managing-adrs
Automates the creation, numbering, and index maintenance of architectural decision documents.
Install
mkdir -p .claude/skills/managing-adrs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16265" && unzip -o skill.zip -d .claude/skills/managing-adrs && rm skill.zipInstalls to .claude/skills/managing-adrs
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Create and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.Key capabilities
- →Auto-detect project's ADR directory.
- →Auto-number Architecture Decision Records.
- →Adapt to project's existing ADR template style.
- →Automatically update README.md with an ADR table index.
- →Mark old ADRs as 'Superseded' and link new ones.
- →Create new ADRs with required and optional sections.
How it works
This skill discovers ADR directories, detects template styles, auto-numbers new ADRs, and maintains an index in README.md.
Inputs & outputs
When to use managing-adrs
- →Documenting a technical decision
- →Updating project architecture logs
- →Creating new ADR files
About this skill
Architecture Decision Records
Create and manage Architecture Decision Records following project conventions with automatic numbering and index maintenance.
Auto-Invoke Triggers
This skill automatically activates when:
- Keywords: "ADR", "architecture decision", "document this decision", "record the decision"
- Editing ADR files: Files in
docs/adr/,doc/adr/,architecture/decisions/,.adr/ - Discussing architectural choices: Framework selection, technology decisions, pattern choices
What This Skill Delivers
1. ADR Creation
- Auto-detect project's ADR directory
- Auto-number ADRs (scan existing, increment)
- Adapt to project's existing template style
- Offer MADR 4.0 enhancements as optional additions
2. Directory Discovery
Search order for ADR directories:
docs/adr/doc/adr/architecture/decisions/.adr/- Create
docs/adr/if none exists
3. Template Detection
Analyze existing ADRs to detect:
- Naming convention:
NNNN-kebab-case-title.mdorNNN-title.md - Section structure: Status, Context, Decision, Consequences
- Optional sections: Decision Drivers, Pros/Cons, Confirmation
4. Index Maintenance
Automatically update README.md with ADR table:
| Number | Title | Status | Date |
|---|
5. Supersession Workflow
When replacing an ADR:
- Mark old ADR status as "Superseded by [ADR-NNNN]"
- Link new ADR with "Supersedes [ADR-NNNN]"
- Update README.md index
Core Template Sections
Required (Minimal)
- Status: Proposed | Accepted | Deprecated | Superseded
- Date: ISO 8601 format (YYYY-MM-DD)
- Context and Problem Statement: 2-3 sentences describing the situation
- Decision: What was decided and why
- Consequences: Positive and negative impacts
Optional Enhancements (MADR 4.0)
- Technical Story: Link to issue/spec (e.g.,
#123) - Decision Drivers: Bulleted list of forces/concerns
- Decision Makers: Who made this decision
- Consulted: Stakeholders whose opinions were sought
- Informed: Stakeholders who need to know
- Considered Options: List of alternatives evaluated
- Pros and Cons: Detailed analysis per option
- Confirmation: How to validate the decision was implemented
Quick Start
Create New ADR
# Auto-invoke by saying:
"Document the decision to use PostgreSQL over MongoDB"
"Create an ADR for our authentication approach"
"I need to record why we chose React Query"
Supersede Existing ADR
"Supersede ADR-0005 with a new caching strategy"
"Replace our database decision ADR with the new approach"
Scripts
Located in scripts/ directory, using uv for execution:
adr_create.py
uv run scripts/adr_create.py --title "Use PostgreSQL for persistence"
uv run scripts/adr_create.py --title "..." --template madr --create-dir
adr_index.py
uv run scripts/adr_index.py --dir docs/adr
uv run scripts/adr_index.py --dir docs/adr --dry-run
adr_supersede.py
uv run scripts/adr_supersede.py --old 5 --new 12 --dir docs/adr
Output Example
# ADR-0012: Use PostgreSQL for Data Persistence
## Status
Accepted
## Date
2026-01-10
## Context and Problem Statement
We need a reliable database solution for our microservices architecture
that supports complex queries and ACID transactions.
## Decision
Chosen option: PostgreSQL, because it provides the best balance of
ACID compliance, query flexibility, and team familiarity.
## Consequences
**Positive:**
- Full ACID transaction support
- Mature ecosystem and tooling
**Negative:**
- Horizontal scaling requires more setup
Progressive Disclosure
- Level 2: WORKFLOW.md - Step-by-step methodology
- Level 3: EXAMPLES.md - Real-world ADR examples
- Level 4: TROUBLESHOOTING.md - Error handling
Related Resources
- MADR 4.0 Template: https://adr.github.io/madr/
- ADR GitHub Organization: https://github.com/adr
When not to use it
- →When the user is not discussing architecture decisions or ADRs.
- →When editing ADR files outside of specified directories.
- →When the task is not related to documenting architectural choices.
Limitations
- →The skill searches for ADR directories in a predefined order.
- →It adapts to existing template styles but can offer MADR 4.0 enhancements.
- →Supersession workflow requires marking old ADRs and linking new ones.
How it compares
This workflow automates the creation, numbering, and indexing of ADRs, ensuring consistency and reducing manual overhead compared to a generic document creation process.
Compared to similar skills
managing-adrs side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| managing-adrs (this skill) | 0 | 5mo | Review | Intermediate |
| deepwiki-rs | 25 | 9mo | Review | Intermediate |
| repo-research-analyst | 1 | 6mo | Review | Intermediate |
| c4-component | 1 | 4mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by diegosouzapw
View all by diegosouzapw →You might also like
deepwiki-rs
sopaco
AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.
repo-research-analyst
parcadei
Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase
c4-component
sickn33
Expert C4 Component-level documentation specialist. Synthesizes C4 Code-level documentation into Component-level architecture, defining component boundaries, interfaces, and relationships. Creates component diagrams and documentation. Use when synthesizing code-level documentation into logical components.
agent-pseudocode
ruvnet
Agent skill for pseudocode - invoke with $agent-pseudocode
spec
matteocervelli
>
cs-arch
wildlily1021
维护 `codestable/architecture/` 这份只记现状的系统地图,三种模式 update / check / backfill。触发:用户说"刷新 architecture"、"做架构检查"、"补这个模块的架构文档"、"方案和代码对得上吗",或 feature 阶段需要先做架构动作。不写未来规划(走 cs-roadmap)。