arcagent-mcp
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.
Best use case
arcagent-mcp is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using arcagent-mcp should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/arcagent-mcp/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How arcagent-mcp Compares
| Feature / Agent | arcagent-mcp | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# 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`.
Related Skills
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
小红书长图文发布 Skill
## 概述