caro

Run the pragmatic-skeptic 'ponytail' reviewer over the current diff to surface over-engineering — code, abstractions, dependencies, files, or process steps the problem does not need. Read-only and advisory; never trims safety, security, accessibility, data-loss handling, or their tests. Use before pushing a PR, when a change feels heavier than the task warranted, or when boilerplate/a new dependency crept in. Triggers: 'ponytail review', 'is this over-engineered', 'what can I delete here', 'did I over-build this'.

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 synthesize transcripts into the hypothesis ledger after each batch of 5 interviews. Triggers - "run a discovery interview for <feature>", "log this user conversation as a Caro discovery transcript", "synthesize this week's transcripts into the hypothesis ledger".

Safely reclaim disk space in the caro project. Cleans Rust build cache, stale git worktrees (both .claude/worktrees/ and .worktrees/), empty stubs, and node_modules 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 free is low.

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.

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 inference and presents the suggestion for explicit approval. Refuses to execute the command itself.

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`.

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 invocations of `/caro new <name>`.

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 workflow", "merge workflow", "rebase WPs", "worktree cleanup", "safe commit". Does NOT handle: runtime loop advancement (use runtime-next), setup or repair (use setup-doctor), mission selection (use mission-system).

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. Triggers: "what missions are available", "how do missions work", "which mission should I use", "explain the mission system", "what is a mission", "change the mission", "mission templates", "step contracts", "action index", "mission procedures". Does NOT handle: runtime loop advancement (use runtime-next), setup or repair (use setup-doctor), governance (use charter-doctrine), or glossary curation (use glossary-context).

Maintainer skill to draft a CVE rule YAML via Nimble for a specific CVE, fill pattern + test_cases, and open a PR. Used off-cycle when a 0day lands between weekly cron runs.

Identify misplaced files and organize project structure following open-source best practices, while delegating refactoring to specialized skills

AI engineering skill for prompt optimization, context inference, and intelligent command routing across different models and use cases

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 activation, personalized video at scale, competitor weakness targeting, and active churn prevention. Use when building marketing automation systems, designing growth engineering workflows, creating AI-powered marketing agents, optimizing ad creatives at scale, implementing AEO (Answer Engine Optimization), or architecting data-driven marketing infrastructure.

CISO & Product Manager skill providing security-focused product vision, risk assessment, and strategic guidance for caro development

Cadence-driven work moderation and recomposition system that discovers unfinished, fragmented, and drifting work across the codebase and collaboration surfaces, then recomposes it into coherent, schedulable units of work aligned with the roadmap and spec-driven development.

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.

Verify debug/dev artifacts are removed before commit. Use at session end to apply 'good boy scout' rule - leave code cleaner than you found it.

Suggests which benchmarks to run based on code changes

Improve embedded LLM system prompt based on evaluation test failures

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.

Guide for integrating safety validation into new inference backends

Systematic audit of safety patterns to identify gaps, regressions, and improvement opportunities

Guide through TDD process for adding new safety patterns - from threat identification to commit

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 cycles, analyzing failures, implementing fixes, and documenting results.

Quality Engineer Manager skill for orchestrating release validation, beta testing coordination, feedback analysis, and release sign-off decisions

Use when users need to simulate unbiased beta testers for CLI tools. Creates tester personas, models their environment, and runs terminal-first exploratory testing based only on documentation and observed terminal output.

Validates code changes against the project's consolidated knowledge and configuration rules. Use on push to catch violations of agreed-upon standards like installation scripts, linking patterns, and configuration consistency.

Expert on multicultural heritage traditions, holidays, and celebrations. Use for maintaining holiday theme features, adding new cultural events, ensuring cultural sensitivity, and managing the data-driven holiday configuration system

Analyze brownfield codebase and create initial continuity ledger