adr-manager
Document architectural decisions using the Michael Nygard ADR format. Use when a significant architectural choice is made: picking a database, deciding on an API protocol, adopting a new pattern, or choosing between competing approaches.
- License 许可
- MIT
- 所属仓库
- muratovv/ai-hats
- 最近更新
- 2026-11-05
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- adr-manager
- license
- MIT
- description
- Document architectural decisions using the Michael Nygard ADR format. Use when a significant architectural choice is made: picking a database, deciding on an API protocol, adopting a new pattern, or choosing between competing approaches.
03 SKILL.md 正文
ADR Manager
Standardize documentation of architectural decisions for traceability.
When to Use
Records a decision already made, for traceability — it is not where you explore options (that is the plan stage) and not general prose docs (→ doc-protocol). The architecture skills whose Completion step appends findings to an ADR (clean-architecture-guide, api-evolution-checklist, distributed-systems-checklist, trust-boundary-mapping) all feed into this format; this skill owns the record, not the analysis behind it.
Format (Michael Nygard)
- Title: Short noun phrase
- Context: What is the problem we are solving?
- Decision: What is the change we are making?
- Status: Proposed / Accepted / Deprecated / Superseded
- Consequences: What becomes easier or harder as a result?
Storage
Save all ADRs sequentially in docs/adr/ (e.g., 0001-use-grpc-for-internal-services.md).
Completion
- ADR file created in
docs/adr/with sequential numbering - All 5 sections filled (Title, Context, Decision, Status, Consequences)
Bundled Rules
Architecture Foundation
- Context Management: Summarize architectural state into ADRs. Operate at C4 level.
- Distributed Systems: Design for failure — retries, circuit breakers, graceful degradation.
- API-First: Define contracts before systems (OpenAPI/Protobuf). Strict backward compatibility.
- Delegation: Delegate deep dives to sub-agents, synthesize findings into ADR updates.
Anti-Patterns
- Missing consequences — the most valuable section, forces thinking about trade-offs
- Documenting after the fact without context — write the ADR when the decision is fresh
- ADR without status — unclear whether this is a proposal or accepted decision
04 同仓库更多 Skills
tool-evaluation-protocol
Time-bounded protocol for evaluating new tools, libraries, or methodologies before adoption. Use when evaluating a candidate dependency for the project, researching a methodology (e.g. ML/LLM frameworks, testing approaches), or following up on a hype-driven recommendation.
systematic-debugging
4-phase bug-fix protocol (evidence, pattern, hypothesis, verify). Use when investigating any error, failure, or unexpected behavior, handling bug reports from users or monitoring, or diagnosing test failures with non-obvious causes.
skill-template
Canonical template and validation guide for ai-hats skills. Use when creating a new skill, reviewing an existing one for structural compliance, or deciding which pattern fits a new behavior.
skill-optimization
Audit and refactor library components to eliminate redundancy and staleness. Use during periodic library maintenance, after adding multiple new skills or rules, when a role's token budget is too high, or after retrospectives identify component issues.
silent-fallback-gate
PreToolUse hook — refuses an Edit or Write that adds an inert broad except. Use when a Python edit was blocked for a silent fallback.
retro-to-framework
Convert an observation about agent behavior — from a retrospective or from a single incident — into a framework-level change (hook, rule, skill, skill update). Use after a retrospective identifies problems that are not project-specific, after an incident where an agent misapplied a component it had read, when CLAUDE.md band-aids accumulate (more than 3 per-project rules that could be generic), or when the same problem recurs across multiple projects.