将PRD意图与产品讨论转成可实施的能力方案,提前暴露约束与待决策项
复制安装指令,让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "product-capability" 技能: 1. 下载 https://raw.githubusercontent.com/affaan-m/ECC/main/skills/product-capability/SKILL.md 2. 保存为 ~/.claude/skills/product-capability/SKILL.md 3. 装好后重载技能,告诉我可以用了
请根据以下PRD草稿,输出一份 implementation-ready capability plan:拆解目标能力、关键约束、不变量、跨服务接口、依赖关系、风险点,以及仍需产品或技术负责人拍板的未决策项。请用结构化标题输出。PRD内容:……
一份结构化能力方案,明确能力边界、接口约束、依赖与待决策清单
我们下季度路线图包含这几个需求:A、B、C。请不要写泛泛计划,而是输出能力视角的实施框架:每项需求对应的能力模块、共享基础能力、技术与业务约束、服务间接口、验收前提,以及需要先澄清的问题。
按能力模块组织的实施框架,帮助团队识别共性能力与前置澄清项
下面是一段产品、设计和工程的会议记录。请提炼成可进入多服务实施前的 capability plan,重点标出:已达成共识的能力、不变量、边界条件、外部接口假设、潜在冲突,以及缺失但必须补齐的信息。会议记录:……
将讨论内容收敛为工程可执行的能力计划,并列出关键缺口与冲突
This skill turns product intent into explicit engineering constraints.
Use it when the gap is not "what should we build?" but "what exactly must be true before implementation starts?"
If the repo has a durable product-context file such as PRODUCT.md, docs/product/, or a program-spec directory, update it there.
If no capability manifest exists yet, create one using the template at:
docs/examples/product-capability-template.mdThe goal is not to create another planning stack. The goal is to make hidden capability constraints durable and reusable.
Read only what is needed:
PRODUCT.md, design docs, RFCs, migration notes, operating-model docsCompress the ask into one precise statement:
If this statement is weak, the implementation will drift.
Extract the constraints that must hold before implementation:
These are the things that often live only in senior-engineer memory.
Produce an SRS-style capability plan with:
End with the exact handoff:
If useful, point to the next ECC-native lane:
project-flow-opsworkspace-surface-auditapi-connector-builderdashboard-buildertdd-workflowverification-loopReturn the result in this order:
CAPABILITY
- one-paragraph restatement
CONSTRAINTS
- fixed rules, invariants, and boundaries
IMPLEMENTATION CONTRACT
- actors
- surfaces
- states and transitions
- interface/data implications
NON-GOALS
- what this lane explicitly does not own
OPEN QUESTIONS
- blockers or product decisions still required
HANDOFF
- what should happen next and which ECC lane should take it
…
通过双评审智能体对结果进行对抗式校验,提升输出发布前的可靠性
帮助团队进行产能规划、工作负载分析与资源利用预测,支持排期和招聘决策。