adr
Skill4 starsChanged 29 days agoMITView on GitHub
[UDS] Create, manage, and track Architecture Decision Records (ADR). Use when: architecture decisions, technology choices, design trade-offs, pattern selection. Not for: decisions that do not change architecture — record them in the spec or commit; ideas not yet formed enough to decide — use /brainstorm. Keywords: ADR, architecture decision, decision record, trade-off.
90 other projects use a version of this.
Adopted by
Most recently taken up by
- GustavoAlecio/claude-setuptheir own version, first seen Nov 8, 2026
- computerlovetech/skillstheir own version, first seen Nov 8, 2026
- rvdbreemen/OTGW-firmwaretheir own version, first seen Nov 8, 2026
- axodouble/skillstheir own version, first seen Nov 8, 2026
- RodrigoAnciaes/golem-sddtheir own version, first seen Nov 8, 2026
- n1kben/agentstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use fdr, product-spec and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
thiagofgfSkillfdr
Use when creating, changing, reviewing, retiring, auditing, or backfilling implemented user-visible feature behavior, permissions, feature-specific rationale, tradeoffs, or relationships to architectural decisions.
Also in 3 projects that use this
vndeeSkillproduct-spec
Use when starting a new feature, product, or project — before any architecture or code, to define what to build and why
Also in 3 projects that use this
OpenAISkillthreat-model
Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
Also in 6 projects that use this
montymiSkilltech-spec
Parse and review Technical Specification documents for completeness, consistency, and implementation readiness
Also in 3 projects that use this
petestewartSkilltest-review
Review unit tests for quality, coverage, consistency, and adherence to existing codebase patterns. Use when the user says "/test-review", "review my tests", "check my test coverage", "are my tests good", or needs feedback on test quality and patterns.
Also in 3 projects that use this
MicrosoftSkilljira
Jira issue workflows for search, issue updates, transitions, comments, field discovery, and interactive credential setup via the Jira REST API. Use when you need to configure Jira access, search with JQL, inspect an issue, create or update work items, move an issue between statuses, post comments, or discover required fields for issue creation.
Also in 5 projects that use this
Other versions90 projects use a version of this.
Word for word · 1
- AsiaOstrich/universal-dev-standards★ 84100% same
Edited · 0
None found.
Wrote their own version · 89
- CrowdDotDev/crowd.dev★ 3.4ksame name
- chattocorp/chatto★ 2.9ksame name
- Cosmian/kms★ 372same name
- linuxfoundation/insights★ 288same name
- rvdbreemen/OTGW-firmware★ 213same name
- sd0xdev/sd0x-dev-flow★ 192same name
- sd0xdev/sd0x-harness★ 192same name
- irahardianto/awesome-agv★ 157same name
- jellydn/my-ai-tools★ 127same name
- EmeaAppGbb/spec2cloud★ 100same name
79 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-coverageSkill
- ai-collaboration-standardsSkill
- ai-friendly-architectureSkill
- ai-instruction-standardsSkill
- api-designSkill
- atddSkill
- auditSkill
- bddSkill
- brainstormSkill
- changelogSkill
- checkinSkill
- ci-cdSkill
- code-reviewSkill
- commitSkill
- contract-testSkill
- databaseSkill
- deploySkill
- methodologySkill
- dev-workflowSkill
- docgenSkill
- documentation-guideSkill
- durableSkill
- e2eSkill
- error-code-guideSkill
- git-workflow-guideSkill
- incidentSkill
- journey-test-assistantSkill
- knowledge-graphSkill
- logging-guideSkill
- metricsSkill
- migrateSkill
- observabilitySkill
- orchestrateSkill
- planSkill
- prSkill
- discoverSkill
- project-structure-guideSkill
- pushSkill
- refactorSkill
- releaseSkill
- requirementSkill
- retrospectiveSkill
- reverseSkill
- runbookSkill
- securitySkill
- scanSkill
- skill-builderSkill
- sloSkill
- spec-deriveSkill
- sddSkill
- sweepSkill
- tddSkill
- coverageSkill
- testing-guideSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 75 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Create, manage, and track Architecture Decision Records.
- Distinctive: line 81
Rule of thumb: If someone might ask "why?" in 6 months, write an ADR.
- Distinctive: line 149
Before accepting an ADR:
- Very specific: line 161
After /adr completes, the AI assistant should suggest:
- Very specific: line 177
When the user invokes /adr, the AI assistant MUST:
- Very specific: line 185
When the user invokes /adr list:
- Distinctive: line 191
Read the existing ADR
- Very specific: line 193
Update old ADR status to Superseded by ADR-NNN
- Very specific: line 194
Add Supersedes ADR-NNN to new ADR
“Common” is measured: kept by at least 6 in 10 of the 75 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ADR Assistant | 架構決策記錄助手
Language: English | 繁體中文
Create, manage, and track Architecture Decision Records. Capture the context, options, and rationale behind significant technical decisions.
建立、管理和追蹤架構決策記錄。捕捉重大技術決策的背景、選項和理由。
Workflow | 工作流程
CAPTURE ──► ANALYZE ──► DECIDE ──► RECORD ──► LINK
捕捉背景 分析選項 做出決策 記錄 ADR 建立連結Phase 1: CAPTURE | 捕捉背景
Identify the context and constraints driving the decision.
識別驅動決策的背景與限制條件。
| Step | Action | 步驟 |
| 1 | Identify the problem or opportunity | 識別問題或機會 |
| 2 | List constraints (time, budget, team skills) | 列出限制條件 |
| 3 | Define decision drivers | 定義決策驅動因素 |
Phase 2: ANALYZE | 分析選項
Explore at least 2 options with pros and cons.
至少探索 2 個選項,列出優缺點。
| Step | Action | 步驟 |
| 1 | Brainstorm candidate options | 腦力激盪候選方案 |
| 2 | Evaluate each against decision drivers | 根據決策驅動因素評估 |
| 3 | Document pros/cons for each | 記錄各方案優缺點 |
Phase 3: DECIDE | 做出決策
Select the best option and articulate the rationale.
選擇最佳方案並闡述理由。
Phase 4: RECORD | 記錄 ADR
Generate the ADR file following the standard template.
依照標準模板產生 ADR 檔案。
Phase 5: LINK | 建立連結
Cross-reference with related artifacts (SPECs, PRs, code).
與相關工件(規格、PR、程式碼)建立交叉引用。
Quick Reference | 快速參考
When to Write an ADR | 何時撰寫 ADR
| Write ADR | Skip ADR |
| Framework/library choice | Routine dependency update |
| API contract or data format | Bug fix within existing architecture |
| Deployment strategy change | Code style decision |
| Establishing new patterns | Trivial implementation choice |
Rule of thumb: If someone might ask "why?" in 6 months, write an ADR.
經驗法則:如果 6 個月後有人可能會問「為什麼?」,就寫一份 ADR。
Status Lifecycle | 狀態生命週期
Proposed ──► Accepted ──► Deprecated
│
└──► Superseded by ADR-NNN| Status | Description | 說明 |
| Proposed | Under discussion | 討論中 |
| Accepted | Active, should be followed | 已接受,應遵循 |
| Deprecated | No longer relevant | 不再適用 |
| Superseded | Replaced by newer ADR | 已被新 ADR 取代 |
ADR Template Summary | 模板摘要
# ADR-NNN: [Title]
- Status: [Proposed | Accepted | Deprecated | Superseded]
- Date: YYYY-MM-DD
- Deciders: [people]
- Technical Story: [SPEC-ID or Issue]
## Context
## Decision Drivers
## Considered Options
## Decision Outcome
### Consequences (Good / Bad / Neutral)
## LinksStorage | 存放位置
docs/adr/
├── ADR-001-short-description.md
├── ADR-002-short-description.md
└── README.md # Index (optional)Commands | 指令
| Command | Action | 說明 |
/adr | Interactive ADR creation wizard | 互動式建立 ADR |
/adr create | Create a new ADR | 建立新 ADR |
/adr list | List all ADRs with status | 列出所有 ADR 及狀態 |
/adr search [keyword] | Search ADRs by keyword | 依關鍵字搜尋 ADR |
/adr supersede [ADR-NNN] | Supersede an existing ADR | 取代現有 ADR |
/adr review | Review ADRs for staleness | 審查過期的 ADR |
Integration with Other Skills | 與其他技能的整合
| Skill | Integration | 整合方式 |
/sdd | Reference ADRs in Technical Design; suggest creating ADR for major decisions | 在技術設計中引用 ADR |
/code-review | Reference ADRs as design rationale during code review | 程式碼審查時引用 ADR |
/commit | Include ADR-NNN in commit footer for traceability | 提交時在 footer 加入 ADR 編號 |
/brainstorm | Feed brainstorm output into ADR option analysis | 腦力激盪結果作為 ADR 選項分析輸入 |
Quality Checklist | 品質檢查清單
Before accepting an ADR:
| Check | Criteria | 標準 |
| ☐ Context | Clearly explains the problem | 清楚說明問題 |
| ☐ Options | At least 2 options considered | 至少考慮 2 個選項 |
| ☐ Drivers | Decision drivers explicitly listed | 決策驅動因素明確列出 |
| ☐ Consequences | Both good and bad outcomes | 包含正面與負面結果 |
| ☐ Links | Related artifacts referenced | 相關工件已引用 |
Next Steps Guidance | 下一步引導
After /adr completes, the AI assistant should suggest:
ADR created. Suggested next steps:
- Execute
/sddto create a spec if the decision requires implementation- Execute
/committo commit the ADR file- Update related SPECs to reference this ADR
- Share with team for review if status is
Proposed
ADR 已建立。建議下一步:
- 執行
/sdd建立規格(若決策需要實作)- 執行
/commit提交 ADR 檔案- 更新相關規格以引用此 ADR
- 若狀態為
Proposed,分享給團隊審查
AI Agent Behavior | AI 代理行為
When the user invokes /adr, the AI assistant MUST:
- Check existing ADRs — Search
docs/adr/to determine next ADR number - Guide interactively — Ask about context, drivers, and options step by step
- Generate the file — Write ADR to
docs/adr/ADR-NNN-title.md - Suggest links — Identify related SPECs or ADRs to cross-reference
- Offer next steps — Show the Next Steps Guidance above
When the user invokes /adr list:
- Scan
docs/adr/directory - Parse status from each ADR file
- Display as a table: Number, Title, Status, Date
When the user invokes /adr supersede [ADR-NNN]:
- Read the existing ADR
- Guide creation of a new ADR
- Update old ADR status to
Superseded by ADR-NNN - Add
Supersedes ADR-NNNto new ADR
Reference | 參考
- Core Standard: adr-standards.md
- Detailed Guide: guide.md
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.

