发现 Skills

Build a promotion case and produce a Promotion Case Pack (target role + timeline, ladder mapping, evidence log, impact narrative, manager alignment plan, sponsor/visibility map, submission-ready promo doc). Use for promotion packet, getting promoted, leveling up, career ladder, promotion committee. Category: Career.

Manage the lifecycle of sub-agents: create or update agent packages, validate cross-surface agent contracts, evaluate routing behavior, tighten invocation boundaries, tune Codex runtime defaults, install or publish agents, or audit an agent library. Use only when the request is explicitly about agents or agent libraries, not for ordinary coding, implementation, or general project planning.

In-depth analysis of an advisor's publications. Analyzes trends in the evolution of research directions, collaboration networks, and publication rhythm to help students understand an advisor's academic trajectory and future directions.

Turn an approved TechnicalSpec and already-implemented tests into production-grade feature code: first record a baseline, then implement the feature without changing the spec semantics, run validations within the agreed scope, and produce a DeliveredChange. Trigger phrases: implement feature, develop per spec, feature implementation, implement from spec.

PDF 综合操作工具：提取、合并、注释、表单处理

Control Philips Hue lights/scenes via the OpenHue CLI.

Use for agent lifecycle hooks, tool mocks, intervention, sub-agent calls and context compression.

Use for splitting heavy domains into capability-level modules (atomic components) across page, portal, share, or micro-app hosts, sinking state (state sinking) and replacing mode/readOnly flags. For simple component splits, use React.

Use for application prompts, generateObject/generateText, model selection and generation tracing. Excludes provider adapters and agent snapshots.

Generates comprehensive, Medium-formatted code tutorials for the LlmTornado API with examples, explanations, and best practices.

Use when you need to lookup documentation for NixOS configuration, Nix packaging, Nix functions or anything else related to Nix.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Cloud migration strategies for AWS, GCP, and Azure. Use for lift-and-shift, replatforming, and cloud-native architecture design.

Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use when writing a PRD, documenting product requirements, preparing a feature spec, or reviewing an existing PRD.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.

File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.

Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.

Coverage analysis measures code exercised during fuzzing. Use when assessing harness effectiveness or identifying fuzzing blockers.

Create and review high-fidelity UI screens, web/app prototypes, interaction demos, design variants, HTML visual artifacts, slides, motion demos, and design direction explorations. Use when the user asks for UI mockups, prototypes, app screens, web screens, Figma/design work, visual layouts, design variants, HTML demos, or when grill-with-docs identifies feature business scope that includes an interface (web, mobile app, dashboard, admin panel, onboarding, checkout, settings, forms, flows, or any user-facing screen). Before creating or editing UI for a feature, ask the user whether they want layouts/screens created or edited and where the work should live (Figma, local HTML prototype, existing codebase, screenshots, or another design surface). All user-facing communication and reports must use caveman style.

Use when implementing new functionality or fixing bugs. Write a failing test first, make it pass, then refactor.

The central orchestrator skill for the "Journey to the Digital Twin" consulting pipeline. Coordinates the flow between specialized sub-agents.

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design.