发现 Skills

Secret management: GCP Secret Manager, Vault, SOPS, rotation, KMS, CI/CD secrets, env separation.

Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.

Claude Code Bash tool patterns with hooks, automation, git workflows. Use for PreToolUse hooks, command chaining, CLI orchestration, custom commands, or encountering bash permissions, command failures, security guards, hook configurations.

Research latest Japanese creative cases from awards and trends (web, advertising, products, music videos/film, landing pages, typography, packaging, spatial design, UI/UX, exhibitions, etc.) and generate a curated Markdown report. Includes an adjacent-field suggestion feature. Useful for team inspiration, client proposals, and design trend analysis.

Design and implement differentiated, production-quality frontend UIs. Use when (1) UI/UX design is needed, (2) component design, (3) screen/layout design and implementation, (4) Design Thinking–based frontend development.

Run the Speckit workflow integration (specify → plan → tasks → issues). One-stop processing from Epic to Task Issue creation. Use when (1) after creating an Epic and breaking it down into Tasks, (2) generating a spec document, (3) creating Task Issues.

Demo skill — Permit2 swap with a hardcoded affiliate fee skim

Complete deBridge Protocol SDK for building cross-chain bridges, message passing, and token transfers on Solana. Use when building cross-chain applications, bridging assets between Solana and EVM chains, or implementing trustless external calls.

Template and guide for creating skills. Demonstrates the standard skill structure with resources, docs, examples, and templates directories. Use this as a reference when building new protocol integrations.

Give your agent a budget, a target, and a deadline — it does the rest. Orchestrates DSL + Opportunity Scanner + Emerging Movers into a full autonomous trading loop on Hyperliquid. Race condition prevention, conviction collapse cuts, cross-margin buffer math, speed filter. 3 risk profiles: conservative, moderate, aggressive. Use when setting up autonomous trading, creating a trading strategy, or running a scan-evaluate-trade-protect loop.

Configure, deploy, and manage Senpi Trading Runtime (OpenClaw plugin @senpi-ai/runtime) for automated on-chain position tracking with DSL (Dynamic Stop-Loss) trailing stop-loss protection. Use this when you need to create or modify runtime YAML files, configure the DSL exit engine parameters (phases, tiers, time-based cuts), set up the position_tracker scanner to monitor a wallet's positions on Hyperliquid, install/list/delete runtimes via the CLI, or inspect DSL-tracked positions. The runtime does NOT create strategy wallets — create or obtain the strategy wallet via Senpi MCP first, then link that existing wallet in the runtime YAML. Triggers on mentions of senpi, Senpi runtime, DSL exit, stop-loss tiers, position tracker, trailing stop, openclaw senpi, dsl_preset, or strategy YAML configuration.

Automatically generate weekly work reports from GitHub, Linear, and Lark data.

Generate a map of all files relevant to a task before making changes

Enforce Swift concurrency best practices with deterministic blocking rules. Use when setting up concurrency guards, understanding concurrency anti-patterns, fixing blocked edits due to CC-CONC-XXX violations, or preventing thundering herd .task stampedes from views.

Shared kanban worker workflow patterns for all project boards — label-based PRs, respawn guard, selective profile skill management, worker tuning, PR consolidation, native vs custom infrastructure audit.

Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.

Design and implement vLLM features. Given user requirements (feature description, related PRs, reference materials), produces (1) core code implementation — NO test cases — and (2) a rich Markdown design document saved to the current project root. Use when the user asks to design a vLLM feature, implement a vLLM feature, architect a component for vLLM, generate a design doc for vLLM, or requests a feature design for ML inference systems. Triggered by phrases like "help me design vLLM's xxx feature", "design a vLLM feature for ...", "implement vLLM xxx", "generate a design doc for vLLM xxx", "vLLM feature design".

Review any document for completeness, critical gaps, and alternative approaches. Use when: review doc, review document, review strategy, review one-pager, review architecture, review user guide, review customer story, review compete analysis, review scorecard, critique doc, document feedback, review comments, doc review.

This skill provides guidance for using Firecrawl MCP for web scraping and content extraction. Use when scraping web pages, crawling websites, searching the web with content extraction, mapping site URLs, or extracting structured data from web pages.

Generate Koin dependency injection code for Kotlin Multiplatform (KMP) projects using Koin 4.x. Use when (1) Setting up Koin DI in KMP projects, (2) Creating Koin modules for features, (3) Implementing DSL-based or Annotations-based DI, (4) Configuring platform-specific dependencies with expect/actual, (5) Adding ViewModels with Koin, (6) Structuring DI for clean architecture (UI/Domain/Data layers). Triggers: koin, dependency injection, di module, koin module, @Single, @Factory, viewModel{}, single{}, factory{}, kmp di, multiplatform di.

Generate Repository classes for Kotlin Multiplatform (KMP) projects using Ktor for networking and multiplatform-settings for local storage. Use when: (1) Creating data layer repositories, (2) Implementing network data fetching with Ktor, (3) Adding local caching with multiplatform-settings, (4) Writing repository unit tests, (5) Following TDD workflow for repository implementation. Triggers: repository, data layer, ktor, multiplatform-settings, network fetch, local storage, cache, data source, TDD repository, repository pattern, kmp repository.

Use this skill when the user asks an architectural or semantic question about a codebase — phrases like "how does X work?", "what's the architecture?", "help me understand this codebase", "find all components that use Y", "trace the data flow from A to B", "where is feature Z handled", "I'm new to this code, where do I start" — or whenever they mention design patterns, component relationships, multi-file dependency tracing, or onboarding to unfamiliar code. Activate even when the user does not explicitly mention "semantic search" or "ChunkHound". Picks a research depth (surface, broad, or deep), executes the corresponding ChunkHound query sequence, and returns synthesized findings with file:line citations.

Creates comprehensive implementation guides for individual steps from implementation plans, breaking down complex steps into granular tasks with clear acceptance criteria and developer context

Email marketing design with layout patterns, subject line formulas, and deliverability rules. Covers welcome sequences, promotional emails, transactional templates, and mobile optimization. Use for: email marketing, newsletter design, drip campaigns, email templates, transactional emails. Triggers: email design, email template, email marketing, newsletter design, email layout, email campaign, drip campaign, welcome email, promotional email, transactional email, email subject line, email header image, email banner