Skip to content

erode-app/erode / .agents/skills/adr

Create and manage Architecture Decision Records (ADRs). Use when making architectural changes (refactoring, API versioning, new domain layers, schema changes), when reviewing recent commits for documentation needs, or when the user mentions ADR, architecture decisions, or documenting technical decisions.

Architecture Decision Records

Create and manage ADRs in packages/web/src/content/docs/docs/contributing/adrs/ to document significant architectural decisions. ADRs are published on the docs site under Contributing.

Instructions

When to Create an ADR

Suggest creating an ADR when detecting:

  • Commits containing: refactor, architecture, migrate, introduce, domain layer, api version
  • New files in: domain/, api/, services/, models/
  • Schema changes: prisma/schema.prisma modified
  • Config changes: tsconfig.json, eslint.config.js significantly changed

Skip ADR suggestion for:

  • Commits containing only: fix, chore, docs, test, style
  • Changes only in: tests/, *.test.ts, *.spec.ts
  • Single file changes under 50 lines

Creating an ADR

  1. Find the next ADR number by listing packages/web/src/content/docs/docs/contributing/adrs/
  2. Check recent plan files in ~/.claude/plans/ for context
  3. Analyze recent commits: git log --since="7 days ago" --oneline
  4. Extract Context, Decision, and Rationale from plans/commits
  5. Create the ADR file using the template below in packages/web/src/content/docs/docs/contributing/adrs/
  6. Update the index page at packages/web/src/content/docs/docs/contributing/adrs/index.md

Listing ADRs

List existing ADRs: ls -1 packages/web/src/content/docs/docs/contributing/adrs/*.md | grep -v index

Template

Use Michael Nygard format in packages/web/src/content/docs/docs/contributing/adrs/NNN-kebab-case-title.md:

---
title: 'ADR-XXX: Title'
description: One-sentence summary of the decision.
---

**Status:** Accepted
**Date:** YYYY-MM-DD
**Authors:** [Names]

## Context

[What is the issue we're solving? What forces are at play?]

## Decision

[What is the change we're making?]

## Rationale

[Why is this the right choice?]

## Consequences

### Positive

- [Benefit 1]

### Negative

- [Tradeoff 1]

## Related Commits

- `hash` - commit message

Examples

User asks: "Document the recent API versioning changes" Action: Create ADR covering the v1 prefix, Zod validation, and thin client decisions

After refactoring: When Claude completes a significant refactor, proactively suggest documenting the decision

Reviewing work: When asked to review recent architectural changes, check if ADRs exist and suggest creating them if missing

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: 465kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall
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: 196kUpdated Claude CodeCodexUnverifiedInstall
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: 196kUpdated Claude CodeCodexVerifiedInstall