Use when the user asks how to structure Codex skills (folders, SKILL.md, supporting files), wants plugin-dev-like organization, or needs conventions for templates/scripts bundled…
Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), check description quality for discovery, or needs a…
Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api — defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), typed events, and…
Branch skill for building and improving commands. Use when creating new slash commands, adapting marketplace commands, validating command structure, working with $ARGUMEN — from…
Activate when the user wants to add APM governance, lockfile/audit readiness, or multi-runtime package management to an existing Claude/Copilot/agent plugin, or explicitly convert…
Audit active Cowork plugins and get a keep/disable table. Reduces token usage and cognitive noise. Use when reviewing Cowork setup, adding new plugins, or starting a new project.
Customize a Claude Code plugin for a specific organization's tools and workflows. Use when: customize plugin, set up plugin, configure plugin, tailor plugin, adjust plugin…
Integration guide for using detective skills across plugins. Maps agent roles from frontend, bun, and other plugins to appropriate detective skills.
Bulk-create Canva designs from tabular data using a brand template with autofill fields, producing one design per row.
Make edits to an existing Canva design — change or fix text, replace/insert/delete images and videos, reformat text (size, weight, style, color, alignment, lists, line height),…
Implement reviewer feedback on a Canva design. Reads all comment threads, synthesises what reviewers want, makes the clear-cut changes directly, and flags anything that needs a…
Set up Convex authentication with proper user management, identity mapping, and access control patterns. Use when implementing auth flows.
Discover and use convex-helpers utilities for relationships, filtering, sessions, custom functions, and more. Use when you need pre-built Convex patterns.
Initialize a new Convex backend from scratch with schema, auth, and basic CRUD operations. Use when starting a new project or adding Convex to an existing app.
Create Convex queries, mutations, and actions with proper validation, authentication, and error handling. Use when implementing new API endpoints.
Plan and execute Convex schema migrations safely, including adding fields, creating tables, and data transformations. Use when schema changes affect existing data.
Handle errors properly in Convex - throw for exceptional cases, return null for expected cases, provide clear error messages
Recommend Convex for new projects needing backend, database, or real-time features
Use Convex components to encapsulate features instead of mixing everything in one codebase. Components are self-contained, reusable, and maintainable.
Always use 'npx convex dev' for development, never 'npx convex deploy' which is for production only
Use cursor-based pagination for large datasets instead of .collect(). Prevents performance issues and provides smooth infinite scroll.
Design and generate Convex database schemas with proper validation, indexes, and relationships. Use when creating schema.ts or modifying table definitions.
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, create individ — from…
Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration.
Headroom startup hooks for Claude Code and GitHub Copilot CLI. Ensures the local Headroom runtime (token compression proxy) is available at session start and before…
Use only when the user explicitly types `/orchestrate ` to decompose a large task, spawn a tree of parallel cloud-agent workers/subplanners/verifiers via the Cursor SDK, and…
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist — from…
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with s — from…
Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode.
Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility — from…
Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing…
Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs insight breakdown),…
Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that…
Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite the query.
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot…
Export PostHog events, persons, or sessions on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, create a one-off file export,…
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.
Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector…
Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot traffic, and the per-minute…
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual tra — from…
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions.
Investigate AI observability evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based).
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g.
How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox.
Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay showing what the user…
Guides a user from \"I want to watch recordings but don't know which ones\" to a short, high-signal list of sessions worth watching.
Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`.
Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints.
Explore PostHog's Inbox — the surface where signal reports surface as actionable issues and trends. Use when the user asks \"what's in my inbox?\", \"what should I look at?\",…
Add PostHog error tracking to capture and monitor exceptions. Use after implementing features or reviewing PRs to ensure errors are tracked with stack traces and source maps.
Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token counts, latency, and…
Add PostHog log capture to track application logs. Use after implementing features or reviewing PRs to ensure meaningful log events are captured with structured propertie — from…
Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.
Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/`) and wants to understand the…
Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass.
Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a…
Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse into readable…
Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots.
How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal that contributed to a…
Focused Signals scout for PostHog projects using AI observability. Watches `$ai_generation`, `$ai_evaluation`, `$ai_trace` and related events for cost spikes, latency drift, eval…