code-abyss
Personas, engineering skills, and security judgment for coding agents
All Skills in This Repository (24)
Pure Emerald Level Indicatorssage
Route user queries to the most relevant knowledge domain across Sage domains.
invalid-tools
Validate tool names against an allowlist in CI/CD configurations.
clash-skill
Detect and flag duplicate entries in datasets or configurations.
multi-script
Coordinate sequential or parallel execution of a.js and b.js scripts.
hi
Replace the most recent assistant message with a universal consent template.
gen-docs
Generate README.md and DESIGN.md skeletons by analyzing module code structure.
verify-security
Scan codebases offline and report security vulnerabilities with severity and remediation guidance.
verify-change
Analyze workspace changes to detect documentation drift and missing tests.
verify-module
Scan module directories to detect missing docs and code-documentation mismatches.
verify-quality
Analyze code quality metrics for complexity, naming, and duplication across repositories.
devops
Organize DevOps knowledge, practices, and tooling into a capability hub.
development
Route programming language questions to language-specific guidance and references.
Frequently Asked Questions
FAQPage SchemaHow to install Code Abyss?▼
Run `npx skills add telagod/code-abyss --all -g -y` in your terminal to install the full skill set globally.
What does Code Abyss actually do?▼
It gives your coding agent a consistent personality, 30 domain skills (security, DevOps, documents, hardware), and a judgment kernel that keeps decisions disciplined across sessions.
Which coding agents does Code Abyss support?▼
It installs natively into Claude Code, Codex CLI, Gemini CLI, and OpenClaw, with the same persona and skill content rendered for each target.
Can I mix personas and output styles?▼
Yes. Any of the 6 personas pairs with any of the 6 output styles, giving 36 validated combinations you can switch with a single flag.
Do I need coding experience to use Code Abyss?▼
No. After installation, you make plain-language requests and the agent applies the right skills and judgment rules automatically.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
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