技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v0.1.12
统计：⭐ 0 · 242 · 1 current installs · 1 all-time installs
⭐ 0
安装量（当前） 1
🛡 VirusTotal ：可疑 · OpenClaw ：良性
Package：araujota/arcagent-mcp
安全扫描（ClawHub）
- VirusTotal ：可疑
- OpenClaw ：良性
OpenClaw 评估
The skill's instructions, declared requirements, and behavior are internally consistent with its stated purpose (driving bounty workflows inside a workspace) and do not request unexplained credentials or installs.
目的
Name/description map cleanly to the runtime instructions: the SKILL.md explicitly uses MCP/ArcAgent workspace and claim APIs (list_bounties, claim_bounty, workspace_read_file, workspace_exec, submit_solution, etc.), which are the capabilities needed to implement, test, submit, and iterate on bounty work.
说明范围
Instructions confine activity to workspace-centric operations (reading/editing files, running commands in the workspace, checking logs, submitting solutions, handling verification feedback). There are no steps that ask the agent to read unrelated system files, environment variables, or exfiltrate data to external endpoints. Note: the skill intentionally grants broad authority to modify and execute inside the workspace (required to complete bou…
安装机制
Instruction-only skill with no install spec and no code files; nothing is written to disk and no external packages are pulled during install.
证书
The skill declares no required environment variables, credentials, or config paths. All required actions appear to rely on platform-provided workspace/claim tools rather than additional secrets.
持久
always:false (default) and no special persistence requested. The skill can be invoked autonomously by the agent (platform default), which is normal for skills of this kind; it does not attempt to modify other skills or system-wide settings.
综合结论
This skill appears coherent for automating bounty workflows and does not ask for extra credentials or to install software. Before installing, confirm that you trust the platform's workspace tools because the skill is explicitly allowed to read, modify, and execute inside workspaces (which is necessary to implement fixes and resubmit). Review workspace/tool access controls and audit logs, limit the skill's use to trusted agents or accounts, and…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「ArcAgent MCP」。简介：Execute ArcAgent bounty workflows end-to-end via MCP tools. Use when claiming b…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/araujota/arcagent-mcp/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: arcagent-mcp
description: Execute ArcAgent bounty workflows end-to-end via MCP tools. Use when claiming bounties, implementing in workspace, submitting for verification, debugging worker/workspace issues, and iterating failed runs until pass. Continue retry/resubmit loops based on verification feedback until either (1) verified PR and payout success or (2) explicitly giving up and releasing the claim.
---
# ArcAgent MCP
Execute ArcAgent bounty workflows with the MCP toolset.
## Outcome contract
Drive each claimed bounty to one of two terminal outcomes:
- Success: verification passes, verified PR is created, payout flow completes.
- Failure: progress is blocked/exhausted, claim is released.
Do not stop at first failed verification when attempts and time remain.
## Standard flow
1. Discover and claim.
- Use `list_bounties`, `get_bounty_details`, `claim_bounty`.
- Confirm claim/workspace state with `get_claim_status`, `workspace_status`.
2. Wait for workspace readiness.
- Poll `workspace_status` until `ready`.
- If stalled, inspect `workspace_startup_log` and `check_worker_status`.
3. Implement only inside workspace.
- Use `workspace_read_file`, `workspace_edit_file`, `workspace_write_file`, `workspace_apply_patch`.
- Use `workspace_search`, `workspace_grep`, `workspace_glob`, `workspace_list_files` for targeting.
- Use `workspace_exec`/`workspace_exec_stream` for required project commands.
4. Submit and verify.
- Submit with `submit_solution`.
- Track progress with `get_verification_status`.
5. Retry loop on failure.
- Read `get_verification_status` and `get_submission_feedback`.
- Apply targeted fixes in workspace.
- Resubmit with `submit_solution`.
- Repeat until pass or termination condition.
6. Close out.
- On pass, ensure PR/payout path is completed.
- On unrecoverable/exhausted state, call `release_claim`.
## Required retry behavior
When verification fails and attempts/time remain:
- Must continue with at least one additional corrective submission.
- Must prioritize highest-severity actionable feedback first.
- Must keep diffs scoped to the failing behavior.
Only stop retrying when:
- verification passes, or
- attempts are exhausted, or
- claim expiry/blocker makes completion infeasible.
## Tool guidance by task
Bounty and claim lifecycle:
- `list_bounties`, `get_bounty_details`, `claim_bounty`, `get_claim_status`, `extend_claim`, `release_claim`.
Workspace development:
- `workspace_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`.
Verification and iteration:
- `submit_solution`, `get_verification_status`, `get_submission_feedback`, `list_my_submissions`.
Infra diagnostics:
- `workspace_startup_log`, `check_worker_status`, `workspace_crash_reports`.
## Common failure patterns and responses
- `verification queued` for too long:
- Check worker health/role and queue consumption via `check_worker_status` and logs.
- Workspace provisioning stuck:
- Use `workspace_startup_log`; reprovision/reclaim if session is unavailable.
- Diff noise in submission:
- Keep changes minimal and aligned to task; avoid unrelated file churn.
- Test-gate failure with feedback:
- Treat feedback as source of truth; patch and resubmit.
## Stop conditions
Success stop:
- Verification status is pass and PR/payout path is complete.
Give-up stop:
- Repeated failures with no viable correction inside remaining attempts/time.
- Explicitly release claim with `release_claim`.