multi-agent-council
多 Agent 协作议会 - 主 agent 派遣多个 sub-agent 对同一问题独立给出完整答案，主 agent 担任裁判+合成器，输出对比分析后的最终答案。灵感来自 OpenRouter Fusion。适用于需要多视角、深度调研、避免单模型偏见的复杂问题。触发词：多模型协作、模型议会、多视角分析、llm…
Skill by ther7777
Chalk Labs
Need help deploying multi-agent-council?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ther7777-multi-agent-council
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/multi-agent-council
What's inside
- Skill name
multi-agent-council- Description
- 多 Agent 协作议会 - 主 agent 派遣多个 sub-agent 对同一问题独立给出完整答案，主 agent 担任裁判+合成器，输出对比分析后的最终答案。灵感来自 OpenRouter Fusion。适用于需要多视角、深度调研、避免单模型偏见的复杂问题。触发词：多模型协作、模型议会、多视角分析、llm council、fusion、议会讨论、几个 AI 一起讨论。
- License
- unknown
- Instructions
- 196 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ther7777/self-skills
- 0.504score
external-ai-brief
ther7777
生成一份自包含的决策上下文闭包，用于向不能访问本地文件的外部强 AI 求助。当用户觉得当前 agent 不够聪明、想找网页端 AI/外部专家求助、需要决策/认知交接而非代码交接、想要外援请求包/决策上下文包、或需要把项目上下文、历史认知修正、约束条件、基建条件、未解决问题整理成外部可消费格式时使用。
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
research-decision-gate
ther7777
Use before research or engineering-research decisions: deciding whether to continue a direction, run an experiment, change route, interpret results, write a…
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
gpu-static-analysis
ther7777
纯静态代码分析，无需 GPU/运行环境，扫描训练项目并输出优化建议报告
SkillCFreshness: C★ 2Claude Code +9 - 0.487score
gpu-training-optimizer
ther7777
端到端 GPU 训练智能调优 — 静态分析 → 硬件采集 → Profiling → 瓶颈诊断 → 代码优化 → 验证迭代
SkillCFreshness: C★ 2Claude Code +9 - 0.445score
web-access
一泽Eze
所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。 触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。
SkillDFreshness: D★ 2Claude Code +9 - 0.444score
pua
ther7777
Forces high-agency exhaustive problem-solving with corporate PUA pressure.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ssh-remote-access
ther7777
Prepare and verify SSH access to remote Linux servers before editing remote code or running experiments.
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
copilot-rule
ther7777
Governs Copilot Agent interaction continuity in all conversations.
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
resume-optimizer
ther7777
Business-oriented SOP for optimizing algorithm/AI engineering resumes targeting top-tier tech company campus recruiting or internship positions.
SkillDFreshness: D★ 2Claude Code +9 - 0.438score
tex-resume-validator
ther7777
Specialized skill for compiling, validating, and iteratively refining LaTeX resumes.
SkillDFreshness: D★ 2Claude Code +9 - 0.435score
ai-research-advisor
ther7777
AI 研究顾问：自动判断用户问题是「方向选择」还是「实验设计」，然后动态调度多个子 agent 并行分析，最后整合输出。 当用户提到「纠结方向」「值不值得做」「选哪个」「实验怎么设计」「怎么验证」「baseline 怎么设」「帮我看看这个研究方向」「AI 顾问」时触发。…
SkillDFreshness: D★ 2Claude Code +9 - 0.433score
conf-papers
ther7777
顶级会议论文搜索推荐 - 搜索 CVPR/ICCV/ECCV/ICLR/AAAI/NeurIPS/ICML 等顶会论文
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 17, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ther7777/self-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ther7777
- 0.504score
external-ai-brief
ther7777
生成一份自包含的决策上下文闭包，用于向不能访问本地文件的外部强 AI 求助。当用户觉得当前 agent 不够聪明、想找网页端 AI/外部专家求助、需要决策/认知交接而非代码交接、想要外援请求包/决策上下文包、或需要把项目上下文、历史认知修正、约束条件、基建条件、未解决问题整理成外部可消费格式时使用。
SkillCFreshness: C★ 2Claude Code +9 - 0.502score
research-decision-gate
ther7777
Use before research or engineering-research decisions: deciding whether to continue a direction, run an experiment, change route, interpret results, write a…
SkillCFreshness: C★ 2Claude Code +9 - 0.493score
gpu-static-analysis
ther7777
纯静态代码分析，无需 GPU/运行环境，扫描训练项目并输出优化建议报告
SkillCFreshness: C★ 2Claude Code +9 - 0.487score
gpu-training-optimizer
ther7777
端到端 GPU 训练智能调优 — 静态分析 → 硬件采集 → Profiling → 瓶颈诊断 → 代码优化 → 验证迭代
SkillCFreshness: C★ 2Claude Code +9 - 0.444score
pua
ther7777
Forces high-agency exhaustive problem-solving with corporate PUA pressure.
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ssh-remote-access
ther7777
Prepare and verify SSH access to remote Linux servers before editing remote code or running experiments.
SkillDFreshness: D★ 2Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get multi-agent-council running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
multi-agent-council skill. Agent Mart. https://agentmart.dev/skills/ther7777-multi-agent-council (last updated 2026-10-24)