Build and manage trusted local Paseo plugins. Use when the user asks to create, edit, install, reload, enable, disable, remove, or troubleshoot a Paseo plugin; add lifecycle hooks; transform agent configuration, environment, MCP servers, or workspace creation; automate permissions or turn follow-ups; add a screen, sidebar header or footer item, or workspace panel; add Command Center items or slash commands; add composer pills or attachment sources; transform, render, or append agent timeline items; contribute a theme; use Paseo from plugin code; or add plugin RPCs.

Use when writing, debugging, or configuring an omp hook or extension — blocking or rewriting tool calls, redacting tool output, reshaping LLM context, registering tools/commands, or wiring modules through config.yml. Covers ExtensionAPI (current) vs HookAPI (legacy), the event catalog, discovery and load order, and disable controls. Not for Claude Code hooks (~/.claude/settings.json) or the shared harness safety guard (~/.agents/harness/hooks/).

EU AI Act (Regulation (EU) 2024/1689) compliance advisor — risk classification across all four tiers, all 9 prohibited practices (Art. 5, including the nudification/CSAM prohibition from Dec 2, 2026), all 8 Annex III high-risk use case areas, provider and deployer obligations (Arts. 9–17, 26), GPAI model obligations including the July 2025 Code of Practice (Arts. 51–55), conformity assessment and CE marking (Arts. 43–48), EU AI database registration, Art. 50 transparency (chatbots, synthetic media, AI-generated content), governance (AI Office, AI Board), penalties (Art. 99), confirmed phase-in timeline (Digital Omnibus, Reg. (EU) 2026/1744, in force July 27, 2026: Annex III deferred to Dec 2, 2027; Annex I to Aug 2, 2028), and cross-framework mapping to ISO 42001, NIST AI RMF, and GDPR. Use for any EU AI regulation, AI system classification, or AI compliance question. Current as of November 2026. GPAI enforcement active: Art. 91 information requests reported since Aug 2026 (procedures: Reg. (EU) 2026/1755).

Find weak, dead or misleading tests in the carnival and file a GitHub issue for each one worth repairing. Use when running the test health maintenance loop, or when asked whether the tests actually check what they claim to. Files issues only; never changes code or tests.

Prepare a local LangBot development and testing environment for an AI agent. Use when setting up WSL or Linux development, shared local URL variables, proxy variables, backend/frontend startup, Playwright MCP browser access, GitHub OAuth browser login, persisted Chrome profiles, or future Codex computer-use environment paths.

Use when creating camera movement, cinematic angles, or motion prompts for AI video generators like Runway Gen-3, Kling, and Luma. Compiles narrative prose into a strict 7-slot camera motion contract.

Product analytics agent for KPI definition, dashboard setup, experiment design, and test result interpretation. Use when a product question needs numbers — e.g., defining activation/retention KPIs and a dashboard spec for a new feature, or sizing an A/B test and judging whether the result is significant enough to ship.

Reviews staged git changes against Karpathy's 4 coding principles. Runs complexity_checker on changed files, diff_surgeon on the diff, and produces a verdict with specific fix recommendations. Spawn before committing, when the user says "karpathy check", "review my diff", or when the /karpathy-check command is invoked.

Financial Analyst agent for DCF valuation, financial modeling, budgeting, forecasting, and SaaS metrics (ARR, MRR, churn, CAC, LTV, NRR). Orchestrates finance skills. Spawn when users need financial analysis, valuation models, budget planning, ratio analysis, SaaS health checks, or unit economics projections.

Use when the user shares a course syllabus or outline and wants supplementary readings. Groups topics with topic_grouper.py, finds recent peer-reviewed papers and writes a .docx with summaries and discussion questions.

Find weak, dead or misleading tests in the carnival and file a GitHub issue for each one worth repairing. Use when running the test health maintenance loop, or when asked whether the tests actually check what they claim to. Files issues only; never changes code or tests.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Architecture review covering spec compliance, automated checks, independent file analysis, and suggestions for improving the checks themselves. Use when asked to review the codebase or check for architectural violations.

Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.

Save, back up, or share the current project on Cursor — creates a repo (a saved, versioned copy that isn't public) even for users who have never used git, handling all setup automatically. Use when the user asks to save, back up, publish, or share their project on Cursor, or how to not lose it.

Sync the current project's knowledge into the Obsidian wiki. Use this skill from any project when the user says "update wiki", "sync to wiki", "save this to my wiki", "update obsidian", or wants to distill what they've been working on into their knowledge base. This is the cross-project skill that lets you push knowledge from wherever you are into the vault.

Python package and project management with UV. Use when creating Python scripts, initializing projects, or managing dependencies.

Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X into my wiki", "file a deep dive on Z in the wiki", "autonomous wiki research on X", or wants comprehensive, web-sourced knowledge on a topic filed directly into their wiki.

Prepare, submit with user authorization, and check municipal reports at avisos.madrid.es. Use for Avisos Madrid, reporting street defects, cleaning, lighting or urban equipment in Madrid city, and requests for new street elements. Not for other municipalities, emergencies, or general administrative appeals.

Ensures proper Python dependency management, avoiding global `pip install` and adhering to project-specific tooling. Use this skill if any of the following are true: 1. Attempting to run `pip install {package_name}`. 2. Python packages or dependencies need to be added or modified. 3. Initiating a new Python project. 4. Creating a new notebook, even if just using BigQuery cells. 5. Generating Python code that includes `import` statements for third-party libraries. 6. Before executing Python scripts via the terminal to ensure the correct virtual environment is active.