netresearch/agent-rules-skill / skills/agent-rules
agent-rules
FlaggedUse when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
scripts/detect-heuristics.sh
View on GitHub#!/usr/bin/env bash
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: Netresearch DTT GmbH
# Detect project heuristics (When X → Do Y decisions)
set -euo pipefail
PROJECT_DIR="${1:-.}"
cd "$PROJECT_DIR"
# Get project language
PROJECT_INFO=$(bash "$(dirname "$0")/detect-project.sh" "$PROJECT_DIR" 2>/dev/null || echo '{"language":"unknown"}')
LANGUAGE=$(echo "$PROJECT_INFO" | jq -r '.language')
output=""
# Check for env file patterns
if [ -f ".env.example" ] || [ -f ".env.sample" ]; then
output="$output| Adding env var | Add to \`.env.example\` first |\n"
fi
# Check for TypeScript env types
if [ -f "src/env.d.ts" ] || [ -f "types/env.d.ts" ]; then
output="$output| Adding env var | Also update \`types/env.d.ts\` |\n"
fi
# Check for Next.js App Router
if [ -d "app" ] && { [ -f "next.config.js" ] || [ -f "next.config.ts" ] || [ -f "next.config.mjs" ]; }; then
output="$output| Adding new page | Create in \`app/\` (App Router) |\n"
fi
# Check for old Next.js Pages Router
if [ -d "pages" ] && [ ! -d "app" ]; then
output="$output| Adding new page | Create in \`pages/\` directory |\n"
fi
# Check for state management
if grep -q "zustand" package.json 2>/dev/null; then
output="$output| Adding state | Use Zustand store in \`stores/\` |\n"
elif grep -q "redux" package.json 2>/dev/null; then
output="$output| Adding state | Use Redux slice pattern |\n"
elif grep -q "mobx" package.json 2>/dev/null; then
output="$output| Adding state | Use MobX observable pattern |\n"
fi
# Check for API directory patterns
if [ -d "src/api" ] || [ -d "api" ]; then
api_dir=$([ -d "src/api" ] && echo "src/api" || echo "api")
output="$output| Adding API endpoint | Create in \`$api_dir/\` |\n"
fi
# Check for test patterns
if [ -d "__tests__" ]; then
output="$output| Adding tests | Create in \`__tests__/\` directory |\n"
elif [ -d "tests" ] || [ -d "test" ]; then
test_dir=$([ -d "tests" ] && echo "tests" || echo "test")
output="$output| Adding tests | Create in \`$test_dir/\` directory |\n"
fi
# Check for TYPO3
if [ -f "ext_emconf.php" ]; then
output="$output| Adding controller | Create in \`Classes/Controller/\` |\n"
output="$output| Adding service | Create in \`Classes/Service/\` |\n"
fi
# Check for Makefile
if [ -f "Makefile" ]; then
output="$output| Running tasks | Check \`make help\` for available commands |\n"
fi
# Check for Docker
if [ -f "docker-compose.yml" ] || [ -f "docker-compose.yaml" ] || [ -f "compose.yml" ]; then
output="$output| Running locally | Use \`docker compose up\` |\n"
fi
# Check for DDEV
if [ -d ".ddev" ]; then
output="$output| Running locally | Use \`ddev start\` then \`ddev ssh\` |\n"
fi
# Language-specific heuristics
case "$LANGUAGE" in
"go")
output="$output| Adding package | Internal → \`internal/\`, Public → \`pkg/\` |\n"
[ -f "go.work" ] && output="$output| Multi-module | Use \`go.work\` for workspace |\n"
;;
"php")
output="$output| Adding class | Follow PSR-4 in \`Classes/\` or \`src/\` |\n"
;;
"python")
[ -f "pyproject.toml" ] && output="$output| Adding dependency | Update \`pyproject.toml\` |\n"
;;
esac
# Output (remove empty lines, duplicates, limit to 10)
echo -e "$output" | sed '/^$/d' | sort -u | head -10
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: 470k | 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: 197k | 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: 197k | 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: 197k | Updated | Claude CodeCodex | Verified | Install |