Loading...
Loading...
Found 115 Skills
17 developer utilities via MCP — base64, UUID, hash, JWT decode, cron, timestamps, JSON, regex. Use for common dev utility tasks.
Use when editing, reviewing, or auditing DRF viewsets and serializers in PostHog. Triggers on files in posthog/api/, products/*/backend/api/, products/*/backend/presentation/, or any file importing rest_framework serializers or viewsets. Covers OpenAPI spec quality, field typing, schema annotations, and DRF best practices that flow through the type pipeline to generated TypeScript types and MCP tools.
Create and manage prompt snippets — reusable text blocks referenced inside AI Config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
Multi-agent orchestration workflow for deep research: Split a research objective into parallel sub-objectives, run sub-processes using Claude Code non-interactive mode (`claude -p`); prioritize installed skills for network access and data collection, followed by MCP tools; aggregate sub-results with scripts and refine them chapter by chapter, and finally deliver "finished report file path + summary of key conclusions/recommendations". Applicable scenarios: systematic web/data research, competitor/industry analysis, batch link/dataset shard retrieval, long-form writing and evidence integration, or scenarios where users mention "deep research/Deep Research/Wide Research/multi-agent parallel research/multi-process research".
Use when committing code, managing branches, pushing to remote, creating pull requests, or performing version control operations. Conforms to packages/shared/schemas/skill-routing-value-standard.md.
Safely fills web forms in Chrome with user approval and verification at every step. Use when asked to "fill this form", "complete the form for me", "fill out registration", "submit this application", or when user needs form automation with safety controls. Works with Chrome browser tabs via MCP tools (tabs_context_mcp, read_page, form_input). Enforces permission workflows, field verification, and never fills sensitive data.
Control Sonos speakers through MCP tools - search and play music, manage queue and playlists, adjust volume. Use when users request music playback, mention artists/songs/albums, want to control Sonos speakers, manage playlists, or ask about what's playing.
Perses variable lifecycle management: create Text and List variables at global, project, or dashboard scope. Handle variable chains with dependencies (A depends on B depends on C). Supports 14+ interpolation formats. Uses MCP tools when available, percli CLI as fallback. Use for "perses variable", "dashboard variable", "perses filter", "add variable". Do NOT use for datasource management (use perses-datasource-manage).
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.
Design and manipulate Pencil (.pen) files using MCP tools. Use this skill when (1) creating UI screens, dashboards, or layouts in .pen format, (2) reading or modifying existing .pen designs, (3) working with design system components, (4) generating code from .pen files, or (5) understanding PEN file structure, tokens, or schema.
Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding --dangerously-skip-permissions, or analyzing what permissions a project needs. Reads session logs to extract Bash commands and MCP tools actually used, then generates appropriate allow/deny rules.