Communitygithub.com

cdeust/zetetic-team-subagents

Cross-platform evidence synthesis for Codex, Gemini CLI, and Claude Code, plus a full Claude-native agent and gate distribution. 11 problem-shaped skills backed by 97 sourced reasoning patterns; commit-time checks block unsourced constants. I do not know is a supported outcome.

zetetic-team-subagents 是什么?

zetetic-team-subagents is a Claude Code agent skill that cross-platform evidence synthesis for Codex, Gemini CLI, and Claude Code, plus a full Claude-native agent and gate distribution. 11 problem-shaped skills backed by 97 sourced reasoning patterns; commit-time checks block unsourced constants. I do not know is a supported outcome.

兼容平台Claude CodeCodex CLI~CursorGemini CLI
npx skills add cdeust/zetetic-team-subagents

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Estimation

Problem shape: a quantity is needed for a decision, but there is no measurement — or there is a single number with false precision and no bracket. The move is order-of-magnitude decomposition, two-sided bounds, and limits derived before methods are chosen.

Relevant geniuses

AgentUse when
fermidecision blocked by missing data; single number with no bracket; feasibility check before committing resources; sanity-check a claimed figure
erlangcapacity planning, queue sizing, arrival-vs-service balance, latency exploding near saturation (Little's law audits)
thompson"will this design survive 10x scale?" — surface-to-volume and allometric scale-break analysis
laplacepriors need eliciting; estimates need updating as evidence arrives; forecaster calibration is unknown
carnotefficiency claims with no derived theoretical limit; "where is the irreversible loss?"
erdosexistence/threshold questions on large combinatorial spaces — probabilistic method instead of enumeration

Invocation

  1. Pick the best-fit agent above. If two or more fit, run tools/genius-invoker.sh route "<problem>" and take the top ranked match.
  2. Load it: tools/genius-invoker.sh invoke <agent> "<problem>", then read agents/genius/<agent>.md in full.
  3. Apply the agent's <workflow> step by step and answer in its <output-format>. Every estimate ships as a two-sided bracket with the dominant uncertainty named — never a bare point value.
  4. Cross-check: two independent decompositions must agree within ×10 before the estimate is used for a decision (fermi's sanity-check shape).
  5. If no shape above matches, use a standard team agent instead.

Refuse when

  • The requester wants a precise number a bracket cannot honestly provide — say what measurement would be needed instead.
  • The estimate would be quoted without its bounds.

相关技能