Total 59,483 skills
Showing 12 of 59483 skills
Design and review cross-module changes in an existing repository through global-model reconstruction, terminology control, evidence-backed research, isolated feasibility probes, and recorded architectural decisions.
Generate Mermaid diagrams (.mmd) and export to PNG/SVG/PDF using mmdc CLI or Kroki API. USE THIS SKILL when user mentions diagram, flowchart, sequence diagram, class diagram, ER diagram, state machine, architecture, visualize, git graph, 画图, 架构图, 流程图, 时序图, 类图, ER图, 甘特图, 状态机. PROACTIVELY USE when explaining ANY system with 3+ components, API flows, authentication sequences, class hierarchies, database schemas, or state machines. Supports 17+ diagram types with fully automatic layout.
Use when generating video clips with Chinese video models — text-to-video (文生视频), image-to-video (图生视频), first/last-frame and reference-to-video across 4 platforms: Bailian (Wan/PixVerse/Kling/Vidu/HappyHorse), Jimeng (doubao-seedance), MiniMax (Hailuo), Hunyuan (hy-video)
Build, modify, debug, or verify Runway model generation in an application: discover accessible models and constraints with MCP, implement SDK calls, and wire inputs and outputs into the product UI. Use with +runway-dev. Not for Model Routers, Characters, recipes, or agent-side generate scripts.
Integrate Arcjet Guard into Python Strands Agents — wrap authored @tool with guard_tool, and put guard_hooks on Agent(hooks=) for unwrapped / MCP tools via BeforeToolCallEvent.cancel_tool. Use when asked to add Arcjet to strands / strands-agents, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python strands, not JS @strands-agents/sdk.
Refine human- or agent-facing prose by removing AI tells, filler, vague abstraction, and instruction noise without changing facts, authority, structure, or intended voice. Use for final cleanup or explicitly requested pruning of verbosity, repetition, and instruction load in technical writing, skills, agent instructions, handoffs, tickets, and reports. Exclude content design, factual review, translation, and code style.
Judge one bounded code candidate for defects, broad review, or read-only behavior parity for one stateful refactor or rewrite. Focus on exact identities, credible failure mechanisms, adversarial validation, maintainability evidence, and an evidence-backed result.
Establish the minimal causal explanation for one reproducible or directly observed failure by building and falsifying competing mechanisms. Use when the missing outcome is diagnosis rather than report validity, review, or correction delivery.
Use when renaming a spec plan and updating all references. Triggers on: "rename plan", "change plan name", "plan name is wrong", "update plan name", "fix plan name", "spec rename". Proactively suggest when a plan name is a typo or no longer reflects scope.
Use when executing or continuing a spec plan interactively. Triggers on: "spec go", "execute plan", "run plan", "continue plan", "work on plan", "start plan", "run the spec". Runs tasks with configurable breakpoints for review. Pass --bg for fully autonomous background execution.
Use when researching technical approaches before building. Triggers on: "explore options", "what are my options for", "research approaches", "compare solutions", "dev explore", "generate proposals", "help me decide between". Runs parallel proposal generation via subagents and outputs to .codevoyant/explore/.
Use when modifying an existing em plan or task files. Triggers on: "update em", "change plan", "modify epic", "add task", "remove task", "rename phase", "apply annotations", "edit plan". Applies inline > and >> annotations or accepts conversational changes to plan.md or task milestone files.