jhd3197

Add new REST API endpoints to CachiBot's FastAPI backend following the project's conventions. Use this skill when adding API routes, endpoints, or REST resources — e.g., "add an API for reminders", "create a CRUD endpoint for bookmarks".

Create new frontend views and components for CachiBot's React+TypeScript UI with Zustand state management. Use this skill when building new pages, views, panels, or major UI components — e.g., "add a dashboard view", "create a logs panel", "build a new settings tab".

Add a complete full-stack entity to CachiBot spanning database table, repository, Pydantic models, API routes, TypeScript types, API client, and Zustand store. Use this skill when adding a new data entity or resource that needs persistence and CRUD across the entire stack — e.g., "add bookmarks", "add a reminders system", "create a templates feature".

Create new CachiBot agent plugins (tools) following the project's capability-gated plugin architecture. Use this skill when adding a new tool, capability, or plugin to the CachiBot agent system — e.g., "add a translate tool", "create a web scraping plugin", "add a new capability".

Add new WebSocket message types and event handlers to CachiBot's real-time streaming system. Use this skill when adding new real-time events, live updates, or bidirectional WebSocket communication — e.g., "add live progress events", "stream file upload status", "add approval request events".

Generate a pull request title and description from the current branch's commits. Produces a concise summary, optional feature highlights, and collapsible technical details.

Run a full-codebase audit of CachiBot using 8 parallel review agents (DRY, Security, API, Data, Frontend, Tests, State, Observability). Each agent reports findings with file paths and line numbers, compiled into a dated report.

Run all project linters (ruff check, ruff format, mypy, eslint) and auto-fix every violation. Fixes line-length, type annotations, unused vars, and formatting in one pass.

Update LLM model pricing in Prompture. Pricing resolves through a pluggable source registry — by default local KB JSON files (primary, curated) then models.dev (fallback). Use when model prices change, new models launch, models.dev data is stale, or you need to add a custom pricing source.

Scaffold a new LLM provider driver for Prompture. Creates sync + async driver classes, registers them in the driver registry, adds settings, env template, setup.py extras, package exports, discovery integration, and models.dev pricing. Use when adding support for a new LLM provider.

Create a new Prompture usage example script. Follows project conventions for file naming, section structure, docstrings, and output formatting. Use when demonstrating extraction use cases or provider integrations.

Create reusable persona system prompts for Prompture. Covers Persona dataclass, template variables, composition, trait registry, global registry, serialization, and Conversation integration. Use when defining system prompts for extraction or agent behavior.

Add function-calling tools to Prompture agents. Covers ToolDefinition, ToolRegistry, tool_from_function, decorator patterns, serialization formats, and Conversation integration. Use when adding callable tools for LLM function calling.

Add predefined field definitions to the Prompture field registry. Handles field structure, categories, template variables, enum support, and thread-safe registration. Use when adding reusable extraction fields.

Add unit and integration tests for Prompture functionality. Uses pytest conventions, shared fixtures from conftest.py, and the integration marker pattern. Use when writing tests for new or existing features.

Run Prompture's test suite with the correct pytest flags. Supports unit-only, integration, single file, single test, verbose, and credential-skip modes. Use when running or debugging tests.

Scan LESS stylesheets for variable errors — undefined variables, CSS custom properties passed to compile-time functions (fade, darken, lighten, etc.), and incorrect variable name patterns. Reports issues with file, line, and fix.

Generate a pull request title and description from the current branch's commits. Produces a concise summary, optional feature highlights, and collapsible technical details.

Scan backend services for subprocess bugs — missing sudo, missing exception handling on distro-specific commands, raw subprocess calls bypassing system utilities, and container/environment assumptions that break in LXC or restricted environments. Reports issues with file, line, and fix.

Inspect the ServerKit SQLite database — show tables, schemas, row counts, and run queries. Runs via WSL for local dev or SSH MCP for production. Use when debugging data issues or understanding the current database state.

Deploy ServerKit to the production server via SSH. Runs update, rebuilds frontend, restarts services, and performs health checks. Use when pushing changes to production.

Scaffold a new full-stack feature for ServerKit with Flask backend (model, service, API blueprint) and React frontend (page, styles, route). Use when creating new modules, pages, or API endpoints.

Manage After Effects from Claude — create configs, build compositions, render videos, diagnose issues, and optionally generate AI content via Prompture

Create and validate JSON automation configs for the After Effects automation pipeline

Add methods to existing mixins or create new mixins for the After Effects automation client

Write unit tests following the project's existing patterns and conventions

Create ExtendScript/JSX files that integrate with the Python-to-AE file-based command bridge