Install
$ agentstack add skill-xinyiai0724-tools-feedback-writeback ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill: feedback-writeback
类型: 原子 Skill 触发时机: feature-writeback pipeline 归档后,或 rejected/withdrawn 结论需要补充经验记录时由人工触发
用途
将 CR 实施结论(验收结果、偏差记录、经验教训)写回到关联的 spec traceability.yml 和 docs/ 知识库,形成闭环可追溯记录。避免变更知识孤岛——确保 CR 的决策依据和实施偏差能被后续开发者查阅。
前置条件
| 条件 | 说明 | |------|------| | CR 状态 | archived、rejected 或 withdrawn(已有结论) | | target-kind | 当前仅支持 spec(target.refs 中 spec 类型) |
参数
| 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | cr-id | string | ✅ | CR 标识符(如 CR-2026-001) | | outcome | enum | ✅ | accepted(已完成回写)/ rejected / withdrawn | | deviation | string | ❌ | 实施偏差说明(实际实施与 PRD/SDD/TASK 不一致之处) | | lessons | string | ❌ | 经验教训(供后续 CR 参考) | | write-tech-note | bool | ❌ | 是否将 lessons 追加到 docs/tech-notes/,默认 false |
操作步骤
Step 1 — 读取 CR 上下文
- 读取
change-requests/{cr-id}/cr.mdfrontmatter,获取:
target.refs(关联 spec 列表)type(变更类型)title
- 读取
change-requests/{cr-id}/prd.md、sdd.md、tasks/与 review-annotations;若存在历史补丁式delta-spec.md,仅作为兼容输入只读展示,不能作为主流程状态依据
Step 2 — 写回 traceability.yml
对 target.refs 中每个 spec(target.kind=spec 的条目):
- 定位
specs/{spec-id}/traceability.yml - 在
change-requests段(若无则新建该段)追加一条记录:
```yaml change-requests:
- cr-id: {cr-id}
title: {cr.md frontmatter.title} type: {cr.md frontmatter.type} outcome: {outcome} # accepted | rejected | withdrawn deviation: "{deviation 或 none}" recorded-at: "YYYY-MM-DDTHH:mm:ss+HH:mm" ```
- 若
outcome=accepted:在 traceability.yml 的deltas段补充:
```yaml deltas:
- cr-id: {cr-id}
applied-at: "YYYY-MM-DDTHH:mm:ss+HH:mm" sections-modified: [从 prd.md / sdd.md / tasks/ 解析的 section-id 列表] ```
Step 3 — 写回 docs/tech-notes/(可选)
若 write-tech-note=true 且 lessons 非空:
- 创建或追加文件
docs/tech-notes/cr-lessons-learned.md - 追加格式:
```markdown ## {cr-id} — {cr.md.title}
日期: YYYY-MM-DDTHH:mm:ss+HH:mm 变更类型: {type} outcome: {outcome}
### 经验教训
{lessons}
--- ```
Step 4 — emit 写回事件
调用 inbox-emit:
target: change-requests/_backlog.yml
event: feedback-writeback-done
cr-id: {cr-id}
outcome: {outcome}
specs-updated: [target.refs 中的 spec-id 列表]
timestamp: "YYYY-MM-DDTHH:mm:ss+HH:mm"
输出
✅ feedback-writeback 完成
cr-id : {cr-id}
outcome : {outcome}
specs 回写 : {N} 个 traceability.yml 已更新
tech-note : {已追加 | 跳过}
错误码
| 错误码 | 含义 | 处理方式 | |--------|------|----------| | FWB_CR_NOT_FOUND | 找不到 change-requests/{cr-id}/cr.md | 检查 cr-id 是否正确 | | FWB_OUTCOME_REQUIRED | outcome 参数缺失 | 必须明确传入 accepted 或 rejected | | FWB_TARGET_NOT_SPEC | target.refs 中存在非 spec 类型 | 当前版本仅支持 spec;其他类型跳过并提示 | | FWB_TRACEABILITY_NOT_FOUND | specs/{spec-id}/traceability.yml 不存在 | 手动创建空 traceability.yml 后重试 |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: xinyiai0724
- Source: xinyiai0724/tools
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.