commit
The `/commit` slash command launches a background subagent that commits staged changes following the ATLAS convention, automatically attributing the commit to the current Claude model without requiring approval. Use this command when you have already staged specific changes and want to create a commit while continuing other work immediately.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/syahiidkamil/Software-Engineer-AI-Agent-Atlas/HEAD/.claude/commands/git/commit.md -o ~/.claude/commands/commit.mdcommit.md
Launch the `commit` subagent **in the background** — call the Agent tool with `subagent_type: commit` and `run_in_background: true`.
Before passing the task, replace `{{CURRENT_MODEL}}` below with **your own current model identity** (from your environment — e.g. `Opus 4.8 (1M context)`). This keeps the commit credit accurate as the model changes, instead of hardcoding a version that goes stale.
Pass it this task:
> Run in **commit (default) mode**. Commit only what is already in the staging area, autonomously — no approval needed. Leave unstaged working-directory changes untouched. If nothing is staged, say so and stop. To stage and commit everything instead, that's `/git:stage-commit`. Follow the ATLAS commit convention, and end the commit message with this trailer verbatim:
> `Co-Authored-By: Claude {{CURRENT_MODEL}} <noreply@anthropic.com>`
Don't block on it: report that the commit agent has been launched in the background and carry on. You'll be notified when it finishes.Activate ATLAS pattern recognition mode. Identify repeated patterns, extract essential characteristics, and create reusable abstractions from concrete examples.
Adversarially review something just built — presume it is broken and find where. Use after implementing a feature, finishing a build, or before shipping, or whenever ATLAS or Boss wants a hostile second opinion on a diff, a running app, or a whole codebase. Spawns clean-context reviewers with opposing lenses (correctness, security, empty-world) and reproduces every finding by running the target before believing it. Distinct from /code-review, which statically reads a diff and never runs the app.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Interview Boss about the project, then reason from first principles to design the ideal ATLAS operating identity/system-prompt for it — free to drop KISS/YAGNI/DRY/clean-architecture entirely when the project (and the LLM's own distribution) calls for a different mindset
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development