skills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 79 files.

• acceptance-criteria-doc

  Generate an Acceptance Criteria (AC) live Confluence doc for a Jira epic, following the Assets team's standard structure (Overview, Documentation table, Testing Scenarios table with Given/When/Then criteria and QA sign-off checkboxes), then link it from the epic and its stories. Use this whenever the user asks to create acceptance criteria, ACs, an "AC doc", testing scenarios, or QA sign-off crit…

  domains/assets/skills/acceptance-criteria-doc/skill.md on GitHub (opens in a new tab)

• react-compiler-migration

  Migrate existing files so the React Compiler can optimize them, using react-compiler-marker output as the source of truth. Use when fixing React Compiler bail-outs, working through a react-compiler-marker report, or when the user mentions rcm, compiler failures, "Cannot access refs during render", "Existing memoization could not be preserved", or other compiler diagnostics.

  domains/assets/skills/react-compiler-migration/skill.md on GitHub (opens in a new tab)

• coding-guidelines

  General coding standards for MetaMask client repos: TypeScript-only new code, no `any`, naming, file layout, error handling, and the required- reading and enforcement checklist. Use when writing or refactoring application code, when deciding how to structure a new module, or when checking whether a change meets repo coding standards before opening a PR.

  domains/coding/skills/coding-guidelines/skill.md on GitHub (opens in a new tab)

• controller-guidelines

  Authoring a MetaMask controller: BaseController or not, state metadata (`persist`, `anonymous`, `usedInUi`), `this.update`, the options-bag constructor, typed messenger actions. Use when writing or reviewing a controller, or changing what it persists or exposes to the UI. To wire one in, see `controller-integration`.

  domains/coding/skills/controller-guidelines/skill.md on GitHub (opens in a new tab)

• controller-integration

  Wire a new or existing controller — whether imported from a `@metamask/*-controller` npm package or defined locally in the repo — into the MetaMask Mobile Engine or the MetaMask Extension background. Use this skill when: adding a controller to Engine or to the extension's messenger-client init, creating a controller init function or messenger, delegating actions/events between controllers, adding…

  domains/coding/skills/controller-integration/skill.md on GitHub (opens in a new tab)

• deeplink-handler

  Deeplink handler creation guidelines

  domains/coding/skills/deeplink-handler/skill.md on GitHub (opens in a new tab)

• flaky-test-detection

  Detect, prevent, and fix flaky Jest unit tests in MetaMask Mobile before they reach CI. Use this skill when: reviewing a PR diff or changed test files for flakiness risk, fixing an intermittently failing Jest test, reproducing a flaky test locally, or auditing GitHub Actions history to rank historically flaky unit tests by failure rate.

  domains/coding/skills/flaky-test-detection/skill.md on GitHub (opens in a new tab)

• selector-patterns

  Redux selector authoring for MetaMask Mobile: named `select<Feature><Thing>` selectors in `app/selectors/`, `createSelector` / `createDeepEqualSelector` from reselect, leaf reads of `state.engine.backgroundState`, and `useSelector(selectX)` in UI. Use when adding or creating a selector, updating or refactoring an existing selector, moving inline `useSelector` derivation out of a component or hook…

  domains/coding/skills/selector-patterns/skill.md on GitHub (opens in a new tab)

• codex

  Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

  domains/general/skills/codex/skill.md on GitHub (opens in a new tab)

• gemini

  Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

  domains/general/skills/gemini/skill.md on GitHub (opens in a new tab)

• grafana-tempo-queries

  Query backend traces in Grafana Tempo with TraceQL — find traces by service or span attribute, fetch a trace by id, inspect its span tree, and enumerate tag values. Covers the datasource-proxy access path, the credential-expiry failure that returns empty results indistinguishable from "no data", the negative control that proves a filter actually applied, and the id/kind/base64 decoding quirks in…

  domains/observability/skills/grafana-tempo-queries/skill.md on GitHub (opens in a new tab)

• instrumentation

  Create and update Sentry spans, MetaMetrics events, and Segment events — methodology, policies, common pitfalls

  domains/observability/skills/instrumentation/skill.md on GitHub (opens in a new tab)

• performance-attribution

  Attribute release-over-release p75/p95 performance movements to specific code changes via black-box diff analysis

  domains/observability/skills/performance-attribution/skill.md on GitHub (opens in a new tab)

• sentry-grafana-correlation

  Join one trace across Sentry and Grafana Tempo by trace id to see the whole client-to-backend path, and diagnose why a half is missing. Covers the split-store model (client spans reach Sentry through the SDK and survive only head sampling; backend spans reach Tempo through tail sampling and Sentry through environment routing), the classification of both-halves / client-only / backend-only outcome…

  domains/observability/skills/sentry-grafana-correlation/skill.md on GitHub (opens in a new tab)

• sentry-mcp-queries

  Query Sentry via MCP — error triage, tag distribution, volume estimation, replay retrieval

  domains/observability/skills/sentry-mcp-queries/skill.md on GitHub (opens in a new tab)

• sentry-quota

  Catch quota-risky Sentry span instrumentation in code and PRs — fan-out × ungated × no-kill-switch — before it blows the span budget

  domains/observability/skills/sentry-quota/skill.md on GitHub (opens in a new tab)

• check-nesting

  Audit a React Native component for unnecessary wrapper nesting and suggest flattening opportunities. Also flags non-interactive containers missing accessible={false}. Use when reviewing or generating components to reduce native view depth and accessibility node count.

  domains/performance/skills/check-nesting/skill.md on GitHub (opens in a new tab)

• data-analysis

  Structured approach for analyzing metrics, attributing changes, and communicating findings — five phases (collection → filtering → curation → questioning → synthesis), confidence assignment, audience-appropriate artifacts

  domains/performance/skills/data-analysis/skill.md on GitHub (opens in a new tab)

• effect-antipattern-scan

  Review PR diffs that add or modify `useEffect` for the systemic React effect antipatterns

  domains/performance/skills/effect-antipattern-scan/skill.md on GitHub (opens in a new tab)

• extension-profiling

  Compare browser extension performance between branches using WDYR, React DevTools Profiler, and E2E benchmarks with statistical rigor.

  domains/performance/skills/extension-profiling/skill.md on GitHub (opens in a new tab)

• perf-hooks-effects

  Extension UI hooks and effects: when not to use `useEffect`, dependency arrays, why `JSON.stringify` deps are never the fix, cascading effects, `AbortController` cleanup. Use when an effect loops or fires every render, deps are stringified to force equality, or state lands after unmount. Rendering goes to `perf-rendering`.

  domains/performance/skills/perf-hooks-effects/skill.md on GitHub (opens in a new tab)

• perf-react-compiler

  React Compiler in the Extension UI: what it optimizes, where it bails out, and when manual memoization is still needed. Use when deciding whether `useMemo`, `useCallback` or `React.memo` are still required, reviewing reflexive memoization, or working out why a component isn't optimized. Dependency arrays go to `perf-hooks-effects`.

  domains/performance/skills/perf-react-compiler/skill.md on GitHub (opens in a new tab)

• perf-rendering

  Extension UI render performance: list keys, virtualization, `React.memo`, code splitting, Web Workers, debouncing. Use when a long list stutters, scrolling feels janky, a component re-renders more than it should, or a route loads slowly. Effects go to `perf-hooks-effects`; selectors to `perf-state-management`.

  domains/performance/skills/perf-rendering/skill.md on GitHub (opens in a new tab)

• perf-state-management

  Extension Redux state and selectors: reducer purity, keeping non-serializable values out of the store, normalization, Immer, batching, identity output selectors. Use when components re-render on unrelated state changes, a selector returns a fresh identity every call, or state is mutated in a reducer. Memoization goes to `perf-rendering`.

  domains/performance/skills/perf-state-management/skill.md on GitHub (opens in a new tab)

• performance

  Use for any performance question about the MetaMask Mobile React Native app. Trigger when: a screen, list, or interaction feels slow, laggy, or janky (account/network switching, scrolling, typing, FPS drops); planning a feature with real-time/websocket data, frequent updates, or large lists; reviewing or auditing PRs/code for excessive re-renders, broken selector memoization, Context providers, h…

  domains/performance/skills/performance/skill.md on GitHub (opens in a new tab)

• profiling-regression-proposal

  Proposes follow-up actions for an already-classified Hermes CPU-profile regression using only the profiling evidence supplied by the caller. Use after deterministic tooling has identified a slow scenario and correlated hot-frame paths with files from recently merged pull requests.

  domains/performance/skills/profiling-regression-proposal/skill.md on GitHub (opens in a new tab)

• react-render-delta

  Prove a React rendering or memoization change actually reduced work, with a delivery gate and a reported band. Covers re-render counts (why-did-you-render), selector recomputes (reselect's real `.recomputations()` API), and A/B arms toggled at a FIXED commit rather than across a merge boundary. The falsifier is an arm whose treatment never reached the built bundle — a null from undelivered treatm…

  domains/performance/skills/react-render-delta/skill.md on GitHub (opens in a new tab)

• selector-antipattern-scan

  Review and diagnose Redux selector antipatterns that cause render cascades, pre-merge and post-merge

  domains/performance/skills/selector-antipattern-scan/skill.md on GitHub (opens in a new tab)

• perps-breakdown-tickets

  Interactively break a perps product requirement into split, dispatch-ready technical tickets across MetaMask Core, its release, Mobile, and Extension. Use when a product manager (or a codebase-aware Claude acting for one) has a perps bug or feature and needs engineering-grade tickets, correctly routed now that @metamask/perps-controller is the Core source of truth. Triages where the change actual…

  domains/perps/skills/perps-breakdown-tickets/skill.md on GitHub (opens in a new tab)

• perps-review-pr

  Execute the Perps static review checklist when explicitly invoked by name or a selected workflow.

  domains/perps/skills/perps-review-pr/skill.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills
• claude-memby thedotmack Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject… 101k stars · 20 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills
• career-opsby career-ops-hq Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendl… 75.1k stars · 6 skills