Results for “nag”

Improve the visual design of a frontend by restyling components one at a time, with approval gates and no functional changes.

Diagnose bugs, failing tests, or unexpected behavior by reproducing, isolating, hypothesizing with evidence, and confirming fixes before making changes.

Scans a single file against the OWASP Top 10:2025, tracks cross-file connections, and maintains a persistent findings record.

Turns a mature product plan into a rough implementation plan with high-level steps, maturity and verification marks, and a risks section.

Systematically adds unit test coverage to existing source files in any project, tracking progress across sessions via scan, plan, and write modes.

Audits a repository for comment coverage and brings under-commented source files up to standard, one file at a time, with a resumable tracker.

Drafts a changelog entry from local git history between two refs, matching the project's existing changelog format, and writes it to a draft file.

Verifies each step of a rough implementation plan against source code and current documentation, attaching proof and marking steps as verified or unverified.

Refreshes the local OWASP Cheat Sheet Series cache for the current project's language, checking GitHub for updates and fetching changed sheets.

Turns a raw feature or project idea into a structured product plan document covering goals, audience, requirements, and constraints, with a maturity-tracking workflow.

Upgrades outdated dependencies one package at a time, checking changelogs for breaking changes and running tests between each upgrade, stopping on failure.

Switches Claude Code into a teaching-first mode for unfamiliar technologies, explaining concepts and commands step by step without writing code until approved.

Aligns repository labels with a preset in labels.yml by creating and editing labels via the GitHub CLI, without deleting or modifying labels outside the preset.

娜美（少年漫）认知与表达框架（压缩蒸馏）：航海图天才、财迷喜剧壳、气候战 触发：海贼王 等。虚构

Scans frontend files, audits them for responsive layout issues, and applies minimal CSS/className fixes to prevent overflow at small window or mobile sizes.

NATS cloud-native messaging system. Covers Core NATS, JetStream persistence, and request/reply patterns. Use for lightweight, high-performance microservices communication. USE WHEN: user mentions "nats", "jetstream", "cloud-native messaging", "request/reply", "subject wildcards", asks about "lightweight messaging", "microservices communication", "nats streaming" DO NOT USE FOR: complex routing - use `rabbitmq`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; JMS compliance - use `activemq`; persistent queues only - use dedicated broker

Analyze NATS clusters with read-only operations: discover JetStream streams and consumers, check cluster health, and inspect message flow.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Triage npm packages for install-script malware, exfiltration, and worming behavior using GuardDog, manual inspection, and safe detonation.

Dropdown component for displaying contextual menus and action lists. Invoke when user needs to implement dropdown menus, context menus, or cascading selections in Naive UI.

Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.

靖王（古装权谋虚构）认知与表达框架（压缩蒸馏）：耿直宗室、信任成本、笨办法正义 触发：琅琊榜 等。虚构

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model.

Popconfirm component for confirmation dialogs in popover style. Invoke when user needs to implement confirmation prompts, delete confirmations, or action verifications in Naive UI.

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model.

Menu component for navigation and actions. Invoke when user needs to implement navigation menus, sidebars, dropdown menus, or hierarchical navigation in Naive UI.

Creates or edits a GitHub pull request in draft state from a reviewed draft file, with strict safeguards against merging, pushing, or modifying tracked files.

Interact with Farcaster via Neynar API. Use when the user wants to read Farcaster feeds, look up users, post casts, search content, or interact with the Farcaster social protocol. Requires NEYNAR_API_KEY.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

Generate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream instead. Calls `runcomfy run google/nano-banana-2/text-to-image` through the local RunComfy CLI. Triggers on "nano banana", "nano-banana-2", "nano banana 2", "google image gen", "gemini image", or any explicit ask to generate with this model.