← 返回 Skills 市场
muselinn

FIS Architecture

作者 Linn · GitHub ↗ · v3.3.1
cross-platform ✓ 安全检测通过
869
总下载
3
收藏
3
当前安装
20
版本数
在 OpenClaw 中安装
/install fis-architecture
功能描述
Orchestrate multi-agent workflows with JSON tickets and A2A coordination. Use when delegating tasks between CyberMao (Main) and Worker agents (Engineer/Resea...
使用说明 (SKILL.md)

FIS Architecture 3.2 Pro

Multi-agent workflow framework for CyberMao (Main) → Worker coordination using JSON tickets and Discord Forum threads.


When to Use This Skill

Use FIS when:

  • CyberMao (Main) needs to delegate complex tasks to specialized Workers
  • A task requires domain expertise (coding, research, writing)
  • You need to track task status across multiple sessions
  • Multi-step workflows require coordination between agents

Agent Roles:

Role Agent ID Expertise
Architect main Coordination, task routing, user communication
Coding engineer Python, gprMax, algorithms, data analysis
Research researcher Theory, literature, simulation planning
Writing writer Documentation, LaTeX, visualization

Discord Bot Permissions (REQUIRED)

Each agent's Discord bot must have these permissions configured in the Discord server. Without them, Thread creation and messaging will fail silently.

Required Bot Permissions:

  • Send Messages — reply in channels and threads
  • Send Messages in Threads — post inside Forum threads
  • Create Public Threads — create new Forum posts programmatically
  • Read Message History — read thread context
  • Embed Links — send rich embeds in reports
  • Attach Files — upload deliverables

How to configure:

  1. Go to Discord Server Settings → Roles
  2. For each bot role (CyberMao, Researcher, Engineer, Writer), enable the permissions above
  3. Ensure each Forum channel grants these permissions to the relevant bot roles

Verify with:

{ "action": "threadCreate", "channelId": "\x3Cforum_channel_id>", "name": "Permission Test" }

If the bot lacks permissions, the discord tool will return an error.


Tool Configuration

Tool Purpose Path
fis_lifecycle_pro.py Ticket lifecycle (create/status/complete/list) scripts/fis_lifecycle_pro.py
fis_coordinator.py Generate delegation templates (CyberMao only) scripts/fis_coordinator.py
fis_worker_toolkit.py Spawn sub-agents, generate reports (Workers only) scripts/fis_worker_toolkit.py

Python Environment: Requires Python 3.8+ with standard library only (no external dependencies).


Core Workflow

Step 1: CyberMao Delegates Task

# Generate ticket + Thread template + A2A command
python3 scripts/fis_coordinator.py delegate \
  --agent engineer \
  --task "Implement GPR signal filter" \
  --forum coding

Output:

  • Ticket ID: TASK_YYYYMMDD_XXX_AGENT
  • Thread template content
  • sessions_send command to notify Worker

Step 2: CyberMao Creates Forum Thread

Use the discord tool to create a Thread in the appropriate Forum channel:

{
  "action": "threadCreate",
  "channelId": "\x3Cforum_channel_id>",
  "name": "TASK_xxx: Implement GPR signal filter"
}

The response returns the new Thread ID. Then notify the Worker with the Thread ID:

python3 scripts/fis_coordinator.py notify \
  --ticket-id TASK_xxx \
  --thread-id \x3Cnew_thread_id>

Execute the generated sessions_send command to notify the Worker.

Step 3: Worker Executes Task

# Check ticket
python3 scripts/fis_lifecycle_pro.py list

# Update status
python3 scripts/fis_lifecycle_pro.py status \
  --ticket-id TASK_xxx --status doing

# Optional: Spawn sub-agent for complex sub-tasks
python3 scripts/fis_worker_toolkit.py spawn \
  --parent-ticket TASK_xxx \
  --subtask "Analyze algorithm complexity"

Worker replies in the Forum Thread using the discord tool:

{
  "action": "threadReply",
  "channelId": "\x3Cthread_id>",
  "content": "Task received. Starting execution."
}

Step 4: Worker Reports Completion

# Generate completion report
python3 scripts/fis_worker_toolkit.py report \
  --parent-ticket TASK_xxx \
  --summary "Successfully implemented GPR filter" \
  --deliverables filter.py test_results.json

Execute the generated sessions_send command to notify CyberMao.

Step 5: CyberMao Finalizes

# View report
python3 scripts/fis_coordinator.py report --ticket-id TASK_xxx

# Mark complete
python3 scripts/fis_lifecycle_pro.py complete --ticket-id TASK_xxx

Archive the Thread and report to User in #daily-chat.


Architecture

User/Linn
    ↓
CyberMao (Main) - Architect, coordinator
    ↓ sessions_send + discord threadCreate
Worker (Engineer/Researcher/Writer) - Domain experts
    ↓ (optional) sessions_spawn mode="run"
SubAgent (temporary, background) - Complex sub-tasks

Key Principles:

  1. A2A via sessions_send — Main calls Workers, Workers report back
  2. Ticket tracking — All tasks have JSON tickets in fis-hub/
  3. Programmatic Thread creation — CyberMao creates Forum Threads via discord tool's threadCreate action
  4. SubAgent background modesessions_spawn with mode="run", no new Thread

Commands Reference

fis_lifecycle_pro.py

# Create ticket
python3 scripts/fis_lifecycle_pro.py create \
  --agent engineer --task "Description" --channel-type coding

# Update status (todo/doing/done)
python3 scripts/fis_lifecycle_pro.py status \
  --ticket-id TASK_xxx --status doing --note "Progress update"

# Mark complete
python3 scripts/fis_lifecycle_pro.py complete --ticket-id TASK_xxx

# List active tickets
python3 scripts/fis_lifecycle_pro.py list

# Archive old tickets
python3 scripts/fis_lifecycle_pro.py archive

fis_coordinator.py (CyberMao only)

# Delegate and generate templates
python3 scripts/fis_coordinator.py delegate \
  --agent researcher --task "GPR theory analysis" --forum theory

# Notify Worker after Thread is created
python3 scripts/fis_coordinator.py notify \
  --ticket-id TASK_xxx --thread-id \x3Cdiscord_thread_id>

# View detailed report
python3 scripts/fis_coordinator.py report --ticket-id TASK_xxx

fis_worker_toolkit.py (Workers only)

# Spawn sub-agent (background, no Thread)
python3 scripts/fis_worker_toolkit.py spawn \
  --parent-ticket TASK_xxx --subtask "Complex sub-task description"

# Generate completion report
python3 scripts/fis_worker_toolkit.py report \
  --parent-ticket TASK_xxx \
  --summary "Completion summary" \
  --deliverables file1.py file2.json

Channel Mapping

Category Forum Channel Worker Tool Flag
RESEARCH 🔬-theory-derivation @Researcher --forum theory
RESEARCH 📊-gpr-simulation @Researcher --forum simulation
DEVELOPMENT 💻-coding @Engineer --forum coding
WRITING 📝-drafts @Writer --forum drafts

Error Handling

If ticket creation fails:

  • Check Python version: python3 --version (need 3.8+)
  • Verify fis-hub/ directory exists and is writable
  • Check disk space

If Thread creation fails:

  • Verify the bot has Create Public Threads permission in the target Forum channel
  • Check that channelId points to a Forum channel (not a regular text channel)
  • Confirm the bot is a member of the server with correct roles

If A2A fails:

  • Verify openclaw.json has agentToAgent.enabled: true
  • Confirm Worker agent ID is in allow list
  • Check Worker session is active

If sub-agent spawn fails:

  • Ensure mode="run" is used (not mode="session")
  • Verify task description is clear and specific

Quality Standards

  1. One Task = One Ticket — Never reuse ticket IDs
  2. Status Updates Required — Workers must update status (TODO → DOING → DONE)
  3. Thread Per Task — Each task gets its own Forum Thread (created via threadCreate)
  4. A2A Confirmation — Always confirm receipt via sessions_send
  5. Archive After Complete — Archive Thread after task completion

Configuration

Required in ~/.openclaw/openclaw.json:

{
  "tools": {
    "agentToAgent": {
      "enabled": true,
      "allow": ["main", "researcher", "engineer", "writer"]
    }
  }
}

Testing

Quick A2A Test

# Test connectivity
sessions_send(sessionKey="engineer", message="A2A test")

Thread Creation Test

{ "action": "threadCreate", "channelId": "\x3Cforum_channel_id>", "name": "FIS Test Thread" }

Full Workflow Test

# 1. Create task
python3 scripts/fis_coordinator.py delegate \
  --agent researcher --task "Test task" --forum theory

# 2. Create Forum Thread via discord tool threadCreate

# 3. Notify Worker with Thread ID
python3 scripts/fis_coordinator.py notify \
  --ticket-id TASK_xxx --thread-id \x3Cthread_id>

# 4. Execute A2A command

# 5. Complete
python3 scripts/fis_lifecycle_pro.py complete --ticket-id TASK_xxx

FIS 3.2 Pro | Multi-Agent Workflow Framework

安全使用建议
This skill appears to do what it says (create/manage JSON tickets, generate Discord thread templates, and coordinate sub-agents). Before installing or running it: 1) Review the repository locally to confirm you trust the hardcoded Discord role and forum IDs and the printed A2A/sessions commands. 2) Note it will create/read ticket files under your OpenClaw home (default ~/.openclaw/fis-hub) and scan workspace output/deliverables directories — consider setting FIS_HUB_PATH or OPENCLAW_HOME to an isolated location if you don't want it enumerating your existing workspaces. 3) When executing generated sessions_send or sessions_spawn commands, inspect them first — spawning background sub-agents can increase the blast radius of any subsequent actions. 4) Ensure the Discord bot permissions it requests are intentionally granted to the correct bot accounts. If you need higher assurance, open the truncated generate_report/archive code paths (not fully shown) to confirm they don't read file contents or transmit more than file metadata and small summaries.
功能分析
Type: OpenClaw Skill Name: fis-architecture Version: 3.3.1 The skill bundle implements a multi-agent orchestration framework (FIS Architecture) designed to coordinate tasks between a main agent and specialized workers using JSON-based tickets and Discord Forum threads. The scripts (fis_coordinator.py, fis_lifecycle_pro.py, and fis_worker_toolkit.py) manage task states, generate Discord message templates, and facilitate agent-to-agent communication. While the framework interacts with the local filesystem (~/.openclaw) and calls the 'openclaw' CLI via subprocess to manage sessions, these actions are clearly aligned with the stated purpose of agent coordination and lack any indicators of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The name/description (FIS multi-agent orchestration) matches the actual behavior: creating JSON tickets, generating thread templates, invoking sessions_send/sessions_spawn semantics, and coordinating Workers. Hardcoded Discord role IDs and forum channel mappings are consistent with a Discord-based coordination workflow.
Instruction Scope
SKILL.md and the scripts instruct the agent to create/modify tickets under a shared hub, create Forum threads via the platform 'discord' tool, and call sessions_send/sessions_spawn. The code also attempts to detect the current session via OPENCLAW_SESSION_KEY or by calling the 'openclaw' CLI, and the lifecycle code scans workspace output/deliverables directories for files. These actions are expected for a coordination tool but do access local filesystem metadata and invoke platform CLI/tools — review outputs before broadcasting.
Install Mechanism
No install spec; the skill is instruction-plus-scripts only. It requires Python 3.8+ (standard library only) and uses existing runtime tools (openclaw CLI, platform-provided 'discord' and session APIs). Nothing is downloaded from external URLs or written by an installer.
Credentials
The skill does not declare required env vars, but the code will read optional variables if present (OPENCLAW_SESSION_KEY, OPENCLAW_HOME, FIS_HUB_PATH). It also writes and reads files under the derived OpenClaw home and workspaces (e.g., ~/.openclaw/fis-hub/tickets and workspace-* directories). These accesses are proportionate to ticket/deliverable tracking, but you should be aware it will enumerate files in workspace output/deliverables and include path/metadata in tickets.
Persistence & Privilege
always is false. The skill uses platform session APIs (sessions_send, sessions_spawn) to notify and spawn sub-agents; this is expected for a coordination skill. It does create and manage its own ticket files under the OpenClaw workspace, but it does not change other skills' configs or request elevated system privileges.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install fis-architecture
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fis-architecture 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v3.3.1
v3.3.1: version bump, removed redundant README, updated lifecycle and config scripts
v3.2.1
A2A coordination fixes, Thread archive support, Discord Forum workflow improvements
v3.2.11
- Updated documentation to reference examples/demo.py instead of examples/generate_badges.py. - Removed mention of dynamic OpenClaw version detection from badge features. - Removed the requirement for the openclaw CLI from the dependencies list.
v3.2.10
Clean release
v3.2.8
Clean template release
v3.2.7
Update Ticket Format documentation to match actual usage: full task object structure, objective, scope, deliverables, notes fields
v3.2.6
- Documentation corrections and updates across compatibility, publishing, and review guides. - SKILL.md updated for clarity and formatting, but no workflow or interface changes. - Package metadata refreshed in package.json and skill.json. - No code, interface, or workflow changes in this release.
v3.2.5-lite
fis-architecture 3.2.5-lite - Documentation updates across INSTALL_CHECKLIST.md, OPENCLAW_COMPATIBILITY.md, PUBLISH_GUIDE.md, REVIEW.md, and SKILL.md for clarity and correctness - SKILL.md version bumped to 3.2.5-lite with minor improvements and expanded instructions - No breaking changes to workflow or ticket format - Improved instructions for safe Python helper usage - Maintains file-based, QMD-integrated architecture with optional badge generation tools
v3.2.4-lite
- Legacy FIS 3.1 Python components (memory_manager, skill_registry, and others) fully removed from this release; historical files remain in Git history for reference. - Cleaned up repository by deleting deprecated files in the archive/deprecated/ directory. - Clarified in documentation that old components are not part of current distribution but are available via version history. - No changes to core workflow, ticket formats, or optional helper scripts—upgrade is non-breaking for users of 3.2.x line.
v3.2.3-lite
- Improved clarity of core workflow: emphasized file-based ticket/knowledge system requires no Python for basic use. - Explicitly separated required vs. optional components, with clear review guidance for optional Python scripts. - Updated description to highlight QMD integration, file-first architecture, and removal of any "no Python dependencies" ambiguity. - Minor wording and formatting adjustments for ease of understanding and onboarding.
v3.2.2-lite
FIS Architecture Skill v3.2.2-lite - **Security**: Removed `archive/deprecated/` from the published package (now only in GitHub). - **Documentation**: Clarified that core workflow needs no Python, but helper tools in `lib/` are optional and may require dependencies. - **Documentation**: Added a security warning about the `resources` field in task tickets. - **Documentation**: Included a Security Checklist in INSTALL_CHECKLIST.md. - **Fix**: Replaced "No Python dependencies" with "Core functionality uses no Python" for accuracy.
v3.2.1-lite
v3.2.1-lite features documentation improvements and usage tips: - Added troubleshooting section with common issues and solutions - Added best practices for ticket naming and knowledge organization - Added real-world usage examples in the SubAgent decision tree - Clarified distinction between when to use and not use SubAgents
v3.2.0-lite
v3.2.0-lite — Major simplification with QMD (Query Model Direct) integration and file-based workflow. - Core Python modules for memory, registry, and deadlock detection removed; QMD now handles semantic search and skill indexing. - All task management shifted to simple JSON ticket files; no Python dependencies required for core workflow. - Documentation rewritten for clarity; emphasizes FIS/QMD separation and migration steps. - Subagent badge generator (v7+) retained and improved with visual enhancements. - Legacy and deprecated files archived, resulting in a cleaner and more maintainable codebase.
v3.1.3
v3.1.3: Complete generalization - removed personal config examples, removed unrelated utilities (tts_edge), all examples now use generic placeholders. Privacy-first design.
v3.1.1
Documentation update: Add data isolation notice, clarify that skill provides framework only. Apology for earlier version confusion.
v3.1.0
Initial stable release: P0 core features (shared memory, deadlock detection, skill registry, subagent lifecycle). Experimental KG/gating staged in experimental/ directory.
v3.1.2
Docs update: Clarify Phase 2/3 features are implemented and staged in experimental/, not pending design
v3.1.1-a
Patch release: Revision a
v3.1.1-lite
International release: Full English documentation with bilingual context
v3.1.0-lite
Initial release of FIS 3.1 Lite: multi-agent collaboration framework with shared memory, deadlock detection, skill registry, and subagent lifecycle.
元数据
Slug fis-architecture
版本 3.3.1
许可证
累计安装 3
当前安装数 3
历史版本数 20
常见问题

FIS Architecture 是什么?

Orchestrate multi-agent workflows with JSON tickets and A2A coordination. Use when delegating tasks between CyberMao (Main) and Worker agents (Engineer/Resea... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 869 次。

如何安装 FIS Architecture?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install fis-architecture」即可一键安装,无需额外配置。

FIS Architecture 是免费的吗?

是的,FIS Architecture 完全免费(开源免费),可自由下载、安装和使用。

FIS Architecture 支持哪些平台?

FIS Architecture 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 FIS Architecture?

由 Linn(@muselinn)开发并维护,当前版本 v3.3.1。

💬 留言讨论