caro: fast Rust CLI that turns natural‑language tasks into a safe POSIX command. Built for macOS (MLX/Metal) with a built‑in model; supports vLLM/Ollama/LM Studio. JSON‑only output, safety checks, confirmation, multi‑step goals, devcontainer included.
This repository also configures its own agents. See what caro tells them →
Skill Claude CodeCodex
Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree lifecycle, auto-commit behavior, merge execution, and the safe-commit pattern. Triggers: "how does spec-kitty use git", "worktree management", "auto-commit", "who commits what", "git…
Skill Claude CodeCodex
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 5-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…
Skill Claude CodeCodex
Auto-commit changes after a Spec Kit command completes.
Skill Claude CodeCodex
Create a feature branch with sequential or timestamp numbering.
Skill Claude CodeCodex
Initialize a Git repository with an initial commit.
Skill Claude CodeCodex
Detect Git remote URL for GitHub integration.
Skill Claude CodeCodex
Validate current branch follows feature branch naming conventions.
Skill Claude Code
AI-powered marketing engineering skill based on Alon Huri's framework. Transforms marketing from copywriting to engineering discipline through 10 agentic mechanisms: infinite creative generation, adaptive budget management, LTV signal hunting, contextual data layers, AEO optimization, dynamic quizzes, behavior-driven…
Skill Claude Code
AI engineering skill for prompt optimization, context inference, and intelligent command routing across different models and use cases.
Skill Claude Code
Guide for integrating safety validation into new inference backends.
Skill Claude Code
Suggests which benchmarks to run based on code changes.
Skill Claude Code
Use when fixing issues identified in beta tester feedback. Guides systematic root cause analysis, worktree-based fixes, regression testing, and release preparation. Invoke with structured beta reports or issue lists.
Skill Claude Code
This skill should be used when the user asks to "run beta test cycle", "run next cycle", "test static patterns", "analyze test failures", "improve pass rate", or wants to systematically improve command generation quality through iterative testing and pattern refinement. Provides structured workflow for running test…
Skill Claude Code
Build, render, ship, AND MAINTAIN the caro landing-page demo video using Remotion. Use when creating, updating, re-rendering, extending the project demo MP4 at website/public/caro-demo.mp4 — or when responding to a drift alert from the caro-demo-drift CI workflow or a beads task with label caro-demo-video.
Skill Claude Code
Document leftover tasks as GitHub issues with full correlation to branch, PR, and original work plan. Use when ending a session with incomplete work that another agent should pick up.
Skill Claude Code
Scaffold a new CaroML task file (.caro) from a natural-language description. Use this when the user wants to create a repeatable shell task that Caro will validate, generate, and maintain over time. Triggers on requests like "make a CaroML task that...", "scaffold a runbook for...", "create a .caro file for...", or…
Skill Claude Code
DEPRECATED 2026-05-16 — use caro-shell instead. This skill recommends the --backend claude flag and a /.config/caro/config.toml path that do not work on the current caro 1.4.0 binary, and its 522-line educational body is 4× the size of caro-shell for no benefit to an agent. Will be removed after 2026-08-01.
Skill Claude Code
Use this skill when the user needs a POSIX shell command synthesized from natural language — "how do I find/grep/awk/find files modified in the last hour", "kill the process on port 3000", "tar this up excluding .git", or any other terminal-task-as-prose. Shells out to the caro CLI for safety-validated command…
Skill Claude Code
Use this skill to run a structured user-discovery interview for Caro and save the transcript into docs/discovery/transcripts/ under the project's anonymization rules. Use when a new product line or major feature spec needs to clear Gate 1 of .claude/rules/validation-discipline.md (the 20-transcripts rule). Also use to…
Skill Claude Code
Safely reclaim disk space in the caro project. Cleans Rust build cache, stale git worktrees (both .claude/worktrees/ and .worktrees/), empty stubs, and nodemodules using a tiered audit that preserves any worktree with uncommitted changes, missing remotes, or a lock file. Use when du shows the project > 30 GB or disk…
Skill Claude Code
Maintainer skill to draft a CVE rule YAML via Nimble for a specific CVE, fill pattern + testcases, and open a PR. Used off-cycle when a 0day lands between weekly cron runs.
Skill Claude Code
CISO & Product Manager skill providing security-focused product vision, risk assessment, and strategic guidance for caro development.
Skill Claude Code
Create or update continuity ledger for state preservation across clears.
Skill Claude Code
Create handoff document for transferring work to another session.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: