Reviews code changes for security, correctness, performance, and maintainability, in Go, TypeScript, PHP, Vue, or any language. Use when given a PR URL, a diff, or a file path; before merging a change; or when asked to check for injection risks, missing edge cases, missing authorization checks, or error-handling gaps.
Runs a fixed-category severity scan over a diff, file, or snippet — correctness, security, error handling, concurrency, performance, readability, tests — and emits a CRITICAL/HIGH/MEDIUM/LOW/INFO-graded report. Use when asked to "scan this code", grade a change by severity, or review Go code for concurrency bugs (data…
Simplifies working code for clarity without changing behavior — reduces nesting, renames vague identifiers, removes dead code and unnecessary abstraction. Use when code works but is harder to read, maintain, or extend than it should be, or when a review flagged accumulated complexity. Not for adding features or fixing…
Cross-language code-quality heuristics -- function size, nesting depth, magic numbers, comment intent, naming -- for reviewing or writing code in any language. Use when reviewing code for maintainability, setting up lint rules, or onboarding conventions. For Go-specific idioms use go-service-idioms, for API contracts…
Patterns for building shared UI across Android, iOS, Desktop, and Web with Compose Multiplatform and Jetpack Compose — state hoisting with ViewModel/StateFlow, type-safe navigation, slot-based composables, recomposition performance, and expect/actual platform code. Use when writing or reviewing Compose UI, wiring a…
Turn one source asset (article, demo, launch memo, podcast) into strong, platform-native content for X, LinkedIn, TikTok/short-video, YouTube, or a newsletter instead of cross-posting the same copy everywhere. Use when the user wants social posts, threads, video scripts, a content calendar, or a launch repurposed…
Cache expensive file-processing results (PDF parsing, OCR, text extraction, image analysis) keyed by a SHA-256 hash of file content rather than file path, so renamed files still hit the cache and changed content auto-invalidates it. Use when building a file-processing pipeline that reprocesses the same files across…
Deliberately curate what an agent sees, when, and how it's structured, to keep output quality high across a session. Use when starting a new coding session, when agent output quality is degrading (hallucinated APIs, ignored conventions), when switching between unrelated parts of a codebase, or when setting up a new…
Use when a coding-agent loop is already running unattended and you need to define its quality gates, detect that it's stuck (churning without progress, retrying the same failure, cost drifting up), and recover it safely. Trigger phrases include "the loop has run 20 times with no progress", "the agent keeps failing the…
Use when designing a fine-grained, hook-driven learning system that observes every tool call (not just session end), stores atomic "instincts" with confidence scores, and evolves clusters of related instincts into skills, commands, or agents — with project-scoped vs. global separation so React conventions don't leak…
Use when setting up end-of-session extraction of reusable patterns (error resolutions, user corrections, workarounds, project conventions) from a Claude Code session into a saved skill file, via a Stop hook. Trigger phrases include "save what we learned this session", "extract a skill from this conversation", "set up…
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".
Codified expertise for customs documentation, tariff classification, duty optimization, restricted-party screening, and regulatory compliance across US/EU/UK/APAC jurisdictions, including HS classification logic, Incoterms application, FTA utilization, and penalty mitigation. Use when classifying goods, preparing…
Use when the user asks to "design a new data model that stores personal data", "add a retention policy", "figure out how long to keep guest data", "handle a data deletion request", "design for GDPR compliance", or is adding any field/table that captures a name, email, phone, ID document, or payment detail. Guides…
Build an automated data-collection agent that scrapes a public source on a schedule, enriches results with a cheap/free LLM, stores them in a database, and improves scoring from user feedback over time — runnable entirely on free-tier infrastructure. Use when the user wants to monitor, collect, or track any public…
Guides safe, reversible PostgreSQL schema and data migrations using golang-migrate, Prisma, Drizzle, or Django migrations. Use when creating or altering tables, adding or removing columns or indexes, planning a zero-downtime schema change, or reviewing a migration before it runs against production. For tables…
Runs a tight four-phase loop — reproduce, isolate, diagnose, fix — to root-cause a single bug with evidence, not guesses. Use when given a specific error message, stack trace, or unexpected behavior for one bug and need a fast, mechanical session (reproduce → isolate → diagnose → fix → prevention). For broader…
Enforces a stop-the-line triage protocol across failure classes — test failures, build breaks, runtime errors, and production incidents — using bisection, safe-fallback design, and instrumentation lifecycle management. Use when any unexpected failure appears and the question is "what class of failure is this and…
Produce a thorough, multi-source, cited research report on an open-ended topic using web search and page-fetch tools, optionally fanning out across parallel sub-agents for broad subjects. Use when the user wants a deep dive, investigation, or "what's the current state of X" report on any topic, not a narrow technical…
This skill should be used when the user asks to write acceptance criteria for a user story, define or review a team's Definition of Done, evaluate whether a story is "ready" or "done", or asks things like "write Given/When/Then criteria for this story", "is this Definition of Done good enough", "why do we keep…
Use when the user asks to "add a dependency", "vet a license", "check if this package is safe to use", "can we use this library", "add this to go.mod/package.json", or is preparing a proprietary/closed-source product that bundles open-source code. Guides license-compatibility review before a dependency is pulled in…
Guides production rollout strategy — rolling/blue-green/canary deployments, liveness/readiness/startup probes, startup config validation, and rollback planning. Use when choosing a deployment strategy, implementing health check endpoints or Kubernetes probes, planning a rollback path before a release, or reviewing a…
Guides deprecating and removing old systems, APIs, or code, and migrating consumers to a replacement. Use when replacing a library, API, or internal system with a new one, sunsetting a feature, deciding whether to maintain or remove legacy code, or planning how a new system will eventually be retired.
Analyzes a git diff or PR across three tracks — complexity, style/convention, and security impact — run together, then synthesized into a single risk-graded report with required actions cited to file:line. Use when given a raw diff, PR number, or branch to triage before merge, especially when the ask is "how risky is…