Community生產力與協作github.com

tderoussel/decision-council

執行結構化的多視角決策審查,而非獲得單一同意答案。當使用者說「召開會議」、「給我對此的觀點」、「我應該做X嗎?」、「壓力測試此決策」或「這是好主意嗎?」時使用。

decision-council 是什麼?

此技能旨在解決單一AI代理因追求連貫而非正確答案而成為糟糕顧問的問題。它透過平行生成多個獨立視角、匿名化後由不知道作者的新審查員進行同行評審,最終由一位主席代理根據這些觀點和評論產出最終裁決。支援平台包括任何能執行指令的AI代理環境(例如Claude Code、Cursor等)。工作流程包含五個步驟:精確陳述決策、平行生成五個不同角色(反對者、樂觀者、執行者、客戶、會計)的觀點、匿名同行評審、主席綜合產出結果,以及誠實報告分歧。此模式適用於真正有成本權衡的決策(如自建與購買、發佈與暫緩),不適用於已知答案的問題。擴充性上,預設五個角色,依決策重要性可調整為三或七個,關鍵在於角色的角度必須真正不同。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/tderoussel/agent-skills/tree/main/skills/decision-council

Installed? Explore more 生產力與協作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

決策會議

此技能解決的問題

問一位代理「為什麼這是個好主意?」你會得到一個論證充分的贊成案例。問「為什麼這是個壞主意?」又會得到一個同樣論證充分的反對案例。兩者都很流暢,但都不是判斷。單一代理是一個糟糕的顧問,因為它追求連貫而非正確的答案。

此技能執行多個獨立視角,讓不知道作者身份的代理進行審查,並產出一個最終裁決。

何時執行

真正有成本權衡的分歧點:自建 vs. 購買、發佈 vs. 持有、定價變更、某功能是否過早實現、下一步該做什麼。不適用於已知答案的問題。

步驟

1. 精確陳述決策

用一句話寫出,其中包含真正的分歧點。如果無法這樣陳述,表示決策還不夠清晰以至於需要審查——先解決這個問題。

收集實際已知的資訊:限制條件、已經嘗試過的方法、哪些是可逆的、哪些是不可逆的。

2. 召開會議——平行、獨立

五位代理,各自擁有真正不同的視角。他們不得看到彼此的答案。

角色任務
反對者假設這個方案失敗了。是什麼導致了失敗?
樂觀者假設它成功了。它開啟了哪些被低估的價值?
執行者誰來做工作、哪些環節會出錯、對使用者時間的真正成本是什麼?
客戶付費的人真的在乎嗎?他們會注意到嗎?
會計這要花多少錢、回報是什麼、機會成本是什麼?

每位回傳:一個建議、理由,以及一個改變其想法的事實。

當決策需要時可替換角色——法規分歧用監管視角,架構分歧用安全視角。保持視角真正不同。

3. 同行審查,盲審

移除署名並隨機打亂。將匿名化後的結果交給新的審查員。請他們回答:哪個論點最強、哪個最弱,以及所有論點都忽略了什麼?

盲審很重要——它能防止審查因看起來最有權威的角色而產生偏倚。

4. 主席

一位最終代理閱讀所有觀點和評論,並回傳:

## 裁決:<問題>

**判決:** <一句話總結>

**信心度:** <高 | 中 | 低> — <理由>

**勝出的理由:** <2-3句話>

**最強的反對論點:** <公平陳述——不要設立稻草人>

**會改變這一點的因素:** <能翻轉答案的具體事實或事件>

**如果我們繼續:** <第一步具體行動>

5. 誠實報告

如果會議出現分歧,就說它分歧了。 強迫達成共識比真實的分歧更糟——大多數人寧願看到真正的緊張關係,然後自行做出決定。

切勿為了顯得果斷而製造虛假的同意。

擴展

五個角色是預設值。對於較小型的決策用三個,對於昂貴或難以逆轉的決策用七個。更多角色只有在視角真正不同時才有幫助——五個不同的角度勝過九個重疊的角度。

致謝

多重角色加盲審加主席的模式來自 Ollie Leman,經由 Remy Gaskell 的 Open Residency 關於代理作業系統的集數。

Individual skills in this repo

This repo contains 8 individual skills — each has its own dedicated page.

tderoussel/codebase-audit

Runs a ranked, evidence-backed audit of a product, codebase, or subsystem, ending in a verify list that separates proven findings from inferred ones. Use when the user asks for an audit, a gap analysis, a deep read, a bug hunt, a readiness check, a re-audit, a state reconciliation, or asks what they are not seeing. Trigger phrases include "audit", "gap analysis", "what am I missing", "deep audit", "readiness", "bug hunt", "review the whole thing". Produces findings and a verify list; does not fix.

tderoussel/competitive-teardown

Researches a competing product against your own and produces a ranked build-or-ignore verdict, plus optional comparison-page copy. Use when the user names a competitor or asks how their product stacks up against one. Trigger phrases include "vs us", "competitor", "what does X have", "should we copy", "competitive gap", "teardown", "are we behind". Produces a ranked verdict with effort estimates and an explicit not-worth-copying list.

tderoussel/fleet-brief

Authors a workstream brief for dispatching multiple parallel build agents across one codebase, with per-lane file ownership, shared-ground warnings, and a derived DO-NOT list. Use whenever work is about to be split across concurrent agents, workers, lanes, or waves — even if the user does not say "write a brief". Trigger phrases include "fan out", "parallel agents", "orchestrate this", "split into lanes", "workstreams", "run these in parallel", "review-gated build". Produces the brief; does not dispatch.

tderoussel/inbox-triage

Triage an email inbox — sort what needs a reply, draft the replies, flag what needs a decision, and surface what can be ignored or unsubscribed. Use when the user says triage my inbox, do my email, what's in my inbox, or clean up my email.

tderoussel/overnight-build

Composes an autonomous unattended Claude Code build prompt that survives usage-limit resets via BUILD_LOG.md checkpointing, plus the launcher that restarts it. Use when the user asks for an overnight build, an autonomous build, a build to run while they sleep, an unattended or unsupervised session, or any long build they will not be monitoring. Trigger phrases include "overnight build", "run overnight", "build while I sleep", "autonomous build", "let it run", "unattended". Produces a single copyable prompt; does not run the build.

tderoussel/session-log

Write a durable record of a work session — what was built, root-caused, or shipped — into the project's notes. Use when the user says log this session, write a session log, record this, or when a substantial piece of work has just finished and needs to be handed off to a future session.

tderoussel/ship-gate

Verification gate for a Next.js-on-Vercel + Supabase + GitHub Actions stack, to run before claiming anything is shipped, deployed, live, merged, passing, or done. Use before saying a change is in production, before merging a PR, before reporting CI green, and before writing any status into a document — even if the user does not ask for verification. Trigger phrases include "is it live", "did it deploy", "ship it", "merge it", "is CI green", "confirm prod", "did that work". Encodes traps where the obvious check returns a false pass.

tderoussel/vault-doctor

Audits and repairs an Obsidian vault's structural health — broken [[wikilinks]], ambiguous duplicate filenames, missing or malformed frontmatter, stale status markers, and hub notes whose state sections have gone cold. Use when the user asks about vault health, broken links, vault cleanup, dead links, orphan notes, tag consistency, or says the vault feels messy or out of date. Trigger phrases include "vault health", "broken links", "clean up the vault", "audit the vault", "is the vault current". Read-only by default; every repair is proposed before it is made.

相關技能