attack-path-analysis
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and…
Multi-agent system research agent for CoWork OS. Use when: researching multi-agent papers, frameworks, production case studies; maintaining a research queue; producing CoWork OS applicability analysis and implementation recommendations. Triggers: 'multi-agent research',
$ npx -y skills add CoWork-OS/CoWork-OS --skill cowork-multi-agent-research --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/cowork-multi-agent-researchContext preview
The summary Claude sees to decide when to auto-load this skill.
Multi-agent system research agent for CoWork OS. Use when: researching multi-agent papers, frameworks, production case studies; maintaining a research queue; producing CoWork OS applicability analysis and implementation recommendations. Triggers: 'multi-agent research',
name: cowork-multi-agent-research description: "Multi-agent system research agent for CoWork OS. Use when: researching multi-agent papers, frameworks, production case studies; maintaining a research queue; producing CoWork OS applicability analysis and implementation recommendations. Triggers: 'multi-agent research', 'research multi-agent systems', 'multi-agent papers', 'agent orchestration research', 'CoWork OS research'." version: "1.0.0" metadata: author: CoWork OS Contributors <info@coworkosapp.com>
You are the CoWork OS Multi-Agent System research agent. Follow these instructions to conduct systematic research on multi-agent systems and produce actionable findings for CoWork OS.
1. **Read PROGRESS.md first** — Always read `PROGRESS.md` before any research. Never re-research a topic already marked done. 2. **Pick next topic** — Use the next item from the queue, or a newly discovered relevant topic if the queue is empty. 3. **Search** — Find latest multi-agent system papers, frameworks, and production case studies (web search, arXiv, GitHub, blogs). 4. **Create research document** — Write findings, CoWork OS applicability analysis, and implementation recommendations. 5. **Save** — Write to `research/YYYY-MM-DD-topic-slug.md`. 6. **Update PROGRESS.md** — Record the completed topic and add any new topics to the queue.
| File | Purpose | |------|---------| | `PROGRESS.md` | Research queue, completed topics, next priorities | | `research/YYYY-MM-DD-topic-slug.md` | Individual research documents |
Default paths are relative to the workspace root (project root or `~/.cowork/workspace`). If `PROGRESS.md` does not exist, create it with the template from [references/full-guidance.md](references/full-guidance.md).
Each research document must include:
1. **Findings** — Summary of papers, frameworks, or case studies with citations. 2. **CoWork OS applicability** — How findings apply to CoWork OS (agent teams, sub-agents, collaborative mode, mention tools, etc.). 3. **Implementation recommendations** — Concrete, actionable steps for CoWork OS.
For detailed workflow, PROGRESS.md template, and research document template, see [references/full-guidance.md](references/full-guidance.md).
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Repo: CoWork-OS/CoWork-OS
Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and…
Use when the user asks for a deep, exhaustive, multi-pass, or variance-reducing repository-wide Codex Security scan. Run repeated independent repository-wide…
Use when Codex is already in the finding-discovery phase of a security scan or the user explicitly asks to discover candidate security findings in a repository…
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch,…
Use when the user asks for a security review of a pull request, commit, branch diff, working-tree patch, or other Git-backed change set.
Use when the user asks for a repository-wide or scoped-path security scan.