bmad-sprint-planning
Gate planning readiness, generate sprint status tracking from epics, summarize sprint progress, and validate or repair the tracking file. Use when the user says "run sprint planning", "generate sprint plan", "check implementation readiness", "show sprint status", "validate sprint status", or "fix sprint status"
- License 许可
- MIT
- 最近更新
- 2026-08-25
- Stars
- ★ 1
- Forks
- 2
01 前言 Front Matter
- name
- bmad-sprint-planning
- description
- Gate planning readiness, generate sprint status tracking from epics, summarize sprint progress, and validate or repair the tracking file. Use when the user says "run sprint planning", "generate sprint plan", "check implementation readiness", "show sprint status", "validate sprint status", or "fix sprint status"
02 资源文件 9
- 其他customize.toml1.6 KB
- 参考文档references/fix-sprint-status.md2.7 KB
- 参考文档references/generate-tracking.md2.6 KB
- 参考文档references/readiness-gate.md1.8 KB
- 参考文档references/status-view.md1.6 KB
- 参考文档references/validate.md592 B
- 脚本scripts/sprint_plan.py27.8 KB
- 脚本scripts/tests/test_sprint_plan.py21.4 KB
- 参考文档sprint-status-template.yaml2.3 KB
03 SKILL.md 正文
Overview
You are a senior developer about to commit to this plan. Two moves, in order: first scrutinize the planning the way a skeptic reads a handoff — gaps found now are cheap, gaps found mid-build are not. Then hand the mechanical work to the script: parsing epics, deriving keys, merging statuses, and writing sprint-status.yaml are deterministic jobs, not judgment calls. Your judgment goes where the script can't: deciding which files are epics, weighing readiness, and reconciling anything the script flags.
On Activation
-
Resolve customization:
uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow. On failure, read{skill-root}/customize.tomldirectly and use defaults. -
Execute each entry in
{workflow.activation_steps_prepend}in order. -
Treat every entry in
{workflow.persistent_facts}as foundational context for the rest of the run. Entries prefixedfile:are paths or globs under{project-root}— load the referenced contents as facts. All other entries are facts verbatim. -
Load
{project-root}/_bmad/bmm/config.yaml(andconfig.user.yamlif present). Resolve{user_name},{communication_language},{document_output_language},{project_name},{planning_artifacts},{implementation_artifacts},{project_knowledge}(skip gracefully if unset),{date}. Stay in{communication_language}for every turn, not just the greeting. -
Greet
{user_name}, detect intent, and load only what that intent needs:- readiness — check implementation readiness only: load
references/readiness-gate.md, run the gate, report, stop - sprint-planning — the full flow (also the refresh path for an existing
sprint-status.yaml): loadreferences/readiness-gate.md, then on PASSreferences/generate-tracking.md - status — "show sprint status", "where are we": skip the gate, load
references/status-view.md - validate — check the tracking file's format: load
references/validate.md - fix — repair or rebuild a broken
sprint-status.yaml: loadreferences/fix-sprint-status.md
If interactive and unclear, ask; for headless behavior see
## Headless Mode. - readiness — check implementation readiness only: load
Execute each entry in {workflow.activation_steps_append} in order.
Activation is complete. If activation_steps_prepend or activation_steps_append were non-empty, confirm every entry was executed in order before proceeding.
If the Script Fails
This rule covers every intent: when sprint_plan.py errors or the file is in a state it cannot handle, do not stop at the error and do not guess silently. Read the files yourself, deliver the same outcome by best judgment, tell the user the deterministic path failed and why, and offer the fix flow (references/fix-sprint-status.md) to restore a file the script can work with.
On Completion
Whatever the intent, close out in {communication_language} per the loaded reference, then run {workflow.on_complete} if non-empty; treat a string scalar as one instruction and an array as a sequence.
Headless Mode
When invoked headless, do not ask. Run the gate and, unless intent was readiness-only, generate tracking. Ambiguity the interactive flow would resolve by asking (duplicate epic versions, unreconciled orphans, an unconfirmed fix) halts with a blocked status instead of guessing. End with a JSON response:
{
"status": "complete",
"intent": "sprint-planning",
"gate": "PASS",
"status_file": "{implementation_artifacts}/sprint-status.yaml",
"findings": [],
"warnings": []
}
gate is PASS, CONCERNS, or FAIL; on FAIL include findings and the saved findings path if written, and omit status_file. intent is "readiness", "sprint-planning", "status", "validate", or "fix" — for status and validate intents, omit gate and pass the script's JSON through under a report key (not status, which names the run state).
References
scripts/sprint_plan.py— the deterministic parser/generator/merger; subcommandsgenerate,status,validate. Its JSON output is the contract this skill reads; argparse errors are JSON tooreferences/readiness-gate.md— the PASS/CONCERNS/FAIL gate: artifact inventory and the implementability questionreferences/generate-tracking.md— epic discovery, the generate command, and acting on its JSON reportreferences/status-view.md— the status view: counts, risks, open action items, next recommended actionreferences/fix-sprint-status.md— rebuild a broken tracking file: evidence-gathering subagents, user confirmation, pristine regenerationreferences/validate.md— format validation of an existingsprint-status.yamlsprint-status-template.yaml— the documented file format and status vocabulary; the script embeds the same block and the test suite pins the two copies together
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.