Skip to main content
NeVibeCode · repository · 26 items

software-engineer-ai-agent-atlas: a set by syahiidkamil

The syahiidkamil/software-engineer-ai-agent-atlas repository on GitHub: 26 cards with a description and an install command. Inside: 12 commands, 7 skills and 6 subagents and more. They install into Claude Code, Codex and GitHub Copilot.

About the repository

GitHub
syahiidkamil/software-engineer-ai-agent-atlas
Stars
★ 406
Source updated
2026-11-01
In the catalog since
2026-10-30
commit command Runs a background subagent to commit staged Git changes following ATLAS conventions. Useful when you want automated commits without blocking your session. CX Codex +1 ★ 406repo stars stage-commit command The stage-commit command hands working-directory changes to a background commit subagent. Use it to create grouped commits and keep going until Git reports a clean tree. CX Codex +1 ★ 406repo stars learning-from-mistakes skill learning-from-mistakes — a skill that writes a bug or mistake into a separate file after the problem is resolved. Captures the cause, fix, and lesson to avoid repeating the debugging work. CX Codex +1 ★ 406repo stars log command log inspects recent git commits, summarizes their themes, and maps them against uncommitted changes in your working tree. CX Codex +1 ★ 406repo stars create-test-cases command create-test-cases drafts browser-focused manual test cases in Markdown for a project feature or area. Use it to prepare cases for /qa:manual-test-run. CX Codex +1 ★ 406repo stars wireframe command The wireframe command renders a static low-fidelity screen layout into a single HTML file — gray boxes, dashed borders, no libraries. Opens with a double-click. CX Codex +1 ★ 406repo stars commit subagent Creates Git commits autonomously using ATLAS conventions without asking for approval. Handles staged files or splits working changes into clean commits. CX Codex ★ 406repo stars abstraction-power skill The abstraction-power skill guides Claude Code from concrete code examples to reusable models by spotting their shared structure. Use it to examine duplicated logic or shape a system design. CX Codex +1 ★ 406repo stars get-to-know command get-to-know is a Claude Code command that initializes project context by gathering stack, structure, and conventions, creating a project map, and configuring the environment. CX Codex +1 ★ 406repo stars adversarial-review skill adversarial-review subjects fresh builds to hostile inspection using isolated reviewer contexts and mandates empirical reproduction on the running system. CX Codex +1 ★ 406repo stars human-writing skill The human-writing skill guides an agent to shape prose around its language, voice, and format. Use it for articles, posts, headlines, and other writing tasks. CX Codex +1 ★ 406repo stars qa-manual-tester subagent qa-manual-tester takes over a real browser and pokes at your app the way a tester would: clicks, typing, screenshots, console reads. Handy when a feature needs a hands-on pass. CX Codex ★ 406repo stars comparator subagent comparator runs blind comparisons between two AI outputs against the original prompt. Identifies the stronger result without knowing which skill produced each file. CX Codex ★ 406repo stars code-review subagent code-review — a subagent for Claude Code that reviews a pull request through gh and posts a comment listing confirmed bugs. Skips closed, draft, or already-reviewed PRs without prompting. CX Codex ★ 406repo stars change-core-self command change-core-self asks you about the project, works out a fitting identity for the agent from scratch, and stores it as a rule file loaded on every session. CX Codex +1 ★ 406repo stars grader subagent grader assesses agent execution transcripts and generated files against expectations, flags superficial passes, and critiques test assertions. CX Codex ★ 406repo stars create-phase command The create-phase command clarifies a development phase through Q&A, then creates an HTML wireframe with the decisions needed for implementation in Claude Code plan mode. CX Codex +1 ★ 406repo stars visual command The visual command turns a discussion into a self-contained HTML document with diagrams, wireframes and matrices the agent implements from in plan mode. CX Codex +1 ★ 406repo stars oneshotapp command oneshotapp builds a functioning app from a brief idea in Claude Code without human intervention. It logs architecture choices and verifies implementation slices on the fly. CX Codex +1 ★ 406repo stars analyzer subagent analyzer examines blind skill comparisons to explain the winner’s advantage and suggest changes to the losing skill. Run it after the comparator finishes. CX Codex ★ 406repo stars free-will skill free-will makes the agent stop at a costly fork, lay out real options, test each against evidence and pick one on purpose. CX Codex +1 ★ 406repo stars design rule Defines visual identity tokens and styling rationale following Google Stitch. Keeps coding agents aligned with design tokens when building user interfaces. CX Codex +1 ★ 406repo stars prototype command Turn an early idea into a clickable, multi-screen React prototype through an interview. Use it to test a concept before committing to production work. CX Codex +1 ★ 406repo stars create-design-md command create-design-md — a command that produces a DESIGN.md file with the project's visual identity: interviews the user, renders three HTML design variants for browser comparison, locks in the chosen direction in Stitch format. CX Codex +1 ★ 406repo stars super-product-owner skill super-product-owner turns vague product ideas into a one-page brief, an interactive prototype, and concrete acceptance criteria. It narrows project scope before any production code gets written. CX Codex +1 ★ 406repo stars super-ui-ux-design skill The super-ui-ux-design skill guides UI design and critique through UX principles and visual design concepts. Use it when working on websites, apps, or individual components. CX Codex +1 ★ 406repo stars

More in NeVibeCode

Project sponsors

Companies that keep this analytics open