model\n\nUse Soulforge when you want: plan → implement → verify/test → PR → review/fix loops with minimal babysitting.\n\nPreferred workflows:\n\nfeature-dev for end-to-end feature delivery\nbugfix for diagnose-first, surgical fixes\nreview-loop for tightening an existing PR until clean\nGolden Rules (Most Important)\nNever run from repo main checkout.\nSoulforge now enforces this guardrail.\nAlways isolate work in worktrees.\nDefault base: <repo>/worktrees/\nKeep tasks tightly scoped.\nSpecific issue, explicit acceptance criteria, explicit DO-NOT list.\nTreat review findings with discipline.\nFIX in-scope issues.\nMark genuine extras as SEPARATE.\nUse callback-exec only.\nHTTP callback mode is removed.\nCurrent Behavior You Should Rely On\nWorkdir / Worktree safety\nIf --workdir is omitted, Soulforge can auto-provision a worktree under <repo>/worktrees/....\nMain checkout is blocked (including bare+worktree edge cases).\nDirty worktrees are rejected for run start.\nOut-of-base workdirs are blocked unless explicitly overridden.\nCheckpoint model\napprove/reject is gone.\nUse structured completion via soulforge complete ....\nPause checkpoints are type: pause.\nCallback model\nUse --callback-exec.\nTemplate vars include:\n{{run_id}}, {{step_id}}, {{step_status}}, {{status}}, {{task}}\n{{callback_message}} (step-level, preferred)\n{{prompt}} remains for backward compatibility in pause scenarios\nRecommended Command Patterns\nFeature build\nsoulforge run feature-dev \"Implement <issue-url>.\nConstraints: max 2 stories. DO NOT refactor unrelated modules.\" \\\n  --workdir /abs/path/to/repo/worktrees/feat-xyz \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'\n\nBugfix\nsoulforge run bugfix \"Fix <issue-url> with failing test first; minimal patch only.\" \\\n  --workdir /abs/path/to/repo/worktrees/fix-xyz \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'\n\nReview-only tightening on an existing PR\nsoulforge run review-loop \"Review PR #123 and fix only in-scope findings.\" \\\n  --workdir /abs/path/to/repo/worktrees/pr-123 \\\n  --var pr_number=123 \\\n  --callback-exec 'openclaw agent --session-key \"agent:cpto:slack:channel:c0af7b05h28\" --message \"Soulforge {{run_id}} {{step_id}} {{step_status}}\" --deliver'\n\nHow to Maximize Autonomous Quality\n1) Give a tight task contract\n\nInclude:\n\ntarget issue/PR URL\nexplicit in-scope list\nexplicit out-of-scope list\nobjective success criteria\n2) Keep iteration loops short\n\nIf a PR loops repeatedly:\n\ncreate/update .soulforge-progress.md in worktree with exact outstanding fixes\nrun review-loop constrained to remaining findings\n3) Handle gates like an operator, not a coder\n\nAt review gate:\n\nmove in-scope defects to FIX\nseparate unrelated ideas into follow-up issues\navoid “while we’re here” drift\n4) Expect long fix steps; optimize signal\n\nLong fix steps are normal for real refactors. Your job is quality control at gates, not interrupting active runs.\n\nPractical Triage Heuristic\n\nWhen code-review returns findings:\n\nHigh/Medium tied to original issue: FIX now\nLow tied to original issue correctness: usually FIX now\nAnything outside scope: SEPARATE\nAnti-Patterns (Avoid)\nRunning multiple workflows in the same checkout\nAllowing scope creep in repeated review-fix loops\nMerging with known Highs because “tests pass”\nTreating this skill as generic Soulforge docs instead of an execution playbook\nMinimal Status Workflow for Operator\nStart run\nWait for review gate\nTriage with strict scope discipline\nRepeat until pass\nMerge\nPull main + build + npm link + daemon restart (when local runtime should track latest)\nNotes\nIf loops hit max_loops, spawn a fresh constrained review-loop run with a scope lock file.\nFor long-running initiatives, keep a brief run ledger in the channel (run id → PR → status)."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jamesrp13/soulforge",
    "publisherUrl": "https://clawhub.ai/jamesrp13/soulforge",
    "owner": "jamesrp13",
    "version": "1.4.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/soulforge",
    "downloadUrl": "https://openagent3.xyz/downloads/soulforge",
    "agentUrl": "https://openagent3.xyz/skills/soulforge/agent",
    "manifestUrl": "https://openagent3.xyz/skills/soulforge/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/soulforge/agent.md"
  }
}