Skip to content

Latest commit

 

History

History
312 lines (209 loc) · 12.9 KB

File metadata and controls

312 lines (209 loc) · 12.9 KB

⚡ CodeRed AI Skills

Give your AI coding agent institutional knowledge — in five minutes, with zero config.

Stars License Skills Agent support


The NASA/DOD Code Review skill catching an unbounded loop, citing the violated rule, offering three fix options, and blocking the merge
The NASA/DOD Code Review skill catching a real Power-of-Ten violation — rule citation, fix options, and merge gate, all in one pass. (regenerate with VHS)


Why this exists

Every new chat with your AI coding agent starts from zero. It doesn't know your team's review standards, your branching conventions, or the five-step process you always run before merging. So you re-explain it — every session, every project, in slightly different words, until the agent's behavior drifts from what you actually wanted.

Skills fix that. A skill is a focused set of markdown instructions that encodes a specific way of working — a review process, a planning workflow, an analysis format — once, precisely, so any agent that can read a file can run it the same way every time.

Note

If your agent can read a file, it can use these skills. No plugins, no frameworks, no SDK.


🚀 Quickstart

1. Clone the repo

# Global install (available across all your projects)
git clone https://github.com/codered/ai ~/.codered

# Per-project install (lives alongside your code)
git clone https://github.com/codered/ai .codered

2. Tell your agent where to find the skills

Add one line to your agent's context file. The exact file depends on your agent — see Installation for specifics.

Skills are available at <path>/skills/. Load the SKILL.md in the relevant skill folder when asked to use a skill.

3. Use a skill

nasa-dod review

That's it.


📦 Skills

Reviews your code against the same engineering standards used for flight software, defense systems, and mission-critical infrastructure.

Works in two modes — full codebase scan during development, diff-first during PR review. Critical findings block the merge. Every issue comes with three fix options, trade-offs included, and working code in your language.

Trigger nasa-dod review · nasa-dod dev review · nasa-dod pr review
Languages C/C++, Python, Go, Rust, Java, JavaScript/TypeScript
Standards NASA Power of Ten · DOD JSF AV · SEI CERT · MISRA · OWASP
Gate P0/Critical blocks merge · 2+ approvals to override on teams

The companion to the review skill above — this one shapes code as you write it, rather than grading it after the fact. Applies the discipline behind flight software (NASA's "Power of Ten") and defense systems (DISA STIGs, CERT Secure Coding, NIST SSDF) to everyday production work, with TDD as the non-negotiable baseline: no production code without a failing test first.

Trigger Writing production code · reviewing a PR · refactoring safety-critical systems · setting standards for a new project
Discipline TDD as the iron law — write the failing test, then the minimum code to pass, then refactor
Rules Bounded loops · short functions · assertion density · minimal scope · input validation
Standards NASA Power of Ten · DISA STIGs · CERT Secure Coding · NIST SSDF

Assembles a five-role engineering team inside any repository — PM, Developer, QA, Security, and DevOps. Each agent has a distinct persona, scope, and responsibilities. They coordinate through a shared memory system and a rolling pipeline that keeps work moving without bottlenecks.

The PM creates a phased plan with explicit gate criteria. The Dev agent implements using TDD and self-reviews with the NASA/DOD Code Review skill before handoff. QA and Security review each completed task while Dev moves forward. DevOps handles CI/CD, infra, and produces the final readiness gate before anything ships.

Trigger init agent team · agent team · agent team status
Roles PM · Dev · QA · Security · DevOps
Pipeline Rolling — Dev never blocks waiting on review
Gate P0/P1 findings block task close · phase gates before advancing

Produces a structured Markdown analysis of any piece of code — function breakdowns, data flow, dependencies, and test case analysis — within a strict 2-minute time budget. Emits live status updates as it works so you always know where it is.

Covers purpose, parameters, return values, side effects, error conditions, and edge cases. Saves the result as <filename>_analysis.md when file tools are available. Designed for developers who need to quickly understand code they didn't write.

Trigger "analyze this code" · "explain what this does" · "document this function" · pasting code with no explanation
Output Structured Markdown: overview, function breakdown, data flow, dependencies, test cases
Time budget 120 seconds — pauses and asks to continue if the limit is reached
Tone Plain language for developers who didn't write the code

Reads an entire codebase and produces a multi-document specification suite thorough enough that an engineer — or an AI agent — can reimplement the whole thing in a different language with no access to the original source.

Works in five phases: orientation, ambiguity resolution, module-by-module analysis, cross-cutting concerns, and delivery. Outputs a spec/ directory with numbered documents covering architecture, requirements, assumptions, limitations, data models, API contracts, per-module deep-dives, and cross-cutting concerns (auth, error handling, logging, concurrency, security). Designed for large codebases (100+ files) but works at any scale.

Trigger "write a spec for this codebase" · "document this project" · "I want to migrate this" · "reverse engineer this"
Output spec/ directory — 00_overview.md through NN_cross_cutting.md
Scale Designed for 100+ file codebases; works at any size
Gate Reimplementation completeness checklist before delivery

Challenges a request, design, plan, or position by actively hunting for logical gaps, hidden assumptions, missed edge cases, and unconsidered counter-framings — in a tone that's friendly yet firm. Doubles as a general-purpose debate partner for any topic, technical or not.

Triages every exchange as low-stakes or high-stakes first, and that single call drives everything downstream: how many rounds of pushback it runs, how direct its tone gets, and whether it replies in structured findings or natural conversation. It's advisory only — it never blocks anything, and it never re-raises a concern you've already closed.

Trigger "play devil's advocate" · "poke holes in this" · "challenge my thinking" · "steelman the other side" · any general debate request
Categories Logical/reasoning gaps · hidden assumptions · missed edge cases · counter-framings
Pushback 1 mention (low-stakes) · up to 3 rounds (high-stakes), then defers either way
Output Conversational prose (low-stakes/debate) · structured findings list (high-stakes/design review)

🔧 Installation

Claude Code

Global install
git clone https://github.com/codered/ai ~/.codered

Add to ~/.claude/CLAUDE.md:

Skills are available at ~/.codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.
Per-project install
git clone https://github.com/codered/ai .codered

Add to CLAUDE.md in your project root:

Skills are available at .codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.

Cursor

Global install
git clone https://github.com/codered/ai ~/.codered

Add to ~/.cursor/rules/codered.mdc:

Skills are available at ~/.codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.
Per-project install
git clone https://github.com/codered/ai .codered

Add to .cursor/rules/codered.mdc in your project root:

Skills are available at .codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.

GitHub Copilot

git clone https://github.com/codered/ai .codered

Add to .github/copilot-instructions.md:

Skills are available at .codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.

Gemini CLI

git clone https://github.com/codered/ai ~/.codered

Add to ~/.gemini/GEMINI.md:

Skills are available at ~/.codered/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.

Any agent

If your agent reads a context file — AGENTS.md, system-prompt.txt, .cursorrules, or anything else — add this:

Skills are available at <path>/skills/. When asked to use a skill,
load and follow the SKILL.md in the relevant skill folder.

Use the path that matches where you cloned the repo.

Tip

Not sure which file your agent reads? Check its documentation or look for AGENTS.md, CLAUDE.md, or .cursorrules in your project root.


💡 How skills work

Each skill is a folder inside skills/. When you invoke a skill by name, your agent loads the SKILL.md in that folder — a YAML frontmatter block (name, description) followed by the instructions — and follows it from that point forward. Companion files referenced inside are loaded as needed during execution.

skills/
└── nasa-dod-code-review/
    ├── SKILL.md               ← agent entry point (frontmatter + instructions)
    ├── standards-sources.md   ← fetched at runtime
    ├── reviewer-prompt.md     ← analysis instructions
    ├── severity-guide.md      ← P0–P3 classification
    ├── codeowners-template.md ← first-run setup
    └── report-template.md     ← output format

Skills are plain markdown. They work because agents are good at following clear written instructions — and plain text is easy to read, version, improve, and contribute to.


🧭 Philosophy

One skill, one job. Each skill does exactly one thing well. No skill depends on another, and none require a specific agent or platform.

Blocking is an act of care. A critical finding that stops a bad merge is worth more than a report that gets ignored. Skills that have gates, have them for a reason.

Actionable over advisory. Every finding comes with working code, not just a rule number.

Quality over quantity. Skills ship when they're ready — tested against real codebases, reviewed, and held to a high standard of clarity.


🤝 Contributing

Contributions are welcome. A few things before you start:

  • Open an issue first for new skills so we can align on scope
  • New skills should follow the structure in skills/nasa-dod-code-review/ — a SKILL.md with frontmatter as the agent entry point, companion files for anything that would bloat it
  • Test with at least two agents before submitting a PR
  • No vague instructions — if a step could be interpreted two ways, pick one and make it explicit
git checkout -b skill/your-skill-name
# build, test, then open a PR

⭐ Show your support

If these skills save you time or catch a bug before it ships, consider leaving a star. It helps others find the project.


📄 License

MIT — see LICENSE for details.