bmad-help
Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.
- License 许可
- MIT
- 最近更新
- 2026-08-25
- Stars
- ★ 1
- Forks
- 2
01 前言 Front Matter
- name
- bmad-help
- description
- Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.
03 SKILL.md 正文
BMad Help
Purpose
Help the user understand where they are in their BMad workflow and what to do next, and also answer broader questions when asked that could be augmented with remote sources such as module documentation sources.
Desired Outcomes
When this skill completes, the user should:
- Know where they are — which module and phase they're in, what's already been completed
- Know what to do next — the next recommended and/or required step, with clear reasoning
- Know how to invoke it — skill name, menu code, action context, and any args that shortcut the conversation
- Get offered a quick start — when a single skill is the clear next step, offer to run it for the user right now rather than just listing it
- Feel oriented, not overwhelmed — surface only what's relevant to their current position; don't dump the entire catalog
- Get answers to general questions — when the question doesn't map to a specific skill, use the module's registered documentation to give a grounded answer
Data Sources
- Catalog:
{project-root}/_bmad/_config/bmad-help.csv— assembled manifest of all installed module skills - Config: Run
uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root}and use the merged JSON to resolveoutput-locationvariables and readcore.communication_languageandmodules.bmm.project_knowledge. The resolver merges_bmad/config.toml,_bmad/config.user.toml,_bmad/custom/config.toml, and_bmad/custom/config.user.tomlin that order. - Artifacts: Files matching
outputspatterns at resolvedoutput-locationpaths reveal which steps are possibly completed; their content may also provide grounding context for recommendations - Project knowledge: If
project_knowledgeresolves to an existing path, read it for grounding context. Never fabricate project-specific details. - Module docs: Rows with
_metain theskillcolumn carry a URL or path inoutput-locationpointing to the module's documentation (e.g., llms.txt). Fetch and use these to answer general questions about that module.
CSV Interpretation
The catalog uses this format:
module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
Phases determine the high-level flow:
anytime— available regardless of workflow state- Skills group into folders (
plan,ship; some modules use numbered phases) and flow in order; naming varies by module
Sequencing determines recommended ordering within and across phases (these are soft suggestions, not hard gates — see required for gating):
preceded-by— skills that should ideally complete before this onefollowed-by— skills that should ideally run after this one- Format:
skill-namefor single-action skills,skill-name:actionfor multi-action skills
Required gates:
required=trueitems must complete before the user can meaningfully proceed to later phases- A phase with no required items is entirely optional — recommend it but be clear about what's actually required next
Completion detection:
- Search resolved output paths for
outputspatterns - Fuzzy-match found files to catalog rows
- User may also state completion explicitly, or it may be evident from the current conversation
Descriptions carry routing context — some contain cycle info and alternate paths (e.g., "back to DS if fixes needed"). Read them as navigation hints, not just display text.
Response Format
For each recommended item, present:
[menu-code]Display name — e.g., "[PR] PRD"- Skill name in backticks — e.g.,
bmad-prd - For multi-action skills: action invocation context — e.g., "dev lets run a code review!"
- Description if present in CSV; otherwise your existing knowledge of the skill suffices
- Args if available
Ordering: Show optional items first, then the next required item. Make it clear which is which.
Constraints
- Present all output in
{communication_language} - Recommend running each skill in a fresh context window
- Match the user's tone — conversational when they're casual, structured when they want specifics
- If the active module is ambiguous, retrieve all meta rows remote sources to find relevant info also to help answer their question
04 同仓库更多 Skills
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.
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.
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.
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.
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.
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.