archive-change
Skill1 starsChanged 3 months agoMITView on GitHub
Archive completed changes and maintain project history. Use when a feature, fix, or change is complete and needs to be documented and archived.
In this repository30 other files it gives its agents.
- api-syncSkill
- auto-flowSkill
- build-reportSkill
- change-impact-reviewSkill
- code-review-auditSkill
- code-reviewSkill
- coverage-reportSkill
- data-logic-validationSkill
- data-risk-auditSkill
- data-validationSkill
- dingtalk-notifySkill
- git-reviewSkill
- knowledge-opsSkill
- learning-engineSkill
- learning-feedbackSkill
- log-auditSkill
- offline-design-analysisSkill
- project-reviewSkill
- release-inspectionSkill
- report-insightsSkill
- requirement-analystSkill
- resource-bindSkill
- service-governance-auditSkill
- service-governance-changeSkill
- service-governance-diagnosisSkill
- service-management-log-analysisSkill
- sls-log-auditSkill
- test-reportSkill
- yapi-sync-interfaceSkill
- yuque-sync-designSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
Create knowledge base entries
- Very specific: line 198
Before archiving, FlowMind checks:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Archive Change Skill
Archive completed changes and maintain project history.
Features
📦 Change Archiving
- Move completed changes to archive
- Generate completion reports
- Update project history
- Clean up working directories
📝 Documentation
- Auto-generate change summary
- Link related artifacts
- Update changelog
- Create knowledge base entries
🔗 Cross-Reference
- Link to related issues
- Reference PRs and commits
- Connect to requirements
- Trace to deployments
Trigger Patterns
"归档", "archive", "完成"
"变更完成", "change complete"
"结束变更", "finish change"
"交付", "deliver"Output Format
┌─────────────────────────────────────────────────────┐
│ Change Archived │
├─────────────────────────────────────────────────────┤
│ Change: {change_name} │
│ Status: ✓ Completed │
│ Duration: {days} days │
├─────────────────────────────────────────────────────┤
│ Artifacts: │
│ • Proposal: ✓ │
│ • Specs: ✓ │
│ • Design: ✓ │
│ • Tasks: ✓ (15/15 completed) │
│ • Tests: ✓ (42 passed) │
├─────────────────────────────────────────────────────┤
│ Archive Location: │
│ archive/changes/{change_name}/ │
└─────────────────────────────────────────────────────┘Archive Structure
archive/
└── changes/
└── {change_name}/
├── SUMMARY.md # Change summary
├── CODE-DELIVERY.md # 代码归档(必填,见下节)
├── PROPOSAL.md # Original proposal
├── SPECS.md # Specifications
├── DESIGN.md # Design document
├── TASKS.md # Task list
├── CHANGELOG.md # Detailed changes
├── TESTS.md # Test results
└── artifacts/ # Related files代码归档(CODE-DELIVERY.md,强制)
归档是双归档:设计文档归档 + 开发代码归档。任何项目经 flowmind 设计后开发的
代码,归档时必须在归档目录生成 CODE-DELIVERY.md,让代码去向可追溯。
TASKS 全部完成但代码未合入/无去向的变更不得归档为 completed。
模板:
# 代码归档 - {change_name}
- 归档时间: {YYYY-MM-DD HH:mm}
- 变更类型: 代码变更 | 纯文档变更(二选一)
## 代码变更记录(纯文档变更则本节写「无代码变更」并说明)
- 仓库: {repo name / namespace / gitId}
- 分支: {feature branch} → 合入 {target branch}
- 提交:
- {short_id} {title}({date})
- ...
- MR/PR: {!id 或 URL}
- 合入状态: 已合入 {branch} | 待合入(注明原因与计划)| 已部署 {env}
- 构建/流水线: {pipeline/build id}(如有)Rules:
- 提交与 MR 信息经 git 平台核实后填写,不得凭记忆编造 commit id。
- 多仓库变更每个仓库单独一节记录。
- 代码仍在 feature 分支未合入时,只能归档为
status: delivered-pending-merge, 并注明计划合入时间;合入后补记并改为completed。
Learning Integration
This skill supports FlowMind learning:
- Archive Format: Learns preferred archive structure
- Summary Style: Learns how to summarize changes
- Cleanup Rules: Learns what to keep/delete
User: "归档时保留测试报告"
FlowMind: ✓ Learned: Keep test reports in archive
User: [Next archive]
FlowMind: [Includes test reports automatically]Examples
Example 1: Archive Feature
User: 归档用户登录功能
FlowMind:
┌─────────────────────────────────────────────────────┐
│ Change Archived │
├─────────────────────────────────────────────────────┤
│ Change: user-login-feature │
│ Status: ✓ Completed │
│ Duration: 14 days │
├─────────────────────────────────────────────────────┤
│ Summary: │
│ • Implemented OAuth2 login │
│ • Added social login (Google, GitHub) │
│ • Created user session management │
│ • Added login rate limiting │
├─────────────────────────────────────────────────────┤
│ Metrics: │
│ • 23 files changed │
│ • 1,847 lines added │
│ • 42 test cases │
│ • 100% test coverage │
├─────────────────────────────────────────────────────┤
│ Archive: archive/changes/user-login-feature/ │
└─────────────────────────────────────────────────────┘Example 2: Bulk Archive
User: 归档所有已完成的变更
FlowMind:
┌─────────────────────────────────────────────────────┐
│ Bulk Archive Complete │
├─────────────────────────────────────────────────────┤
│ Archived: 3 changes │
│ • user-login-feature (14 days) │
│ • order-optimization (7 days) │
│ • api-refactor (21 days) │
├─────────────────────────────────────────────────────┤
│ Total: │
│ • 67 files archived │
│ • 12,456 lines documented │
│ • 156 test cases │
└─────────────────────────────────────────────────────┘Configuration
{
"archive-change": {
"location": "archive/changes",
"keepTests": true,
"keepArtifacts": true,
"generateSummary": true,
"updateChangelog": true
}
}Archive Checklist
Before archiving, FlowMind checks:
- All tasks completed
- Code delivery recorded (CODE-DELIVERY.md: repo/branch/commits/MR/合入状态)
- All tests passing
- Documentation updated
- Code reviewed
- No open issues
- Deployment verified
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

