{
  "schemaVersion": "1.0",
  "item": {
    "slug": "arcagent-mcp",
    "name": "ArcAgent MCP",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/araujota/arcagent-mcp",
    "canonicalUrl": "https://clawhub.ai/araujota/arcagent-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/arcagent-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=arcagent-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "agents/openai.yaml"
    ],
    "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/arcagent-mcp"
    },
    "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/arcagent-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/arcagent-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arcagent-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arcagent-mcp/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": "ArcAgent MCP",
        "body": "Execute ArcAgent bounty workflows with the MCP toolset."
      },
      {
        "title": "Outcome contract",
        "body": "Drive each claimed bounty to one of two terminal outcomes:\n\nSuccess: verification passes, verified PR is created, payout flow completes.\nFailure: progress is blocked/exhausted, claim is released.\n\nDo not stop at first failed verification when attempts and time remain."
      },
      {
        "title": "Standard flow",
        "body": "Discover and claim.\n\nUse list_bounties, get_bounty_details, claim_bounty.\nConfirm claim/workspace state with get_claim_status, workspace_status.\n\nWait for workspace readiness.\n\nPoll workspace_status until ready.\nIf stalled, inspect workspace_startup_log and check_worker_status.\n\nImplement only inside workspace.\n\nUse workspace_read_file, workspace_edit_file, workspace_write_file, workspace_apply_patch.\nUse workspace_search, workspace_grep, workspace_glob, workspace_list_files for targeting.\nUse workspace_exec/workspace_exec_stream for required project commands.\n\nSubmit and verify.\n\nSubmit with submit_solution.\nTrack progress with get_verification_status.\n\nRetry loop on failure.\n\nRead get_verification_status and get_submission_feedback.\nApply targeted fixes in workspace.\nResubmit with submit_solution.\nRepeat until pass or termination condition.\n\nClose out.\n\nOn pass, ensure PR/payout path is completed.\nOn unrecoverable/exhausted state, call release_claim."
      },
      {
        "title": "Required retry behavior",
        "body": "When verification fails and attempts/time remain:\n\nMust continue with at least one additional corrective submission.\nMust prioritize highest-severity actionable feedback first.\nMust keep diffs scoped to the failing behavior.\n\nOnly stop retrying when:\n\nverification passes, or\nattempts are exhausted, or\nclaim expiry/blocker makes completion infeasible."
      },
      {
        "title": "Tool guidance by task",
        "body": "Bounty and claim lifecycle:\n\nlist_bounties, get_bounty_details, claim_bounty, get_claim_status, extend_claim, release_claim.\n\nWorkspace development:\n\nworkspace_status, workspace_read_file, workspace_batch_read, workspace_edit_file, workspace_apply_patch, workspace_write_file, workspace_batch_write, workspace_exec, workspace_exec_stream, workspace_shell.\n\nVerification and iteration:\n\nsubmit_solution, get_verification_status, get_submission_feedback, list_my_submissions.\n\nInfra diagnostics:\n\nworkspace_startup_log, check_worker_status, workspace_crash_reports."
      },
      {
        "title": "Common failure patterns and responses",
        "body": "verification queued for too long:\n\nCheck worker health/role and queue consumption via check_worker_status and logs.\n\n\n\nWorkspace provisioning stuck:\n\nUse workspace_startup_log; reprovision/reclaim if session is unavailable.\n\n\n\nDiff noise in submission:\n\nKeep changes minimal and aligned to task; avoid unrelated file churn.\n\n\n\nTest-gate failure with feedback:\n\nTreat feedback as source of truth; patch and resubmit."
      },
      {
        "title": "Stop conditions",
        "body": "Success stop:\n\nVerification status is pass and PR/payout path is complete.\n\nGive-up stop:\n\nRepeated failures with no viable correction inside remaining attempts/time.\nExplicitly release claim with release_claim."
      }
    ],
    "body": "ArcAgent MCP\n\nExecute ArcAgent bounty workflows with the MCP toolset.\n\nOutcome contract\n\nDrive each claimed bounty to one of two terminal outcomes:\n\nSuccess: verification passes, verified PR is created, payout flow completes.\nFailure: progress is blocked/exhausted, claim is released.\n\nDo not stop at first failed verification when attempts and time remain.\n\nStandard flow\nDiscover and claim.\nUse list_bounties, get_bounty_details, claim_bounty.\nConfirm claim/workspace state with get_claim_status, workspace_status.\nWait for workspace readiness.\nPoll workspace_status until ready.\nIf stalled, inspect workspace_startup_log and check_worker_status.\nImplement only inside workspace.\nUse workspace_read_file, workspace_edit_file, workspace_write_file, workspace_apply_patch.\nUse workspace_search, workspace_grep, workspace_glob, workspace_list_files for targeting.\nUse workspace_exec/workspace_exec_stream for required project commands.\nSubmit and verify.\nSubmit with submit_solution.\nTrack progress with get_verification_status.\nRetry loop on failure.\nRead get_verification_status and get_submission_feedback.\nApply targeted fixes in workspace.\nResubmit with submit_solution.\nRepeat until pass or termination condition.\nClose out.\nOn pass, ensure PR/payout path is completed.\nOn unrecoverable/exhausted state, call release_claim.\nRequired retry behavior\n\nWhen verification fails and attempts/time remain:\n\nMust continue with at least one additional corrective submission.\nMust prioritize highest-severity actionable feedback first.\nMust keep diffs scoped to the failing behavior.\n\nOnly stop retrying when:\n\nverification passes, or\nattempts are exhausted, or\nclaim expiry/blocker makes completion infeasible.\nTool guidance by task\n\nBounty and claim lifecycle:\n\nlist_bounties, get_bounty_details, claim_bounty, get_claim_status, extend_claim, release_claim.\n\nWorkspace development:\n\nworkspace_status, workspace_read_file, workspace_batch_read, workspace_edit_file, workspace_apply_patch, workspace_write_file, workspace_batch_write, workspace_exec, workspace_exec_stream, workspace_shell.\n\nVerification and iteration:\n\nsubmit_solution, get_verification_status, get_submission_feedback, list_my_submissions.\n\nInfra diagnostics:\n\nworkspace_startup_log, check_worker_status, workspace_crash_reports.\nCommon failure patterns and responses\n\nverification queued for too long:\n\nCheck worker health/role and queue consumption via check_worker_status and logs.\n\nWorkspace provisioning stuck:\n\nUse workspace_startup_log; reprovision/reclaim if session is unavailable.\n\nDiff noise in submission:\n\nKeep changes minimal and aligned to task; avoid unrelated file churn.\n\nTest-gate failure with feedback:\n\nTreat feedback as source of truth; patch and resubmit.\nStop conditions\n\nSuccess stop:\n\nVerification status is pass and PR/payout path is complete.\n\nGive-up stop:\n\nRepeated failures with no viable correction inside remaining attempts/time.\nExplicitly release claim with release_claim."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/araujota/arcagent-mcp",
    "publisherUrl": "https://clawhub.ai/araujota/arcagent-mcp",
    "owner": "araujota",
    "version": "0.1.12",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/arcagent-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/arcagent-mcp",
    "agentUrl": "https://openagent3.xyz/skills/arcagent-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arcagent-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arcagent-mcp/agent.md"
  }
}