发现 Skills

C4 model architecture diagramming tool. USE WHEN: C4, architecture diagram, system context, container diagram, component diagram, C4 model, architecture visualization. Provides C4-to-Mermaid/PlantUML generation, documentation capabilities, and code-as-architecture support.

Generate retention/nurture email sequences (5–7 emails) to reduce churn, reinforce purchase decisions, and increase customer lifetime value using RMBC principles.

Generate RMBC-structured one-time offer (OTO) / upsell page scripts — post-purchase pages that capitalize on buying momentum with a complementary offer.

Create a code repository from a template, and/or update an existing repository incrementally by applying parts of a template that contains examples for tools such as make, pre-commit Git hooks, Docker, and quality-check tooling.

Create and validate skills. USE WHEN create skill, new skill, skill structure, canonicalize. SkillSearch('createskill') for docs.

Audit and improve SwiftUI runtime performance from code and architecture review. Use for requests to diagnose slow rendering, janky scrolling, high CPU or memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient.

Fetch secrets and create/manage 1Password items via CLI. Use when needing API keys, tokens, or credentials, or when storing new secrets. Ask user for the 1Password secret reference (op://Vault/Item/field format) rather than the actual secret.

Provide expert C++23 modernization advice, idiomatic refactorings, and examples that reference cppreference.com. Use when a user asks to modernize, refactor, or explain C++ code; always target C++23 and cite cppreference.com for language and library details.

Regenerate DBX code after making changes to .dbx schema files. Runs code generation, shows diff summary, validates compilation, and reports any errors.

Run unit tests that require PostgreSQL. Use this skill when the user wants to run tests with PostgreSQL database backend. Automatically handles checking for and configuring a PostgreSQL Docker container.

Run unit tests that require the Spanner emulator. Use this skill when the user wants to run tests in packages like satellite/metabase, satellite/metainfo, or any other tests that interact with Spanner. Automatically handles checking for and configuring the Spanner emulator environment.

> **Type:** Rigid > **Trigger:** Implementation complete, all tests pass, ready to integrate work

Correct subtitle files (.srt) generated from speech recognition. Use when the user uploads subtitle files and asks to correct, fix, or proofread subtitles, especially for technical content like programming tutorials, AI/ML courses, or any content with domain-specific terminology. Supports Chinese and English subtitles with intelligent error detection and correction while preserving exact timeline information.

[full] [spec] Use when analyzing specs, writing specifications, generating checklists, or writing constitutions

UI architecture and component development specification. Covers shadcn/ui integration, Tailwind CSS usage, animation standards, and custom component principles.

Calendar management and scheduling. Create events, manage meetings, and sync across calendar providers.

Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and deliver complete work products.

Use at the start of any conversation — establishes how to find and use skills and requires invoking a skill before ANY response, including clarifying questions.

Perform an in-depth analysis of the current project's architecture, Agent configuration, and MCP integration, and generate an architecture document in Chinese.

Build release binaries and install them into ~/.local/nils-cli.

Use the Synth AI SDK end-to-end for policy optimization (GEPA), graph optimization, eval, and inference

Guided end-to-end feature development workflow (discovery → codebase exploration → clarifying questions → architecture → implementation → review → summary). Use when implementing a new feature or significant change and you want a structured, question-first approach.

Use criminal policy statistics and studies portal for crime trends, victimization studies, and justice-policy evidence.

Query National Audit Office publications and audits to extract findings on public-sector performance and governance operations.