adr-skills
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANTHROPIC_API_KEY | No | Anthropic API key used for AI-powered ADR generation (via Claude Opus) and quality review. If not provided, the server falls back to keyword-based extraction and review tools become unavailable. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| save_sessionC | Save a Claude Code development session to the database |
| generate_adrB | Analyze a saved session and auto-generate an ADR. Exports a markdown file and warns about similar past decisions. |
| update_adr_statusC | Update the status of an ADR: Proposed → Accepted → Deprecated → Superseded |
| search_decisionsC | Search past architectural decisions by keyword |
| get_timelineC | Get the decision timeline for a project |
| review_adrB | AI quality review of an ADR — scores completeness, flags missing context, unconsidered alternatives, and optimistic consequences |
| link_adrsB | Create a relationship between two ADRs: related_to, conflicts_with, or depends_on |
| get_adr_graphB | Visualize ADR dependency graph. Optionally scope to a single ADR. |
| check_stale_adrsB | Find Accepted ADRs that have not been reviewed in a while and may need revisiting |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have distinct purposes focused on different aspects of ADR management, but there is some potential overlap between 'search_decisions' and 'check_stale_adrs' since both involve finding ADRs based on criteria. The descriptions clarify their differences well, with only minor ambiguity.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'check_stale_adrs', 'generate_adr', and 'update_adr_status'. This predictability makes it easy for agents to understand and select the right tool without confusion.
With 9 tools, this server is well-scoped for managing architectural decision records (ADRs), covering creation, review, search, visualization, and lifecycle updates. Each tool serves a clear purpose, and the count aligns well with the domain's complexity.
The tool set provides comprehensive coverage for ADR workflows, including generation, review, status updates, linking, visualization, search, and session management. There are no obvious gaps, as it supports the full lifecycle from creation to maintenance and analysis.