Results for “ma”

Modern Java 21+ language standards including Records, Pattern Matching, and Virtual Threads. Use for Java language constructs or Java-to-Java upgrades; defer Kotlin, tests, formatting/build tools, CompletableFuture, builder patterns, and isolated null-handling questions.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Create and maintain Actor entities — humans and AI agents that participate in the project. Use when adding a new collaborator (human or agent) to the project, updating their preferences/expertise, or querying who does what.

Manage Heroku config vars safely across environments. Use when the agent needs to inspect, compare, set, remove, or audit Heroku config vars, check `.env` parity, or reason about runtime versus build-time configuration on Heroku.

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

Use when tracking emerging developments in technology, markets, regulations, or industry practices. This skill provides a systematic approach to monitoring trends so the organization stays informed about changes that could impact strategy or operations.

Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

Creating and integrating out-of-tree Zephyr modules. Covers module.yml configuration, Kconfig and CMake integration within a module, and West manifest inclusion. Trigger when developing reusable libraries, driver packages, or external software components for Zephyr.

Ad intelligence and app analytics assistant for searching ad creatives, analyzing apps, rankings, downloads, revenue, and market insights. Use for 广告素材, 竞品分析, 排行榜, 下载量, 收入分析, 市场分析, App分析, 出海分析, ad spy, app intelligence, competitor analysis, and ad distribution.

Developing custom GitHub Actions (JavaScript, TypeScript, Docker, Composite). Use this skill when the user asks to 'create a GitHub Action', 'build a custom action', 'publish action to marketplace', 'write action.yml', or 'develop reusable action'.

Configure and maintain Python projects, dependencies, packaging, environments, linting, formatting, type checking, testing, builds, and publishing. Use for pyproject.toml, an existing repository toolchain, or repository-level Python tooling work, not for a standalone script.

Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration for Hermes. Uses Hermes-managed OAuth2 setup, prefers the Google Workspace CLI (`gws`) when available for broader API coverage, and falls back to the Python client libraries otherwise.

Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.

Identify the best GTM motions and tools across 7 motion types: Inbound, Outbound, Paid Digital, Community, Partners, ABM, and PLG. Use when selecting marketing channels, choosing between inbound and outbound strategy, or planning cross-channel campaigns.

Revise an academic paper based on internal review comments. Reads review report or annotated manuscript, then applies revisions one by one with user approval. Trigger when user says "self revise" / "paper-selfrevise" / "内部修改" / "根据审稿意见修改".

Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.

Validate, review, and compare DESIGN.md design-system files using the Google `@google/design.md` specification and CLI. Trigger this skill whenever the user asks to lint / validate / verify / check / review / diff a `DESIGN.md` (case-insensitive), mentions "design.md", "design system spec", "design tokens YAML", "WCAG contrast on tokens", or uses Korean phrases like "DESIGN.md 검증", "디자인 시스템 검사", "디자인 토큰 점검", "design.md 린트". Also fire when the user pastes a YAML front-matter block that looks like a design-token document (top-level `colors:` / `typography:` / `components:` keys) or when a DESIGN.md file appears in the workspace and the conversation turns to validating, comparing, or shipping it. Covers YAML front matter, markdown section order, token references, component property validity, WCAG contrast findings, missing primary colors or typography, orphaned tokens, and regressions between two DESIGN.md versions.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

Eliminate generic-looking UI — anti-default checklist, custom hover states, precision typography, non-stock spacing, surface depth, and production-grade polish that separates professional from template. Use when asked to "make this look less generic", "UI looks Bootstrap-y", "looks like a template", "add polish", "impeccable UI", "production quality design", "make it look custom", "it looks like every other SaaS app", "remove default styles", or "design lacks personality". Do NOT use for: design system token architecture — see design-system-gen. Do NOT use for: animation timing specifics — see motion-design.

Model a Phase-Locked Loop (PLL) IC from its datasheet or system specs using Mixed-Signal Blockset. Without this skill, agents universally select the wrong solver and produce non-functional PLL models — 100% of unguided attempts fail. Covers Integer-N, Fractional-N, Dual Modulus architectures, loop filter design, lock time optimization, VCO phase noise configuration, and msbPllArchitectures/msbPllFoundation block assembly. Use when: PLL modeling, frequency synthesizer design, phase noise simulation, lock time analysis, charge pump design, loop filter tuning, datasheet-to-model, Mixed-Signal Blockset PLL, msbPllArchitectures.

Set up and verify a connection to an NI USRP radio (USRP E320, N300, N310, N320, N321, X300, X310, or X410) using Wireless Testbench. Use when connecting a USRP for the first time, configuring radio hardware, troubleshooting connection failures, or verifying a radio setup. Covers host inspection (OS, NIC type/speed/MTU), device discovery (findsdru, probesdru), UHD version checking, programmatic radio configuration, and basebandTransceiver verification. Also use when the user mentions USRP setup, radio not found, connection errors, dropped samples, or network configuration for SDR hardware.

The living embodiment of WinDAGs V3 — the AI orchestration platform where agents accumulate genuine expertise. Knows the full constitution, convention process, tradition positions, behavioral contracts, and derivative documents. Advises on architecture with ADR provenance, explains decisions with tradition attribution, grows source material as we build. Activate on "windags", "WinDAGs", "constitution", "convention", "why did we decide", "what does WinDAGs say", "how should we build", "architecture decision", "tradition", "behavioral contract". NOT for building specific DAGs (use windags-architect), creating individual skills (use skill-architect), or managing skill libraries (use windags-librarian).

Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate in a week", "rapid prototype", "test with users", "de-risk before building", "GV sprint", "prototype testing", or "design workshop". Also trigger when a team needs to make a critical product decision quickly, resolve stakeholder disagreements, or test risky ideas before investing in development. Covers mapping, sketching, deciding, prototyping, and testing. For ongoing experimentation, see lean-startup. For customer job analysis, see jobs-to-be-done.

Evaluates Google Cloud workloads against the Reliability pillar of the Well-Architected Framework, providing actionable recommendations for building, deploying, and managing reliable systems.

Coordinate the end-to-end pipeline from CAD or source assets to SimReady USD assets, including conversion, material and physics assignment, validation, conformance, and optional packaging.

Assesses NumPy code for cuPyNumeric migration readiness by analyzing source code against an API support manifest and GPU-scaling idioms, producing a structured verdict with per-finding reasoning.

Score a clinical ASR manifest against a chosen NIM, produce a five-section KER leaderboard, and route the user via a post-eval decision tree.

Provides practical accessibility patterns for React and Next.js, covering form labeling, semantic HTML, ARIA attributes, keyboard navigation, focus management, and screen reader support.