发现 Skills

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect — coordinates parallel sub-agents to locate, analyze, and synthesize findings.

Coder CLI commands for workspace management, templates, and platform operations

Build, extend, and operate Sherlock — an OSINT tool for hunting usernames across social networks and online platforms. Use when the user asks about Sherlock, OSINT username enumeration, social media footprinting, account discovery across platforms, or building a digital profile of a target. Covers installation, single and bulk username searches, output formats (text, CSV, XLSX), filtering by site, proxy and Tor support, NSFW site inclusion, false positive mitigation, and integration with theHarvester and SpiderFoot for comprehensive OSINT investigations.

OpenRouter API integration for unified access to 400+ LLM models from 70+ providers. Use when building applications that need to call OpenRouter's API for chat completions, streaming, tool calling, structured outputs, or model routing. Triggers on OpenRouter, model routing, multi-model, provider fallbacks, or when users need to access multiple LLM providers through a single API.

WHAT: Route ambiguous HE requests to the right lifecycle stage. Use when intent mixes brainstorm, spec, plan, work, review, or aliases.

Estimate single-phase incompressible pipe pressure drop, Reynolds number, Darcy friction factor, and head loss. Use when a user asks for chemical engineering, process engineering, applied science, or statistics work matching this scope.

Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text actually reflows, heights are computed, layouts are dynamic. 30KB overhead, zero deps. Smart API routing: picks the right Pretext patterns for each design type. Use when: "finalize this design", "turn this into HTML", "build me a page", "implement this design", or after any planning skill. Proactively suggest when user has approved a design or has a plan ready. (gstack) Voice triggers (speech-to-text aliases): "build the design", "code the mockup", "make it real".

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS. Includes component scaffolding, performance optimization, bundle analysis, and UI best practices. Use when developing frontend features, optimizing performance, implementing UI/UX designs, managing state, or reviewing frontend code.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error.

Obtains Figma design context with browser fallback when MCP is rate-limited. Use when implementing UI from Figma and MCP returns rate limit errors, user mentions being rate-limited, or browser-based extraction is explicitly needed. Complements the official implement-design skill.

Guide for implementing Obsidian knowledge management — vault operations, plugin development, URI scheme automation, Markdown extensions, and Local REST API integration. Use this when working with Obsidian vaults, creating plugins, automating note workflows, querying notes via the API, or implementing knowledge-graph features.

Understand existing codebase patterns and context to inform feature judgement.

Generate AGENTS.md for AI agent navigation. Covers build/test commands, coding conventions, task routing, and codebase structure. Use for /init workflow or when creating agent-readable repository documentation. Examples: - user: "/init" → full AI navigation AGENTS.md + skill recommendations - user: "/init basic" → minimal AGENTS.md structure only - user: "Create AGENTS.md for this repo" → assess complexity, generate navigation doc - user: "Document codebase for AI agents" → structured AGENTS.md with task routing

Create and manage OpenCode slash commands. Use for defining /command shortcuts, template syntax, argument interpolation, and workflow composition. Use proactively when user says "create a command", "slash command", "/command", "shortcut for", or asks about command frontmatter options. Examples: - user: "Create a /review command" → design command with description, optional agent routing - user: "How do I pass arguments to commands?" → explain $ARGUMENTS, $1, $2, `!shell`, @file - user: "Make a command that runs tests" → create command with shell interpolation

Systematically analyze existing media to extract transferable elements for new settings. Use when adapting TV, film, or games to fiction, translating tropes across genres, or transforming genre elements for new contexts.

Create fables that embody paradoxical wisdom without resolving into simple morals. Use when exploring tensions that can't be resolved, when you need narrative forms that bypass analytical defenses, or when creating teaching stories.

Manage long-term fate and fortune across a shared world. Use when powerful entities feel permanent, when the world becomes static, when you need probabilistic death/fall mechanics, or when campaigns need world-level consequences that persist. Operates above the game-facilitator level.

Create presentation slides in Markdown format (Deckset/Marp compatible). Use when user requests to create slides, presentations, or convert documents to slide format. Handles image positioning, speaker notes, and proper formatting.

Build and launch the app in the iOS Simulator and enable remote previewing from an iPhone via TrollVNC. Use this when asking a user to verify an implementation, when someone requests a simulator preview, VNC preview, or device check, or when you want to show the results of UI changes.

Developing, running, and testing ncps

Guides kcli configuration and provider setup. Use when setting up ~/.kcli/config.yml, configuring providers (KVM, AWS, GCP, Azure, etc.), or managing profiles.

AI-powered Telemetry Validator Agent that verifies instrumentation works in sandbox environments. Use when: (1) Validating OTel spans are emitted correctly, (2) Verifying correlation headers in Kafka messages, (3) Confirming OpenLineage events for data pipelines, (4) Generating validation evidence for merge approval. Triggers: "validate telemetry", "verify instrumentation", "check OTel spans", "validate correlation headers".

The awesome PPT format generation tool provided by Baidu.