skilld
All skills
cat-xierluo avatar

/multi-agent-orchestration

@41268aa
by 杨卫薪律师cat-xierluo/legal-skills705 stars
106

编排两个以上边界独立的本地 worker，使用 Orca Run/Task/Dispatch、独立 worktree/session 或 tmux 回退，由 PM 负责拆解、派发、巡检、429 停滞恢复、独立验收、PR 收口与临时资源清理；也用于用户明确要求“并行推进”“多个 worker”“PM 总控”“Wave Autopilot”或防止 PM 直接实现逃逸。不要用于单个短任务、纯状态同步，或仅需 Git 分支、提交、PR、merge 规则的工作。

Ask your Agent

Use this Skill: https://skilld.dev/gh/cat-xierluo/legal-skills/multi-agent-orchestration

This session only. Nothing lands on disk.

templateswave-summary.md

≈366 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Wave Summary

Wave

  • Wave ID: {{wave_id}}
  • Goal ID: {{goal_id}}
  • Loop iteration: {{loop_iteration}}
  • Base ref: {{base_ref}}
  • Goal: {{wave_goal}}
  • Started at: {{started_at}}
  • Closed at: {{closed_at}}

Workers

Worker Branch Type Settings/Profile Provider / Model Slot Exit state PR Notes
{{wave_worker_id}} {{branch_name}} {{worker_type}} {{settings_or_profile_path}} {{api_provider}} / {{model_name}} {{provider_slot}} {{merged_blocked_deferred_restarted}} {{pr_url}} {{notes}}

Exit states: merged, done-unmerged, blocked, deferred, restarted.

Provider And Model Review

Worker Isolation STATUS Commit cadence Scope Verification Review fixes Quality notes
{{wave_worker_id}} {{ok_or_issue}} {{ok_or_issue}} {{ok_or_issue}} {{ok_or_issue}} {{ok_or_issue}} {{count}} {{notes}}

Decisions

  • Parallelism: {{keep_increase_reduce_next_wave_worker_count}}
  • Provider routing: {{provider_routing_changes}}
  • Deferred items: {{deferred_items}}
  • Next wave entry criteria: {{next_wave_entry_criteria}}

Goal Loop Decision

  • Continue decision: {{continue_stop}}
  • Continue reason: {{continue_reason}}
  • Stop condition hit: {{stop_condition_or_none}}
  • Remaining executable tasks: {{remaining_executable_tasks}}
  • Next Wave ID: {{next_wave_id_or_none}}

Source: SKILL.md on GitHub

Third-party checks

1 alert10d3 checks · Risk HIGH
  • Gen Agent Trust Hub10d

    The skill is a comprehensive multi-agent orchestration framework designed to manage multiple AI agents across isolated git worktrees and terminal sessions. It incorporates robust internal security controls such as an installation guard and a scope guard to limit the actions of sub-agents. It uses pinned executables and cryptographic hashes to verify script integrity. A potential risk of indirect prompt injection exists because the manager agent processes output from worker agents, but this is inherent to its function and mitigated by instructional boundaries and secret redaction.

  • Socket10d

    2 alerts: gptSecurity, gptAnomaly

  • Snyk10d

    Risk: LOW · No issues

Provenance

Signed by skilld at 41268aa. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated yesterday

Capability

Other metadata
metadata
{
  "version": "2.31.1",
  "homepage": "https://github.com/cat-xierluo/legal-skills",
  "author": "杨卫薪律师（微信ywxlaw）"
}

README badge

README badge for cat-xierluo/legal-skills/multi-agent-orchestration