Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.

Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop", "Electron alternative", "Tauri vs native", "WebView wrapper", "near-native performance", "Raycast architecture", "WebKit/WebView2 quirks", "WKWebView", "system tray app", "global hotkey app", "launcher app". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.

Git-native worktree management via a bundled single-file CLI - create, list (with per-worktree git stats), and safely tear down isolated checkouts under .worktrees/ for parallel workstreams. Use when the user or an orchestrating skill wants to "create a worktree", "work on this in a separate worktree", "spin up an isolated checkout", "list my worktrees", "clean up / remove a worktree", or invokes $prp-worktree.

Use when deciding whether to exit after achieving major success to avoid becoming a threat. Based on Fan Li's departure from Yue: recognize danger signals ('when birds are gone, the bow is hidden'), assess your superior's character, resign formally, and leave completely with portable wealth.

Inspects a project's installed node_modules and produces three reports: duplicated packages (installed in multiple versions), packages sorted by install size, and maintenance actions (dep-upgrade opportunities + publint findings, grouped by consumer/author). Use when the user wants to audit dependencies, find duplicate packages, check what's taking up disk space in node_modules, identify outdated peer/prod dependencies that newer dependents could upgrade past, or list publint problems. Available as a CLI (`npx node-modules-inspector report <duplicates|sizes|maintainers> [--json]`) or an MCP stdio server (`npx node-modules-inspector mcp`) exposing the same three reports as agent tools. Works with pnpm, npm, and bun.

Code-quality standards for RedisInsight: TypeScript strictness, naming conventions (camelCase, PascalCase, UPPER_SNAKE_CASE), linting rules, no `any` without reason, no `!important` in styles, and constant extraction. Use when writing or refactoring any TypeScript/JavaScript code in this repo, when ESLint or Prettier issues come up, or when the user mentions code style, lint, naming conventions, or general code quality.

Build applications with React Router in Framework, Data, Declarative, and unstable RSC modes. Use when configuring routes, route modules, loaders, actions, forms, fetchers, navigation, pending UI, SSR/SPA/pre-rendering, middleware, URL params/search params, or React Router upgrades.

Pick the right y-axis unit when creating or updating an insight via `posthog:insight-create` or `posthog:insight-update` — both TrendsQuery (`trendsFilter.aggregationAxisFormat`) and SQL insights (`DataVisualizationNode`, `chartSettings.yAxis[].settings.formatting`). Use when the agent is about to add a `formula` purely to convert units (e.g. dividing seconds by 60 to display minutes), when a `math_property` or SQL column is a duration, currency, ratio, or large count, or whenever the user mentions "format the y-axis", "duration", "seconds", "minutes", "hours", "milliseconds", "ms", "percentage", "%%", "currency", "decimals", "axis label", or "axis unit" in the context of a graph insight.

Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, paused, exposure frozen, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.

Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP. Use when a user asks to create a dashboard, put several metrics/charts together on one page, assemble a dashboard for a topic (product analytics, retention, revenue, activation, etc.), or add/remove/replace insights on a dashboard they already have. Covers deciding create vs update, reusing existing insights vs creating new ones, and using PostHog's vetted dashboard templates as reference for what a strong dashboard on a topic looks like.

Starts, connects to, and troubleshoots a PostHog devbox, a remote Coder workspace for PostHog development that can also run the full stack, through `hogli devbox:*` commands. Use when asked to spin up or resume a devbox, open a shell or editor on it, run a command on it, mirror a local checkout to it (devbox:sync), run the PostHog app on it and share a link, clone, update, share, or free disk on a devbox, store gh or Claude Code tokens for it, or diagnose a failing devbox command (tailnet, DNS, Coder CLI version, SSH). Not for running the stack on the local machine or for changing the Coder template in posthog-cloud-infra.

Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before reporting a task done, or after editing Python, serializers, migrations, workflows, or dependency manifests — to avoid burning a CI matrix on a failure you could catch locally (formatting, lint, broken lockfiles, OpenAPI drift, migration conflict, stale branch). Trigger terms: ci:preflight, preflight, pre-push checks, pre-push hook failed, "will this break CI".

How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same way customers do. Use when adding application metrics in this monorepo (web, Celery, Temporal), when asked to push or ship metrics into posthog metrics, or when unsure whether the SDK in this environment supports posthog.metrics yet. Covers the environment decision (SDK-first per the public docs, OTel fallback when the SDK path is not available), the exact version gates per SDK, what is already wired internally, and how to validate metrics actually arrive.

Triage, verdict, and reply to automated PR review comments from GitHub Copilot and Greptile, then iterate until the bots have nothing left to say. Use this whenever a pull request has feedback from Copilot or Greptile and the user wants those comments handled — e.g. "deal with the bot review comments", "address the Copilot/Greptile feedback on my PR", "go through the review bots", "resolve the automated review", or after pushing a branch and asking to "clear the AI reviewers". It judges each comment on its merits (fixing real issues, pushing back on nitpicks), replies inline on each thread, commits and pushes fixes, re-requests review from both bots, waits for the fresh round, and repeats until clean.

Write B2B cold emails and follow-up sequences that get replies. Use when the user wants to write cold outreach emails, prospecting emails, cold email campaigns, sales development emails, or SDR emails. Covers subject lines, opening lines, body copy, CTAs, personalization, and multi-touch follow-up sequences.

Audit container images, Dockerfiles, and Kubernetes manifests for misconfigurations, excessive privileges, exposed secrets, and runtime risks. Use when the user mentions 'container security,' 'Docker security,' 'Dockerfile audit,' 'Kubernetes security,' 'K8s security,' 'pod security,' 'container hardening,' 'kubectl audit,' 'image scanning,' 'distroless,' 'rootless containers,' 'pod security policy,' 'pod security standards,' 'PSS,' 'network policy,' 'OPA Gatekeeper,' 'Kyverno,' 'runtime security,' or needs to review container or orchestration security.

Audit, design, and migrate Identity and Access Management — cloud provider IAM (AWS, GCP, Azure), identity providers (Okta, Entra ID / Azure AD, Auth0, Google Workspace), application authorization (RBAC, ABAC, ReBAC), and federated identity. Use when the user mentions 'IAM,' 'identity,' 'access management,' 'least privilege,' 'role design,' 'SSO,' 'SAML,' 'OIDC,' 'OAuth,' 'JIT access,' 'just-in-time access,' 'break-glass,' 'service accounts,' 'RBAC,' 'ABAC,' 'privilege creep,' 'role explosion,' 'identity governance,' 'IAM strategy,' 'identity migration,' 'Okta,' 'Entra ID,' 'Azure AD,' 'Auth0,' 'Cognito,' or needs identity consultant-level guidance.

Run an ASI-Evolve style evaluator-driven search workflow for code, algorithms, prompts, or pipelines. Use when Claude needs to align the objective, scoring, evaluator, writable scope, and cognition first, then execute a preflight-gated learn/design/experiment/analyze loop with the bundled Evolve CLI instead of the repository's multi-agent pipeline.