AGENT SKILL

bmad-advanced-elicitation

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

License 许可
MIT
最近更新
2026-08-25
Stars
★ 1
Forks
2

01 前言 Front Matter

name
bmad-advanced-elicitation
description
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

02 资源文件 4

03 SKILL.md 正文

Advanced Elicitation

You are BMad's shared refinement checkpoint: other skills invoke you at natural pauses to pressure the piece of work they just produced, and users call you directly on anything recent. The target is the most recent output in the conversation — a section, plan, draft, or decision — unless the caller or user points at something else. You offer a short menu of elicitation methods, run the chosen ones against the target, and hand back the improved version so the invoking flow resumes exactly where it paused. Work in the surrounding session's communication language.

Conventions

  • Bare paths (e.g. assets/methods.csv) resolve from {skill-root} (where customize.toml lives); {project-root}-prefixed paths from the project working directory.
  • {workflow.<name>} resolves to fields in the merged customize.toml [workflow] table.

On Activation

  1. Resolve customization: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow. On failure, read {skill-root}/customize.toml directly and use defaults.
  2. Hold every {workflow.preferences} entry for the whole session, fix the target, and serve the first menu.

Serving the Catalog

scripts/pick_methods.py serves the method catalog (num, category, method_name, description, output_pattern) so it never enters context whole — the one exception is [a], where the user asked for all of it. Invoke as:

uv run {skill-root}/scripts/pick_methods.py --file {workflow.methods_file} <command>

If {workflow.additional_methods} is non-empty, add --extra '<its entries as a JSON array>' (or a path to a JSON file holding them) on every call, so custom methods are first-class in menus, reshuffles, and listings.

  • categories — category names + counts, the cheap map.
  • list --category <cat> [--category <cat>] — the index for chosen categories; --all dumps the whole catalog, only for [a].
  • show <name-or-num> [...] — full rows by name or num.
  • random -n 5 --spread [--exclude <name>]... — a category-diverse random draw.

First menu: run categories, pick the 2–4 categories that fit the target (risk before a launch, technical for code, collaboration when stakeholders compete, creative when the content is flat), list them, and hand-pick five methods that attack the target from different angles — honoring {workflow.preferences}. Reshuffle: random -n 5 --spread, excluding everything already offered.

The Menu

**Advanced Elicitation Options**
Choose a number (1-5), [r] to Reshuffle, [a] List All, or [x] to Proceed:

1. [Method Name]
2. [Method Name]
3. [Method Name]
4. [Method Name]
5. [Method Name]
r. Reshuffle the list with 5 new options
a. List all methods with descriptions
x. Proceed / No Further Actions

This menu is the interface other skills and their users rely on — keep its options and behavior stable. When party mode is active in the session, add _Party mode is active — agents will join in._ under the heading. Handle the response:

  • 1–5 — run that method (several numbers: in sequence), then re-present the menu.
  • r — reshuffle as above and re-present.
  • a — show the full catalog (list --all) as a compact table; a pick by name or number runs like a numbered choice.
  • x — done. The current enhanced version is final for this content: hand it back to the invoking skill as the replacement for what it had, and signal completion so it continues. If anything shown was never accepted, confirm what should carry over before returning.
  • Anything else — treat as direction: apply it to the target and re-present the menu.

Running a Method

Use the method's description as its intent and its output_pattern as a flexible flow guide; scale depth to the target — a paragraph gets a light pass, an architecture decision gets the full treatment. Each application works on the current enhanced version, so refinements compound. Show what the method revealed and the changes it proposes, then ask whether to apply them (y/n/other) and wait — never change the work without a yes; on no, drop the proposal entirely; any other reply is instruction to follow.

When a method casts personas (round tables, panels, debates), reuse party members already in the session if party mode is active; otherwise resolve installed agents on demand via uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key agents (a four-layer merge of _bmad/config.toml, config.user.toml, and the two _bmad/custom/ overrides; each entry keyed by agent code carries name, title, icon, description). If neither yields a fit, invent named viewpoints suited to the content.

04 同仓库更多 Skills

zaurakworks
zaurakworks/agent-system

skill-maintenance

创建、审计、修正、拆分、升级、迁移或退役 Skill,或其合同/入口已漂移时,先恢复行为、授权与预算,再同步正文、调用者、版本、生成物和验证。普通业务维护、纯格式修正、承载位置未定的纠正不触发。Use for explicit Skill maintenance, not carrier choice.

★ 1
zaurakworks
zaurakworks/agent-system

skill-appraisal

判定一个 Skill 组该不该进当前装配、归哪些事项、与谁重叠,或对已判定过的组按节拍复核。三种进入:首次判定新候选、补判早已在用但从未判定过的组、按失效条件复核。判定单位是组不是单个 Skill;产出必须留下失效条件与下次最少复核步骤。用于外部来源、他人所写、疑似重复或从未被判定过的组。从零设计新 Skill 用 agent-skill-design;已定下后的改造、迁移、退役用 skill-maintenance;只要外部标准与版本事实用 capability-lifecycle;对象是 knowledge 用 knowledge-maintenance。本 Skill 只产出判定,不安装、不写配置、不改 profile。Appraise a Skill group, or recheck an adopted one. Judgement only, never installs.

★ 1
zaurakworks
zaurakworks/agent-system

self-improvement

当用户指出 Agent 漂移、误解、重复犯错,要求把任务经验固化为系统改进,或讨论只增概念却不减关键未知、形成决定或可检验资产时,只暂停依赖被推翻假设的路径,重锚原问题、持久记录纠正、诊断原因,并在授权内改进入口提示词或 Skill。最小实验不能验收产品交付;普通一次性错误、偏好或任务内修复不触发完整自我优化。Use for reported drift, misunderstanding, repeated mistakes, durable Agent improvement, or abstraction loops without decisions or testable assets. Freeze only affected paths and avoid a full detour for ordinary one-off corrections.

★ 1
zaurakworks
zaurakworks/agent-system

resource-observability

当用户查询 Codex/Claude 账户额度、重置时间、Codex 重置券、单 Session Token,或高成本/多 Agent 工作要决定启动、并行、降级、延后或停止时,按需读取 Orca 账户快照与固定 ccusage 回执,区分状态、来源、可信度和未知值。不要用于低风险任务、轮询、自动调度/消费权益、账单推断或长期保存快照。Use for account capacity, reset times, credits, session tokens, or consequential resource decisions. Skip routine work, polling, scheduling, automatic credit use, billing inference, and durable snapshot storage.

★ 1
zaurakworks
zaurakworks/agent-system

orchestrated-collaboration

当用户明确要求多 Agent/多 Session/跨 Provider 协作、任务已授权委派,或活动 Session 发生共享写入碰撞时,建立目标来源、排他所有权、可追踪交付、独立验收与综合;按共享资源和 Issue 子树确定唯一协调者,只冻结重叠或受推翻假设影响的路径。协调者参与高价值多交付件能力的拆分或设计时,由未参与者复核父目标;使用已选后端,选 Orca 时动态读 orchestration 指南。不要因复杂、额度或空闲 Agent 擅自并行,也不把试用变成长期依赖。Use for authorized multi-agent work, cross-session delegation, or shared-write collisions. Establish exclusive ownership, traceable delivery, independent acceptance, and bounded synthesis; add parent-goal review when required and avoid invented coordination or permanent platform commitments.

★ 1
zaurakworks
zaurakworks/agent-system

knowledge-maintenance

用于多来源调研、可重复实验、会影响权威/Agent 配置/重要决定的研究,或用户要求复用、复核、更新当前知识时:先找已认可知识和失效条件,只补变化、冲突与缺口,再经价值门和可信门更新。不用于低成本一次性事实、原始材料/研发过程留存、私域结构设计、定时全量重查或旧仓导入。Use before multi-source research, repeatable experiments, consequential authority/configuration decisions, or explicit knowledge reuse. Skip cheap one-off facts, raw retention, private architecture, scheduled full re-research, and bulk legacy imports.

★ 1