Claude Skills by NeverSight

Systematic code refactoring skill that transforms complex, hard-to-understand code into clear, well-documented, maintainable code while preserving correctness. Use when users request "readable", "maintainable", or "clean" code, during code reviews flagging comprehension issues, for legacy code modernization, or in educational/onboarding contexts. Applies structured refactoring patterns with validation.

Monetization expert that analyzes codebases to discover features, calculate service costs, model usage patterns, and create data-driven pricing with revenue projections. Use when: (1) Analyzing app features and their costs, (2) Modeling user consumption and usage patterns, (3) Calculating ARPU, LTV, and revenue projections, (4) Setting optimal tier limits based on usage percentiles, (5) Creating pricing tiers with adequate margins, (6) Implementing payment systems (Stripe, etc.), (7) Break-ev...

Comprehensive Stripe integration agent for payments, subscriptions, billing, and marketplace management. Use when Claude needs to work with Stripe API for creating customers, managing subscriptions, processing payments, handling checkout sessions, setting up products/prices, managing webhooks, Connect marketplaces, metered billing, tax calculation, fraud prevention, or any payment-related task. Triggers on mentions of Stripe, payments, subscriptions, billing, checkout, invoices, payment inten...

Expert guidance for developing, testing, and deploying mobile applications with Tauri 2. Use when working with Tauri 2 mobile development for Android/iOS, including project setup, Rust backend patterns, frontend integration, plugin usage (biometric, geolocation, notifications, IAP), emulator/ADB testing, code signing, and Play Store/App Store deployment.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when a forge legacy-bridge or forge archive command emits a Task manifest (forge/.cache/legacy-bridge-task-<op>.json) that needs agent fulfillment - reads the manifest, performs the LLM op, writes results, runs --apply. Ops include map / index / regenerate / sync-check / extract.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Use when verifying a forge change — analyze Completeness / Correctness / Coherence three dimensions with concrete prose evidence (file:line / spec:Requirement-id), instead of degenerate "tests pass" binary

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating or modifying a forge skill — RED-GREEN-REFACTOR discipline + frontmatter conventions + forge-eval integration so new skills actually shape AI behavior in forge contexts

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.

Color contrast analyzer for WCAG compliance. Use when analyzing color contrast in code files, when user mentions WCAG compliance, color accessibility, contrast ratios, or when discussing colors in UI components. Calculates contrast ratios, identifies violations, and suggests accessible color alternatives that preserve design themes.

Accessibility refactoring specialist. Automatically fixes accessibility issues across multiple files. Performs complex refactoring like extracting accessible components, restructuring markup, and implementing proper ARIA patterns.

Reverse-engineer the current state of analytics tracking from a codebase. Scans for SDK calls, identity management, and instrumentation patterns to produce a factual inventory — not recommendations. Outputs .telemetry/current-state.yaml and a timestamped audit report. Use when the user wants to know what's currently tracked, audit existing analytics, capture tracking reality before designing a new plan, 'what analytics do we have,' 'what events are tracked,' 'scan for tracking,' or 'tracking ...

Generate real instrumentation code from the tracking plan and instrumentation guide. Produces typed SDK wrapper functions, identity management, and integration guidance. Outputs files in a tracking/ directory. Use when the user wants to generate or regenerate tracking code, implement the delta plan, turn the instrumentation guide into working code, 'implement tracking,' 'generate code,' 'create tracking module,' or 'build analytics SDK wrapper.'

Update the tracking plan when a feature ships, changes, or is removed. Assesses whether new events are needed, extends existing events with properties where possible, and produces a versioned mini-delta with changelog entry. Updates .telemetry/tracking-plan.yaml, delta.md, and changelog.md. Use when the user ships a new feature, modifies existing functionality, wants to keep tracking coherent as the product evolves, 'feature shipped,' 'new feature tracking,' 'update tracking for [feature],' '...

Generates comprehensive API documentation from source code by analyzing endpoint definitions, request/response schemas, authentication requirements, and error codes. Produces structured docs in OpenAPI-compatible format with examples, parameter descriptions, and usage guides. Use when documenting APIs, generating API reference docs, creating endpoint documentation, or when the user needs API docs from their codebase.

Generates audience-aware changelogs from git history with SemVer impact classification, migration instructions for breaking changes, grouped categories (features, fixes, performance, dependencies), and upgrade guides for major versions. Use when generating changelogs, writing release notes, preparing version bumps, or when the user needs to document what changed between releases.

Performs structured code reviews analyzing diffs or files for bugs, security vulnerabilities, performance issues, style violations, and maintainability concerns. Produces categorized findings with severity levels and actionable fix suggestions. Use when reviewing code, pull requests, merge requests, code changes, or when the user asks for feedback on their code.

Writes safe, reversible database migrations with rollback plans, data backup commands, zero-downtime deployment notes, and index impact analysis. Produces both up and down migration files with verification queries. Use when writing database migrations, schema changes, ALTER TABLE statements, adding indexes, or when the user needs to modify database structure.

Standardizes error handling across a codebase with a unified error taxonomy, consistent error codes, proper propagation chains, user-facing vs internal error separation, and structured logging with correlation IDs. Use when adding error handling, implementing error classes, standardizing exceptions, creating error responses, or when the user needs consistent error patterns.

Guide selection, configuration, and customization of Google Cloud Foundation Fabric (CFF) Terraform modules and FAST landing zone stages. Use when working with cloud-foundation-fabric, Fabric FAST, GCP landing zones, CFF modules, project factory, VPC factory, or when the user mentions Google Cloud Terraform modules from GoogleCloudPlatform/cloud-foundation-fabric. Also use when designing GCP organization structure, networking stages, or configuring factories_config patterns.

Generates conventional commit messages from staged git changes by analyzing diffs, classifying change types (feat, fix, refactor, docs, test, chore, ci, perf, style, build), and composing structured commit messages with optional scope and breaking change notation. Use when committing code, writing commit messages, preparing git commits, or when the user asks for help with commit messages.

Decides whether a validated wedge should become software, defines the narrow product wedge, and separates what stays manual versus automated. Use when a service, workflow, or audience-driven opportunity may be ready for micro-SaaS scoping or when a user is tempted to build software too early.

Adds structured observability to services including health check endpoints (liveness, readiness, startup), metrics collection (latency, error rates, throughput), distributed tracing with correlation IDs, alert threshold configuration with escalation policies, and runbook links. Use when adding monitoring, setting up observability, creating health checks, configuring alerts, or when the user needs production readiness instrumentation.

Implement Nostr client architecture including relay pool management, subscription lifecycle with EOSE/CLOSED handling, event deduplication, optimistic UI for publishing, and reconnection strategies. Use when building Nostr clients, managing WebSocket relay connections, handling subscription state machines, implementing event caches, or debugging relay communication issues like missed events or broken reconnections.

Guide implementation of Nostr cryptographic operations including NIP-44 encrypted payloads, NIP-59 gift wrap privacy layers, NIP-49 private key encryption (ncryptsec), NIP-06 key derivation from mnemonic, and NIP-46 remote signing. Use when implementing encrypted DMs, private messaging, key backup/export, mnemonic-based key generation, or remote signer integration in Nostr applications.

Build Nostr Data Vending Machine (DVM) services and clients using NIP-90. Use when implementing AI/compute service providers (kinds 5000-5999 job requests, 6000-6999 job results, kind 7000 feedback), creating DVM job request clients with payment handling, chaining DVM jobs, handling encrypted DVM params, or publishing NIP-89 service provider discovery events for DVMs.

Use when constructing Nostr events from natural language descriptions, building kind-specific tag structures, implementing NIP-10 threading for kind:1 replies, creating NIP-22 comments on non-note content, or generating correct event JSON with proper e/p/a tag markers and serialization format.

Construct correct Nostr REQ filters for complex queries. Use when building Nostr relay subscriptions, querying events, constructing REQ messages, filtering by tags, combining multiple filter conditions, or working with Nostr protocol filter syntax. Handles AND/OR semantics, tag filter gotchas, multi-filter subscriptions, and common query patterns like threads, zaps, reactions, and feeds.

Build Nostr marketplace applications using NIP-15 stalls, products, auctions, and NIP-69 P2P orders. Use when creating e-commerce on Nostr, building product listings, setting up stalls with shipping zones, implementing auction bidding systems, constructing checkout flows with NIP-04 DMs, creating P2P trading orders, or generating marketplace UI configurations. Covers kind:30017 stalls, kind:30018 products, kind:30020 auctions, kind:1021 bids, kind:1022 bid confirmations, kind:30019 marketplac...

Identifies which Nostr NIPs apply when implementing a feature (DMs, zaps, marketplace, groups, authentication, etc.), warns about deprecated or unrecommended NIPs, and provides correct event structures. Use when building Nostr clients, relays, or features, when asking which NIPs to implement, when planning Nostr protocol integration, or when encountering NIP-04, NIP-08, NIP-96, or NIP-26 in existing code.

Set up NIP-05 DNS-based identity verification for Nostr, including the /.well-known/nostr.json endpoint, CORS headers, and kind:0 profile updates. Use when configuring NIP-05, setting up nostr.json, debugging NIP-05 verification failures, adding DNS identity to a Nostr profile, or working with /.well-known/nostr.json files and CORS for Nostr clients.

Build a Nostr relay from scratch with WebSocket handling, NIP-01 event validation (id computation, Schnorr signature verification), filter matching, subscription management, and progressive NIP support (NIP-11, NIP-09, NIP-42, NIP-50). Use when building a Nostr relay, implementing the Nostr relay protocol, handling Nostr WebSocket connections, validating Nostr events, matching Nostr filters, or adding NIP support to a relay. Also use when the user mentions relay development, nostr server, eve...

Build and traverse Nostr social graphs including follow lists (kind:3, NIP-02), relay list metadata (kind:10002, NIP-65), the outbox model for relay-aware event fetching, mute lists (kind:10000), and NIP-51 lists with public and private encrypted items. Use when implementing follow/unfollow, building feeds from followed users, discovering user relays, implementing the outbox model, creating mute or bookmark lists, or working with any NIP-51 list kind.

Implement Lightning Zaps (NIP-57) and Nutzaps (NIP-61) for Nostr applications. Use when building zap request construction (kind:9734), zap receipt validation (kind:9735), LNURL-pay flows, zap splits, Cashu/Nutzap sending (kind:9321), nutzap receiving configuration (kind:10019), or any payment integration between Nostr and Lightning/Cashu.

Extract text, tables, and images from PDFs, OCR scanned PDFs, create PDFs from text/images/markdown, and merge or split PDF files. Use when working with PDF documents, when the user mentions PDFs, document extraction, OCR, scanning, PDF merging, splitting, combining, or creating PDF reports. All operations use bundled Bun TypeScript scripts with structured JSON output.

Generates structured pull request descriptions from branch diffs with context, motivation, testing instructions, rollback plans, and reviewer guidance. Produces descriptions that help reviewers understand what changed, why, and how to verify. Use when creating PRs, writing PR descriptions, preparing merge requests, or when the user asks for help describing their changes.

Create agent skills and improve them via eval-driven subagent loops. Use when creating a skill, building a SKILL.md, testing with evaluations, benchmarking skill performance, or optimizing trigger accuracy. Also use for reusable agent workflows or packaging agent knowledge.

Capture a project’s telos in TELOS.md or assess whether a proposed feature aligns with that telos when planning or evaluating new project work.

ACE-Step documentation and troubleshooting. Use when users ask about installing ACE-Step, GPU configuration, model download, Gradio UI usage, API integration, or troubleshooting issues like VRAM problems, CUDA errors, or model loading failures.

Manage your AceDataCloud account through the management API (platform.acedata.cloud). Use when the user wants to check their balance / remaining credits, look up API call (usage) records and spend, list or create or delete API keys (credentials), list subscribed services, list/create/pay recharge orders, manage platform tokens, view referral/affiliate earnings, or (admins) publish an announcement. Also covers the PUBLIC catalog & docs (no token needed): service detail & pricing, API list & Op...

Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from GPT, Claude, Gemini, Kimi, Grok, or other models through a single endpoint. Supports streaming, function calling, and vision.

Manage Apple Notes on macOS — list, search, read, create, append, move, delete, and export notes, and manage folders. Use when the user mentions Apple Notes / 备忘录, "add a note", "my notes", searching their notes, organizing folders, or exporting a note to Markdown/HTML. macOS-only; runs locally against Notes.app — no cloud API, no token.

Read and publish 专栏 articles on Bilibili (bilibili.com) with the user's own login cookies (BYOC) — list their published articles with view/like/comment stats, inspect one article, and publish a new article. Use when the user mentions Bilibili / B站 / 专栏, "我的B站专栏", reading article stats (阅读/点赞), or publishing/投稿 a 专栏 article.

Publish posts to your Blogger blog and read your blogs / posts via the Blogger API v3. Use when the user mentions Blogger, blogspot, publishing a post to their blog, listing their blogs, or updating an existing Blogger post.

Publish (with optional images), delete and read your own posts on Bluesky via the AT Protocol (XRPC). Use when the user wants to post to their Bluesky account (text or 带图 / with a picture), cross-post an article as a short dev-focused post, attach an image, delete a post, or list their own recent posts with engagement stats (reposts, likes, replies). Auth uses the user's handle plus an App Password.

Upload a local file to AceData Cloud CDN and get back a public URL. Use whenever you produce a local artifact (image, audio, video, doc) that another API needs as a URL, or that you need to return/persist (e.g. feed a generated image into an image-to-video API, or publish a finished video).