Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ChrisLamDev/hermes-core-skills --skill multi-role-synthesis-frameworkgit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chrislamdev/hermes-core-skills/multi-role-synthesis-framework)<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/multi-role-synthesis-framework"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/multi-role-synthesis-framework.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.02568 |
| Opus 5 | $0.00028 | $0.01284 |
| Sonnet 5 | $0.00011 | $0.00514 |
| Haiku 4.5 | $0.00006 | $0.00257 |
Grade A, and why
multi-role-synthesis-framework scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🎭 多角色合成篩選框架
兩種模式
呢個 framework 支援兩種使用模式：
模式一：平行建議 + 終極篩選（預設）
多角色各自俾建議 → 終極角色做篩選整合。適合設計決策場景。
模式二：順序 Pipeline（今次新增）
角色順序執行，一個做完交俾下一個。適合反饋修復場景。 UX分析師 → 產品設計師 → 前端工程師
揀模式嘅原則：
- 想俾 Chris 多個選擇去揀 → 用模式一
- Chris 已經講咗要改咩，只想執行好 → 用模式二
兩種任務類型（核心區分）
呢個框架有兩個完全唔同嘅用法，揀錯角色組合會搞到成件事歪晒：
類型 A：內部決策審視（預設用法）
審視我哋自己項目嘅功能/設計/技術決策。角色組合係「內部專家」。
- 例子：設計學佛問答 feedback 機制、決定 UX 流程、cut 功能
類型 B：外部項目學習（今次新增）
分析外部開源項目/技術/pattern，將好嘢吸收轉化為我哋嘅能力。角色組合係「外部專家 → 翻譯官 → 內部落地」。
- 例子：學習 Godogen 嘅 AI 開發模式、研究某個 framework 嘅架構
關鍵區分：
- 類型 A 嘅角色係「審視角度」（UX設計師、法師顧問、遊戲化設計師）
- 類型 B 嘅角色係「轉化鏈條」（外部專家→翻譯官→架構師→工程師）
- 類型 B 唔可以就咁用類型 A 嘅角色組合，否則會出現「用內部審視角度去分析外部項目」嘅錯配
何時使用
- Chris 話「用幾個角色去睇一睇呢個設計」
- Chris 話「搵一個角色去總結晒所有角色嘅意見」
- 需要多角度審視一個 feature、設計決策、或者外部項目，然後做終極篩選
- 決策涉及 UX、遊戲化、內容、技術、商業等多個維度
流程
Step 1：先確定任務類型
係「內部決策審視」（類型 A）定係「外部項目學習」（類型 B）？
Step 2：揀角色
根據任務類型揀 3-5 個相關角色。
類型 A：內部決策審視 — 常用角色組合
| 場景 | 建議角色組合 |
|---|---|
| 用戶功能設計 | UX 設計師、遊戲化設計師、內容設計師、產品策略師 |
| 技術決策 | 軟體架構師、微信開發者、安全工程師、性能工程師 |
| 內容創作 | 法師顧問、內容設計師、故事寫手、產品策略師 |
| 商業策略 | 產品策略師、市場營銷、用戶增長、法師顧問 |
| 綜合（常用組合） | UX 設計師 + 遊戲化設計師 + 內容設計師 + 產品策略師 + 法師顧問 |
類型 B：外部項目學習 — 推薦角色組合
角色應該形成「外部 → 內部」嘅轉化鏈：
| 角色 | 職責 | 場景例子 |
|---|---|---|
| 📖 原項目專家 | 最了解外部項目嘅設計哲學、pattern 背後嘅「點解」 | Godogen 原作者視角 |
| 🌉 技術翻譯官 | 將外部項目嘅技術 pattern 翻譯成我哋平台嘅語言 | Godot → Cocos/WeChat |
| 🏗️ 架構設計師 | 將翻譯完嘅 pattern 設計成具體架構方案 | 點樣融入現有系統 |
| 👨💻 實戰工程師 | 最後落地可行性判斷 | 每日寫 code 嘅角度 |
| 🛡️ 安全檢測員 | 審計漏洞、系統衝突、負面影響；開工後實際檢測每個改動 | 任何改動執行前Review |
終極角色建議用 🧭 Product Manager 或者 🧠 Strategist，因為需要判斷「邊啲 pattern 值得學、邊啲唔值得」。
重要：唔好將類型 A 嘅角色（UX設計師、法師顧問）直接用喺類型 B。法師顧問係審視內部項目功能決策用，唔係分析外部技術 pattern。
Step 2：收集每角色建議
每個角色從自身角度俾意見，格式：
### 👤 角色：[角色名]
**對 [決策項目] 嘅意見：**
- [建議 1 + 理由]
- [建議 2 + 理由]
- [建議 3 + 理由]
每個建議要有：
- 具體建議（做啲咩）
- 背後理由（點解咁做）
- 無需太詳細，一句到肉就得
類型 B 特別指引：收集嘅唔係「審視意見」，而係「翻譯轉化建議」。
- 📖 原項目專家：呢個 pattern 嘅本質係咩？Godogen 點解要用呢個方法？
- 🌉 技術翻譯官：呢個 pattern 喺我哋平台應該點樣實現？
- 🏗️ 架構設計師：翻譯完之後嘅架構方案係點？
- 👨💻 實戰工程師：呢個方案每日用起嚟順唔順？有冇阻滯？
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 169 lines · 55 tokens per session scan A 73ebd860694d
multi-role-synthesis-framework is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 2,568 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ralphex-adopt
Convert plans from various source formats (OpenSpec, spec-kit, GitHub/GitLab issues with checklists, generic task-lists, free-form markdown) into ralphex-format plans in docs/plans/. Triggers on "ralphex-adopt", "adopt plan", "convert plan to ralphex", "import plan as ralphex".
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
thinking-lindy-effect
Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
autonomous-run
Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.
authentication-patterns
OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.