naravid19/ai-project-rules-generator
generating-project-rules
VerifiedMake sure to use this skill WHENEVER the user mentions creating, generating, or updating project rules files (.cursorrules, AGENTS.md, CLAUDE.md, GEMINI.md, or equivalent) for any software project. This is essential when a user wants to integrate AI skills into their development workflow, or when they need cross-platform AI tool configuration. Skip this for general code generation, refactoring, or tasks unrelated to AI agent configuration files.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 21.0 KB |
| assets/i18n/README.md | markdown | 2.9 KB |
| assets/images/logo.png | binary | 14.1 KB |
| assets/templates/README.md | markdown | 3.1 KB |
| assets/templates/mcp_registry.yaml | config | 1.2 KB |
| assets/templates/rulesrc-template.yaml | config | 7.3 KB |
| scripts/audit.py | script | 6.5 KB |
| scripts/config_runtime.py | script | 4.0 KB |
| scripts/discover-skills.py | script | 26.4 KB |
| scripts/extract-capabilities.py | script | 2.0 KB |
| scripts/indexer.py | script | 15.3 KB |
| scripts/lib/__init__.py | script | 74 B |
| scripts/lib/confidence.py | script | 1.8 KB |
| scripts/lib/config_runtime.py | script | 1.1 KB |
| scripts/lib/design_tokens.py | script | 4.7 KB |
| scripts/lib/semantic_matcher.py | script | 2.1 KB |
| scripts/log_viewer.py | script | 2.7 KB |
| scripts/memory_manager.py | script | 4.6 KB |
| scripts/project_rules_runtime.py | script | 27.3 KB |
| scripts/remote_source.py | script | 2.1 KB |
| scripts/rules_config.py | script | 5.7 KB |
| scripts/skill_metadata.py | script | 7.2 KB |
| scripts/traceability.py | script | 2.9 KB |
| scripts/validate-output.ps1 | script | 24.5 KB |
| scripts/validate-output.sh | script | 19.9 KB |
| scripts/wizard.py | script | 18.1 KB |
assets/templates/rulesrc-template.yaml
View on GitHub# =============================================================================
# .rulesrc.yaml - Configuration Template
# =============================================================================
# Place this file in your project root to customize workflow behavior.
# The workflow reads this file during Stage 0 (User Preferences).
# All fields are optional - defaults are used when omitted.
# =============================================================================
# --- Target Platforms ---------------------------------------------------------
# Which AI tools to generate files for.
# Options: cursor, claude, antigravity, gemini, codex, kiro, copilot, opencode, adal
# If set, this overrides AI-tool auto-detection.
# Default: auto-detect from existing files, fallback to [cursor, codex]
target_platforms:
- cursor
- codex
# --- Severity Level -----------------------------------------------------------
# How strict should the generated rules be?
# strict = more critical rules, fewer soft suggestions
# balanced = default mix of critical and important guidance
# relaxed = fewer blocking rules, more notes and examples
severity_level: balanced
# --- Output Language ----------------------------------------------------------
# Language for generated documentation comments and descriptions.
# Code examples remain in the original programming language.
# Options: en, th, ja, zh, ko, es, fr, de, pt
# Default: en
output_language: en
# --- Sections ----------------------------------------------------------------
# Include or exclude optional sections in generated files.
# Required sections stay present regardless of this filter.
# Default: all optional sections included
sections:
include:
- project-identity
- coding-standards
- critical-rules
- important-guidelines
- code-smells
- testing
exclude: []
# Uncomment to exclude optional sections:
# - security
# - accessibility
# - i18n
# - git-workflow
# - performance
# - api-design
# --- Skill Sources ------------------------------------------------------------
# Override automatic skill-source discovery roots.
# If omitted, the workflow scans the project-local `.agent/` directory.
# Paths may be relative to the project root or absolute.
# Exactly one entry should be marked `confirmed: true` before generation begins.
# Roots are scanned in the order listed here, but generation must only retrieve
# and reference skills from the confirmed root.
# `format` is optional; if provided, the workflow trusts it and skips inference.
# Keep `.agent/skills` as the default Antigravity CATALOG target for backward compatibility.
# Hybrid skill directories may include `SKILL.md` with companion `AGENTS.md`, `CLAUDE.md`,
# `README.md`, and adjacent `references/` or `rules/` folders.
# skill_sources:
# - path: "C:/shared/team-skills/.agent"
# confirmed: true
# - path: .agent
# confirmed: false
# --- Custom Keywords ----------------------------------------------------------
# Additional keywords to search for during skill discovery (Stage 2).
# These are merged with auto-detected keywords from your tech stack with case-insensitive dedupe.
custom_keywords:
# - microservices
# - event-driven
# - real-time
# - cqrs
# --- Template Style -----------------------------------------------------------
# How to structure the generated files.
# progressive = overview -> details (default)
# flat = same content scope with shallower headings and fewer long examples
# minimal = essential sections only, tuned for shorter outputs
# Options: progressive, flat, minimal
template_style: progressive
# --- Quality Threshold --------------------------------------------------------
# Minimum quality score to pass verification (Stage 5).
# Validation scripts use this threshold unless a CLI threshold overrides it.
# Scale: 0-50, Default: 38
quality_threshold: 38
# --- Superpowers Methodology (v1.9.4+) ----------------------------------------
# Enables TDD for documentation and Verification Before Completion.
# verification_before_completion: Forces commands to be run before claiming success.
# strict_tdd_requirements: RED-GREEN-REFACTOR enforcement for rules and specs.
verification_before_completion: true
strict_tdd_requirements: true
# --- Karpathy Methodology (v1.9.4+) -------------------------------------------
# Enables high-fidelity 'Think Before Coding' features.
# surgical_mode: Adds 'Assumptions' and 'Tradeoffs' sections to outputs.
# goal_driven_execution: Forces [Step] -> verify: [check] pattern for workflows.
surgical_mode: true
goal_driven_execution: true
# --- Confidence Threshold -----------------------------------------------------
# Minimum confidence score before the workflow must stop and ask the user to clarify
# the project type / intent with multiple-choice options.
# Scale: 0-100, Default: 80
confidence_threshold: 80
# --- Skill Match Limit --------------------------------------------------------
# Maximum number of matched technical skill candidates to carry forward.
# This prevents context overload on large catalogs.
# Default: 5
skill_match_limit: 5
# Maximum number of matched agentic/functional skills (e.g. planning, security) to carry forward.
# Default: 3
agentic_match_limit: 3
# --- Preview Mode -------------------------------------------------------------
# Show a preview of the planned structure before writing files.
# Default: false
preview_mode: false
# --- Audit Logging ------------------------------------------------------------
# JSON audit logs must stay project-local to avoid mixing runs across repos.
logging:
enabled: true
directory: .agent/logs
# --- Memory Summary -----------------------------------------------------------
# Summarized state file generated from recent project-local logs.
memory:
enabled: true
summary_path: .agent/memory/project_state.md
# --- Native MCP Servers & Subagents -------------------------------------------
# Optional list of native MCP server names to surface in generated AGENTS.md
# under the [Native MCP Servers] section.
# mcp_servers:
# - filesystem
# - github
# Enable specific orchestration strategies (Superpowers Methodology)
# Instructs the AI on *how* to use the tools it has.
enable_subagent_orchestration: true # Recommends dispatching subagents for multi-step tasks
enforce_mcp_tool_mapping: true # Maps specific domains to specific MCPs (e.g. React -> chrome-devtools)
# ------------------------------------------------------------------------------
# --- Intent Override ----------------------------------------------------------
# When the confidence gate falls below the threshold, the CLI wizard can store
# the user's clarified intent here for downstream routing.
project_intent_override:
# --- Monorepo Cascading Rules -------------------------------------------------
# Optional configuration for Monorepo Auto-Routing.
# When enabled, subagents will automatically be dispatched to discover local
# skills and generate local .cursorrules for each sub-project, merging them
# with the universal root rules.
monorepo:
enabled: auto
service_dirs:
- frontend
- backend
- apps/web
- apps/api
# --- Existing Files -----------------------------------------------------------
# What to do if output files already exist.
# merge = diff-based update guidance that preserves user customizations
# Options: ask, overwrite, merge, skip
# Default: ask
existing_files: ask
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |