Capture
SkillMediaRecord already-confirmed multi-context designs into a handoff-ready, controllably revisable SPEC. Use when work needs to span sessions or agents, or when design decisions must be preserved; do not use it to redo decisions on the user's behalf.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Capture skill
What this skill tells your AI
The instructions your AI receives, as published by yibie/supertag in skills/capture/SKILL.md and read by ahel’s review.
把已确认的共识写成一个活的设计契约。
前置条件
plan已结束并得到approve、compatible revise、breaking,或明确的plan-only执行授权。breaking时,SPEC 必须包含迁移方案;ADR 不在这里写, 由learn收尾时写。- 设计需要跨多个上下文,或必须交给之后的 agent 继续。
docs/spec-agents/WORKFLOW.md、CONTEXT.md、项目KERNEL.md(若存在)、 相关 ADR、Protocol、Runbook 和 Lesson 已被读取;冲突回到plan。
写入位置
创建或更新:
.specs/<feature>/SPEC.md
不要在根目录再创建第二份 SPEC。目录不存在时按需创建;不要预建未来 feature 的文件。
SPEC 最小结构
# <feature>
status: draft | confirmed | in-progress | revised | superseded
revision: <number>
context_refs:
## Problem and goal
## Unchanged contracts
## Decision and boundaries
## Model delta
## Action Contracts
## Seams and verification
## Compatibility and migration
## Out of scope
## Issue map
## Revision notes
记录“已经决定的 what/why/where”,不要把新的取舍藏进 SPEC。实现细节只写到能让后续切片保持一致的程度。
当 SPEC 是 Kernel Bootstrap 时,记录 K1 已确认的概念、关系、动作契约和
不变量,以及待确认的扩展;不要把 K1 复制成第二份长期真相。验证通过后由
learn 更新项目 KERNEL.md。
修订
- 文字澄清、链接和验证补充可以直接修订。
- 改变目标、边界、身份、关系、不变量、接口或验收标准,必须重新经过
plan。 - 修订时保留 revision、原因、受影响的 CONTEXT/Protocol、兼容性、迁移和验证。
- 受影响的 Slice 标为
stale;不要让旧 Slice 继续执行。
完成条件
SPEC 状态、未改变的契约、边界、Action Contracts、验证入口和 out-of-scope 齐全,并能让一个新上下文不依赖本次对话继续工作。
Signals
- GitHub stars
- 358
- Forks
- 15
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
capture-yibie- Source
- github.com/yibie/supertag