ai-writing-guide
Multi-framework SDLC, research, and writing workflow orchestration
All Skills in This Repository (53)
Pure Emerald Level Indicatorsrisk-cycle
Track and manage risks across the Software Development Life Cycle.
config-validator
Validate AIWG YAML/JSON configuration files for syntax, schema, and references.
flaky-detect
Analyze CI history and test execution patterns to identify flaky tests.
quality-checker
Validate Claude skill packages for structure, content, and standards compliance.
tdd-enforce
Configure pre-commit hooks and CI coverage gates to enforce test-driven development.
traceability-check
Maps requirements to code and tests, computes coverage gaps and generates a traceability report.
claims-validator
Detects inflated or unsupported claims in text and generates a structured report.
test-coverage
Analyze lcov, cobertura, and istanbul coverage reports to identify gaps and recommend prioritized tests.
architecture-evolution
Analyze architecture change impact and generate ADRs and migration plans.
security-assessment
Perform security assessments with STRIDE threat modeling and CVSS scoring.
skill-builder
Transform extracted documentation into Claude skill packages with SKILL.md and references.
skill-enhancer
Enhance SKILL.md files with code examples, quick references, and FAQs.
Frequently Asked Questions
FAQPage SchemaHow to install ai-writing-guide?โผ
Run `npx skills add jmagly/ai-writing-guide --all -g -y` in your terminal to install all skills in this suite globally.
What does AIWG actually do?โผ
It deploys agents, commands, skills, and rules into your AI coding platform's native directories so one source of truth works across 10 platforms. It also adds research corpus management, iterative agent loops, and writing voice enforcement.
Which AI platforms does AIWG support?โผ
Claude Code, GitHub Copilot, Cursor, Warp, Windsurf, Codex, Factory, OpenCode, OpenClaw, and Hermes. Each platform gets artifacts in its native format and directory.
How do I run an autonomous fix loop?โผ
Ask your agent to 'ralph this: fix all tests' and the agent-loop skill iterates until a measurable completion criterion passes. External crash-resilient loops are available for long-running tasks.
Can non-developers use AIWG?โผ
Yes. Marketing, research, and writing frameworks work through plain-English requests, and the agent handles the underlying technical execution.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core