发现 Skills

Standards for Hilt setup, scoping, and modules

Automatically fix code formatting issues using mojo format, markdownlint, and pre-commit hooks. Use when formatting checks fail or before committing code.

Build and deploy on Cloudflare's edge platform. Use when creating Workers, Pages, D1 databases, R2 storage, AI inference, or KV storage. Triggers on Cloudflare, Workers, Cloudflare Pages, D1, R2, KV, Cloudflare AI, Durable Objects, edge computing.

Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio, Jan, OpenWebUI), or in secure/closed environments. Triggers on local LLM, Ollama, LM Studio, Jan, air-gapped, offline AI, Serena, local inference, closed network, model routing, defense network, secure coding.

Sets up and configures Hookdeck Outpost for outbound event delivery to customer endpoints. Use when sending webhooks to customers, building webhook delivery infrastructure, configuring destinations (HTTP, SQS, RabbitMQ, Pub/Sub, EventBridge, Kafka), or managing tenants and subscriptions in Outpost.

Use this skill when generating React forms with React Hook Form, Zod validation, and shadcn/ui components. It applies to creating entity forms, character editors, location forms, data-entry forms, or any form that requires both client- and server-side validation. Trigger terms include create form, generate form, build form, React Hook Form, RHF, Zod validation, form component, entity form, character form, data entry, and form schema.

Contract-driven coding workflow. Use when implementing any module/features based on one or more *.contract.md documents; enforces Preconditions/Conformance sections and clause traceability.

Activate collaborative pair programming mode. Friendly coding partner who thinks aloud, explains decisions, and teaches while coding. Use when working through implementation together, learning new concepts, or collaborative problem-solving.

Automated penetration testing — web, API, browser, GitHub, and local code. Zero false positives. Use when user wants to hack-test their app, find vulnerabilities, or run security pentesting.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Deep-dive into a codebase or folder to understand its architecture, functionality, and implementation details. Produces a structured research report in research.md (in Chinese). Use when asked to research, analyze, study, or deeply understand a codebase, project, or folder.

Optimize prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts.

Trigger: Invoke when you have proposed a plan, hypothesis, or judgment that needs to be tested in practice and improved through trial-and-error, iteration, or post-action review. Common signals include experiment, prototype, validate, iterate, feedback loop. Use this skill to move from action to understanding and back to action in a spiral learning loop.

Add a configurable selector widget (HomeWidget) to a Flutter plugin, allowing users to enter configuration, select data, and render dynamic content. Core features: (1) configure a dataSelector to persist required identifiers and display fields; (2) pass an id via a controller and provide interfaces to fetch/refresh the latest data; (3) support navigation to a detail page.

GDS sphere health monitoring — drift detection, regime change tracking, alert response, and periodic health assessment. Use when user asks to "check sphere health", "monitor drift", "are there any alerts", "what changed since last time", "detect regime changes", "find emerging anomalies", "temporal health check", or "is the sphere healthy". Requires hypertopos MCP server with temporal data.

Find and identify CCSPlayer_WeaponServices_PickupItem , CCSPlayer_WeaponServices_CanUse and CCSPlayer_WeaponServices_EquipWeapon functions in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or libserver.so to locate the weapon pickup functions. CCSPlayer_WeaponServices_PickupItem is a virtual function on CCSPlayer_WeaponServices found via "Player.PickupGrenadeAudible" string xref. CCSPlayer_WeaponServices_EquipWeapon is called within PickupItem. Trigger: CCSPlayer_WeaponServices_PickupItem, CCSPlayer_WeaponServices_EquipWeapon, PickupItem, EquipWeapon, Player.PickupGrenadeAudible, item_pickup

Structure stories around protagonists who refuse to acknowledge what they're becoming. Use when exploring self-deception, moral transformation, or the gap between self-perception and reality.

Structure scenes and control pacing using scene–sequel rhythm. Use when individual scenes work but don't accumulate, when pacing feels off (too rushed or too slow), when transitions feel mechanical, or when readers can follow but aren't compelled forward. Based on Dwight Swain's Goal-Conflict-Disaster and Reaction-Dilemma-Decision structure.

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Includes critical guidance on choosing between Agents SDK (infrastructure/state) vs AI SDK (simpler flows). Use when: deciding SDK choice, building WebSocket agents with state, RAG with Vectorize, MCP servers, multi-agent orchestration, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors.

Generate or update documentation from code analysis

MySQL/MariaDB database inspection and queries. Use when investigating table schemas, running queries, checking processlist, replication status, InnoDB engine status, or lock contention.

PostgreSQL real-time activity monitor. Show running queries, locks, blocking chains, and per-database stats. Use when debugging slow queries, investigating locks, or monitoring database load.

Track AI engine brand narratives. Use when: detecting narrative drift, misrepresentation, or competitor narrative gains over time.

SEO content brief creation with keyword research, search intent analysis, and content structure. Covers SERP analysis, heading hierarchy, word count targets, and internal linking strategy. Use for: content briefs, SEO writing, blog strategy, content planning, keyword targeting. Triggers: seo content brief, content brief, seo brief, keyword research, search intent, content strategy, blog brief, seo writing, content planning, keyword targeting, serp analysis, content outline, seo article, blog seo