Decompose a top-line metric into a quantified metric tree with mathematical relationships, size each node, and identify where the real leverage is. Use when a PM needs to understand what drives a metric, where to focus, or where NOT to focus.

Step up a layer of abstraction to map how unfamiliar code fits into the larger system. Use when the user says "zoom out", "bigger picture", "I don't know this area", "give me a map", "where does this fit", is reading code and feels lost, or is about to change unfamiliar code.

Inspect Sentry issues, summarize production errors, and pull health data via the Sentry API (read-only). Use when user says "check Sentry", "what errors in production?", "summarize Sentry issues", "recent crashes", or "production error report". Requires SENTRY_AUTH_TOKEN. Do NOT use for setting up Sentry SDK, configuring alerts, or non-Sentry error monitoring.

Astro-specific performance optimizations for 95+ Lighthouse scores. Covers critical CSS inlining, compression, font loading, and LCP optimization. Use when optimizing Astro site performance, improving Astro Lighthouse scores, or configuring astro-critters. Do NOT use for non-Astro sites (use perf-web-optimization or core-web-vitals) or running Lighthouse audits (use perf-lighthouse).

When the user wants to price an AI product, choose a charge metric, design pricing tiers, or optimize margins. Also use when the user mentions 'AI pricing,' 'usage-based pricing,' 'consumption pricing,' 'outcome pricing,' 'BYOK,' 'bring your own key,' 'per-seat pricing,' 'pricing tiers,' 'AI margins,' 'cost per token,' or 'pricing model.' This skill covers pricing strategy, packaging, and margin management for AI-native products. Do NOT use for technical implementation, code review, or software architecture.

AI frontend specialist and design consultant that guides users through a structured discovery process before generating any code. Collects visual references, design tokens, typography, icons, layout preferences, and brand guidelines to ensure the final output matches the user's vision with high fidelity. Use when the user asks to build, design, create, or improve any frontend interface — websites, landing pages, dashboards, components, apps, emails, forms, modals, or any UI element. Also triggers on "build me a UI", "design a page", "create a component", "improve this layout", "make this look better", "frontend", "interface", "redesign", or when the user provides mockups, screenshots, or design references. Do NOT use for backend logic, API design, database schemas, or non-visual code tasks.

Address review and issue comments on the open GitHub PR for the current branch using gh CLI. Use when user says "address PR comments", "fix review feedback", "respond to PR review", or "handle PR comments". Verifies gh auth first and prompts to authenticate if not logged in. Do NOT use for creating PRs, CI debugging (use gh-fix-ci), or general Git operations.

Use when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that require real-time input/output - provides tmux-based approach for controlling interactive sessions through detached sessions and send-keys

Extracts human-readable pseudocode from a verified formal artifact (Dafny, Lean, TLA+) while preserving the verified properties as annotations, so the proof-carrying logic can be reimplemented in a production language. Use when porting verified code to an unverified target, when documenting what a formal spec actually does, or when handing a verified algorithm to an implementer.

TLA+-specific instance of model-guided repair — reads a TLC error trace, identifies the enabling condition that should have been false, strengthens the corresponding action, and maps the fix to source code. Use when TLC reports an invariant violation or deadlock and you have the code-to-TLA+ mapping from extraction.

Dispatch skill — routes a formal specification request to the right concrete generator based on what's being specified and what needs to be proven. Use when the user asks to formally specify something without naming a target formalism, or when unsure which verification tool fits the problem.

Converts a model checker counterexample trace into an executable test case in the source language, so the bug found in the model is reproducible (and regression-guarded) in the real code. Use when TLC/NuSMV/Spin finds a violation and you want a failing test before writing the fix.

Generates test oracles — the "expected output" part of a test — by choosing among reference implementations, invariants, inverse functions, or differential comparison when the correct answer isn't obvious. Use when the hard part of testing is knowing what the right answer is, not generating inputs.

Generates domain-specific mutation operators beyond the standard arithmetic/relational set — mutations tailored to your codebase's idioms, APIs, and bug history that standard tools don't try. Use when generic mutation testing plateaus, when your domain has specific failure modes, or when mining bug history reveals patterns standard operators miss.

Generates tests that mock external dependencies — HTTP, databases, filesystems, clocks — isolating the unit under test while still exercising realistic interactions. Use when the code has side effects you can't run in a test, when external services are slow or unavailable, or when testing error paths that are hard to trigger for real.

Translates natural-language requirements into formal constraints — logical predicates, schemas, or property-based test generators — that a machine can check. Use when turning a spec into validation code, when writing property tests, or as the bridge between requirements and formal verification.

Recognizes structural situations that match known design patterns and recommends whether to apply them — or explains why the pattern doesn't fit. Use when the user has a structural problem and is considering a pattern, when reviewing a design that uses a pattern questionably, or when the user asks which pattern fits their situation.

Analyze and optimize React component performance issues (slow renders, re-render thrash, laggy lists, expensive computations). Use when asked to profile or improve a React component, reduce re-renders, or speed up UI updates in React apps.

Look up VoltAgent documentation embedded in node_modules/@voltagent/core/docs for version-matched docs. Use for API signatures, guides, and examples.

Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check security alerts, manage variable groups, approve deployments, or configure branch policies. Covers 13 domains with 99 tools via REST API.