mgiovani/ai-arsenal / skills/docs-adr
docs-adr
VerifiedCreate a numbered Architecture Decision Record (ADR) documenting a technical decision with context, alternatives, and consequences. Trigger on "create an ADR", "document this architectural decision", "record why we chose X", or "write an ADR for [decision]". Not for a decision still open for discussion (use docs-rfc, RFCs propose, ADRs record) and not for bootstrapping a project's whole docs/ tree from scratch (use docs-init).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.9 KB |
| assets/templates/full.md | markdown | 2.5 KB |
| assets/templates/lightweight.md | markdown | 508 B |
| assets/templates/nygard.md | markdown | 339 B |
| evals/evals.json | config | 3.2 KB |
| evals/trigger-eval.json | config | 2.0 KB |
evals/evals.json
View on GitHub{
"skill": "docs-adr",
"evals": [
{
"id": "database-migration-strategy-default",
"prompt": "/docs-adr \"Database Migration Strategy\"",
"assertions": [
"Uses the Explore agent (or, when Task isn't available, direct grep/find searches) to verify the current database/migration setup before writing the Context section, rather than inventing it",
"Creates the file at docs/adr/XXXX-database-migration-strategy.md with a 4-digit ADR number one higher than the highest existing docs/adr/XXXX-*.md file (0001 if none exist)",
"Defaults to the Nygard template (Status, Context, Decision, Consequences sections) since no variant keyword was given",
"Fills every {{TOKEN}} the loaded nygard.md template actually contains (ADR_NUMBER, ADR_TITLE, DATE, CONTEXT) and leaves zero unresolved {{...}} placeholders in the written file",
"Sets the initial Status to \"Proposed\" and reports the ADR number and file path back to the user"
]
},
{
"id": "title-contains-variant-lookalike-word",
"prompt": "/docs-adr \"Full-Text Search Implementation for Product Catalog\"",
"assertions": [
"Recognizes that \"full\" here is part of the phrase \"Full-Text Search\", not a standalone variant keyword, since it isn't a separate leading token — correctly defaults to the Nygard template rather than misfiring the full variant",
"Preserves \"Full-Text Search Implementation for Product Catalog\" intact as the ADR title and in the kebab-case filename (docs/adr/XXXX-full-text-search-implementation-for-product-catalog.md), not stripped of \"full\"",
"Does not fabricate a search-implementation approach that isn't backed by anything found in the codebase during context gathering"
]
},
{
"id": "event-driven-architecture-full-variant",
"prompt": "/docs-adr full \"Adopt Event-Driven Architecture\"",
"assertions": [
"Strips the leading \"full\" variant keyword and uses \"Adopt Event-Driven Architecture\" as the title",
"Uses the full.md template and fills its actual token set (e.g. AUTHORS, STAKEHOLDERS, PROBLEM_STATEMENT, OPTION_1_NAME/OPTION_2_NAME, POSITIVE_CONSEQUENCES/NEGATIVE_CONSEQUENCES/NEUTRAL_CONSEQUENCES) rather than the shorter Nygard token set",
"Consequences are split into Positive, Negative, and Neutral subsections as the full template defines",
"Gathers and cites real context (existing messaging/event code, configs, or docs actually found via search) rather than generic boilerplate options",
"ADR number increments correctly from the highest existing docs/adr/XXXX-*.md file"
]
},
{
"id": "missing-title-argument",
"prompt": "/docs-adr",
"assertions": [
"Does not invent a placeholder decision title (e.g. \"Untitled Decision\") and does not create any file under docs/adr/",
"Does not run the ADR-numbering scan, context gathering, or template population phases — stops before Phase 1 completes",
"Final response asks the user to supply a decision title (and optionally which variant) rather than guessing one",
"No Write tool call occurs anywhere in the transcript for this run"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |