Claude Skills by NeverSight

Create, validate, and evolve Product Requirements Documents with interactive discovery, technical architecture, phasing, TDD protocol, and dependency analysis. Use when: writing a PRD, planning a feature, defining requirements, or updating an existing PRD. Supports /prd (create), /prd --update (incremental update), /prd --validate (run checklist), /prd --audit-deps (dependency analysis only), /prd --to-plan (generate orchestrate-ready task plan).

Use when assessing release readiness or running a pre-launch review. Spawns 5 specialist agents in parallel (security, testing, performance, observability, code quality) and synthesizes a prioritized report with ship/don't-ship recommendation. Keywords: production readiness, release review, pre-launch, security audit, test coverage, ship checklist.

Stage, lint, scan, review, and commit changes with full quality gates in a single standardized flow.

Terraform module extraction decision framework. Use when: (1) deciding whether to create module vs keep inline, (2) determining module boundaries, (3) avoiding over-abstraction, (4) handling state migration. NOT a Terraform tutorial. Focuses on the refactoring decision (when to modularize, when to keep inline) and anti-patterns that create module sprawl. Triggers: terraform module, refactor terraform, module boundaries, when to create module, terraform abstraction, module sprawl, state migr...

Pre-PR review pipeline — runs security, API audit, and scope check agents in parallel. Read-only, no changes. Use before creating PRs or after completing a phase of work.

Use when storing secrets in OCI Vault, debugging 401/403 secret retrieval errors, implementing secret rotation, configuring instance principal auth, or caching Vault API calls. Covers IAM dual-permission gotcha, vault hierarchy confusion, temp file security window, BASE64 encoding requirement, and cost optimization.

Use when reviewing code changes before commit or PR merge. Covers tool sequencing, finding severity priorities, fix ordering strategy, and conflict resolution between tools. Keywords: code review, semgrep, coderabbit, security scan, pre-commit review, PR review, hardcoded secrets, SQL injection, XSS.

Use when converting Stitch designs into production React components. Enforces modular architecture: logic in hooks, data in mockData.ts, Readonly TypeScript interfaces, theme-mapped Tailwind classes. Triggers on: Stitch to React, design to code, stitch export, stitch MCP, stitch:get_screen.

TanStack Query v5 expert guidance - migration gotchas (v4→v5 breaking changes), performance pitfalls (infinite refetch loops, staleness traps), and decision frameworks (when NOT to use queries, SWR vs React Query trade-offs). Use when: (1) debugging v4→v5 migration errors (gcTime, isPending, throwOnError), (2) infinite refetch loops, (3) SSR hydration mismatches, (4) choosing between React Query vs SWR vs fetch, (5) optimistic update patterns not working. NOT for basic setup (see official d...

Test-driven development workflow — write failing tests first, implement minimum code, run full suite, commit. Use when implementing features, fixing bugs, or adding test coverage. Includes mock bootstrap phase for projects with mockReset:true.

Turborepo monorepo architecture decisions and anti-patterns. Use when: (1) choosing between monorepo vs polyrepo, (2) deciding when to split packages, (3) debugging cache misses, (4) setting package boundaries, (5) avoiding circular dependencies. NOT for CLI syntax (see turbo --help). Focuses on architectural decisions that prevent monorepo sprawl and maintenance nightmares. Triggers: turborepo, monorepo, package boundaries, when to split packages, turbo cache miss, circular dependency, wor...

Use when drafting, translating, polishing, or reviewing Swedish text so it sounds natural, fluent, contemporary, and appropriate for its audience. Triggers include \"write better Swedish\", \"make this sound natural in Swedish\", \"translate into Swedish\", \"polish this Swedish\", \"tech company Swedish\", \"contemporary Swedish words\", \"Swedish developer docs\", and \"avoid Anglicisms\".

Add test coverage to existing code with correct mock patterns. Use when adding tests to untested modules, writing regression tests for bugs, or user asks to test a specific file. Handles mockReset:true, vi.hoisted(), forwarding pattern, and test app builder utilities.

Use when architecting OCI solutions, migrating from AWS/Azure, designing multi-AD deployments, or avoiding common OCI anti-patterns. Covers VCN sizing mistakes, Cloud Guard gotchas, free tier specifics, OCI terminology confusion, and multi-AD patterns.

Use when launching OCI compute instances, troubleshooting out-of-capacity or boot failures, optimizing compute costs, or handling instance lifecycle. Covers shape selection, capacity planning, service limits, and production incident resolution.

Use when creating Autonomous Databases, troubleshooting connection failures, managing PDBs, or optimizing database costs. Covers connection string confusion, password validation errors, stop/start cost traps, clone type selection, and backup retention gotchas.

Use when optimizing OCI costs, investigating unexpected bills, planning budgets, or identifying waste. Covers hidden cost traps (boot volumes, reserved IPs, egress), Universal Credits gotchas, shape migration savings, free tier maximization, and cost allocation challenges.

Use when implementing OCI GenAI inference APIs, troubleshooting rate limits or token errors, optimizing GenAI costs, or handling sensitive data (PHI/PII) in prompts. Covers model selection, cost calculations, token management, response validation, and healthcare/compliance considerations.

Use when writing IAM policies, troubleshooting permission denied errors, setting up dynamic groups, or implementing IDCS integration. Covers policy syntax gotchas, principal types confusion, compartment inheritance, and common authorization failures.

Use when writing Terraform for OCI, troubleshooting provider errors, managing state files, or implementing Resource Manager stacks. Covers terraform-provider-oci gotchas, resource lifecycle anti-patterns, state management mistakes, authentication issues, and OCI Landing Zones.

Use when designing multi-tenant OCI environments, setting up production landing zones, implementing compartment hierarchies, or establishing governance foundations. Covers Landing Zone reference architectures, compartment strategy, network topology patterns (hub-spoke vs multi-VCN), IAM structure, tagging standards, and cost segregation.

Use when designing OCI networks, troubleshooting connectivity, optimizing egress costs, or configuring VCN security. Covers Service Gateway cost savings, VCN CIDR immutability, Security List vs NSG tradeoffs, VCN peering limitations, and Load Balancer subnet requirements.

Use when implementing event-driven automation, setting up CloudEvents rules, troubleshooting event delivery failures, or integrating with Functions/Streaming/Notifications. Covers event rule patterns, filter syntax, action types, dead letter queue configuration, and event-driven architecture anti-patterns.

Use when managing Oracle Autonomous Database on OCI, troubleshooting performance issues, optimizing costs, or implementing HA/DR. Covers ADB-specific gotchas, cost traps, SQL_ID debugging workflows, auto-scaling behavior, and version differences (19c/21c/23ai/26ai).

Use when storing credentials in OCI Vault, troubleshooting secret retrieval failures, implementing secret rotation, or setting up application authentication to Vault. Covers vault hierarchy confusion, IAM permission gotchas, cost optimization, temp file security, and audit logging.

Oracle DBA and DevOps expertise for Autonomous Database (ADB) on OCI. This skill should be used when managing Oracle Autonomous Databases, writing optimized SQL/PLSQL, configuring security (TDE, Database Vault, Data Safe), implementing HA/DR (Data Guard, PITR), using OCI CLI for database operations, or integrating with Oracle MCP servers for AI-assisted database management. Covers Oracle Database versions 19c, 21c, 23ai, and 26ai.

Apidog API development platform documentation - API design, testing, mocking, and documentation

Use when the user invokes /simply or @simply, or says reply like Google dev docs: more dead prose, no aphorisms, no flourishes, simple, like one human to another. Apply to drafts, edits, docs, Slack, emails, PR text, and chat replies.

Generate professional article cover images as SVG files. Use when user wants to create cover/banner images for blog posts, technical articles, or documentation. Creates visually appealing covers with titles, diagrams, and tech-themed graphics.

Execute Codex CLI for code generation, analysis, web search and web fetch. Two capabilities - (1) Code Generation with deep reasoning, (2) Web Search & Fetch for online research.

Generate hand-drawn style diagrams (architecture, flowcharts, system design) as .excalidraw.json files. Use when user wants diagrams, mentions Excalidraw, or needs Mermaid-to-visual conversion.

Generate images using AI when user wants to create pictures, draw, paint, or generate artwork. Supports text-to-image and image-to-image generation.

Generate concise commit messages based on conversation context and minimal git inspection.

Squash multiple git commits into a single commit with an auto-generated comprehensive commit message based on the changes made.

Generate a verifiable GitHub Wrapped year-in-review as a single-file HTML (raw gh API JSON saved, Python-built dataset embedded), with a Bilibili-style narrative, smooth transitions, and mobile-friendly paged mode. Requires gh CLI to be authenticated.

Structured web research with multi-source validation. Output reports with complete citation links. Focus on key results, verify information quality.

Write technical blog posts with source code analysis OR doc-driven research. Use when user wants to explain system internals, architecture, implementation details, or technical concepts with citations.

Generate technical design documents with proper structure, diagrams, and implementation details. Default language is English unless user requests Chinese.

Write precise technical implementation docs (developer or user) with clear structure, accurate flows, render-safe Mermaid diagrams, and audience-appropriate detail; avoid boilerplate; include a meaningful Code Index for developer docs.

Use when adding new configuration fields to the Configuration interface for combat conditions, buff stacks, or other build parameters used in damage calculations (project)

Use when adding hero trait mod implementations in hero-trait-mods.ts - guides reading trait descriptions, creating mod factories, adding stackables/config, and wiring up the calculation engine (project)

Use when adding new push* resolver functions inside resolveModsForOffenseSkill to handle mod-based combat mechanics like tangles, debuffs, or conditional damage bonuses (project)

Use when adding support mod parsers to convert support skill affix strings to typed SupportMod objects - guides the template-based parsing pattern (project)

Use when implementing skill data generation from HTML sources for game build planners - guides the parser-factory-generation pattern for extracting level-scaling values for active and passive skills (project)

Author, refresh, or repair the changelog entry for the current branch — derive metadata, write the frontmatter and grouped body, run the deterministic enrichment scripts, and validate against the changelog contract. Use when asked to write or update a changelog entry, refresh an entry after new commits, or as the changelog step inside a ship/PR flow. Detects an existing entry for the branch (idempotent update-vs-create), keeps `created_at` sacred, leaves post-merge fields to the release step,...

Clean up a Git repository's merged branches and worktrees, then prune filesystem cruft (recursively-empty directories and orphaned node_modules). Use when asked to clean up / tidy / prune merged branches, remove stale or finished worktrees, delete branches whose PRs have already merged (including squash-merges), or sweep empty directories and leftover node_modules. Two-pass merge detection (git ancestry plus merged GitHub PRs), an uncommitted-changes guard on worktrees, an optional Linear "Do...

Turn the working tree into logical, atomic Conventional Commits — classify uncommitted files as in-scope vs out-of-scope against the branch's merge base, show a staging plan, and create one commit per coherent unit (type + optional scope + British-English body; `!` / `BREAKING CHANGE:` for breaking changes). Never `git add -A`; files that look like they belong to another branch/worktree are never staged silently. Use when asked to commit uncommitted work, tidy WIP into atomic commits, or as t...

The all-in-one ship finisher — bundle uncommitted work into atomic commits, run the change-gated lint preflight, author or update the dated changelog entry, compose a Conventional Commits PR title (the release-please bump signal), push, open or update a PR, and transition linked Linear issues to In Review. Use when asked to ship, send it, finish a branch, open or update a PR for the current work, or wrap up and push. A thin orchestrator that delegates the commit step to the `commit` skill, th...

Drive a pull request from draft with failing CI to merge-ready. While the PR is a draft, inspect and fix in-scope CI failures (lint, manifest-lint, build, tests) using the gh CLI and GitHub Actions logs — never weakening CI config to greenwash. After the PR is marked ready-for-review, fetch the unresolved AI review threads (Claude Code Review, Bugbot), validate each finding against the codebase before changing anything, fix the valid ones, decline the invalid ones with technical reasoning, th...

阿峰 1.0：从任意现有代码项目中梳理业务逻辑、架构边界、主要代码风格和风格权重，并生成完全适配该项目的专属 Codex skill。Use when the user asks to 创建项目规范skill、梳理业务逻辑、提炼代码风格、让后续代码保持项目一致、生成项目开发标准、项目阿峰、按现有代码写规范、从代码库反推出开发规则。