Top Agent Skills

阅读理解故事文本，总结人物、关系、情节，整理成流畅大纲。适用于快速了解故事核心、为剧本创作提供大纲基础

基于故事文本提炼主要情节与要点，生成完整故事梗概。适用于快速了解故事内容、剧本改编、项目推介

全面分析故事五元素：题材类型、故事梗概、人物小传、人物关系、大情节点。适用于深度分析故事、剧本改编准备、故事开发文档制作

基于大情节点，深入分析并生成详细情节点描述及情节发展说明。适用于细化故事大纲、指导剧本写作、分析情节内在逻辑

Run the Ouroboros specification-first development loop: reduce ambiguity with a Socratic interview grounded in live git data (commits, churn, contributors), freeze an immutable seed/spec, render the execution plan through spec-kit (/speckit.plan → /speckit.tasks), execute against that contract through cli-anything agent-native CLI harnesses (cli-hub, --json evidence), verify before claiming success, and keep looping until completion is actually verified. Use when the user wants spec-first clarification, git-aware interviews, immutable requirements, drift-aware implementation, harness-driven execution, or a persistent completion loop that should keep going until tests / checks / acceptance criteria pass. Triggers on: ooo, ouroboros, interview, seed, run workflow, evaluate, evolve, ooo ralph, specification first, socratic interview, git-aware interview, ambiguity reduction, execution plan, cli harness execute, persistent completion.

Run Comet's Opik — open-source LLM observability, evaluation, and optimization — from one routing-first skill: install the Python/TypeScript SDK, stand up a server (Comet.com cloud, Docker Compose via `./opik.sh`, or Kubernetes/Helm), wire tracing through `@opik.track` or one of 50+ framework integrations (OpenAI, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, DSPy, Ollama, Bedrock, Vercel AI SDK, …), score outputs with LLM-as-a-judge metrics (Hallucination, Moderation, Answer Relevance, Context Precision), and run Datasets/Experiments evaluations including PyTest CI gates. Use when the user wants LLM tracing, prompt evaluation, production LLM monitoring, agent optimization, or guardrails with Opik. Triggers on: opik, comet opik, opik configure, opik.sh, llm observability, llm tracing, llm as a judge, hallucination metric, prompt evaluation, opik dashboard, opik guardrails, agent optimizer.

Turn natural-language descriptions into editable `.drawio` diagrams and export them to PNG / SVG / PDF / JPG via the native draw.io desktop CLI, or turn an existing codebase (Python / JS-TS / Go / Rust) into an auto-laid-out structure diagram. Wraps Agents365-ai/drawio-skill: 6 diagram presets (ERD, UML class, sequence, architecture, ML/DL, flowchart), search across 10,000+ official AWS/Azure/GCP/Cisco/K8s/UML/ BPMN shapes, 321 AI/LLM brand logos, vision self-check + auto-fix, and a 5-round iterative refinement loop. No MCP server, no daemon — runs from a single SKILL.md and the draw.io CLI. Use when the user wants polished, precise, exportable diagrams or wants to visualize code structure. Triggers on: drawio, draw.io, drawio diagram, architecture diagram, ERD, UML diagram, sequence diagram, flowchart, network diagram, visualize codebase, code structure diagram, class hierarchy, export diagram png/svg/pdf, AWS/Azure/GCP icon, draw.io shapes.

Generate, convert, preview, and integrate retro game sound effects with raysan5/rfxgen. Use when a user needs coin, laser, explosion, power-up, hit, jump, or blip SFX; wants `.rfx` parameters converted to WAV/raw/C headers; needs batch CLI generation; or must build and troubleshoot rFXGen. Triggers on: rFXGen, rfxgen, sfxr, chiptune SFX, .rfx, procedural game sound, or sound preset.

Moves tracker issues through a structured triage state machine with category and readiness decisions; use to evaluate or prepare work items for implementation.

Assist with Colibri: pure-C LLM inference engine for running GLM-5.2 (744B MoE) on consumer machines with ~25 GB RAM. Use when setting up, building, converting models, running inference, configuring expert streaming and caching, optimizing speculative decoding (MTP), GPU integration, and integrating Colibri into production pipelines. Includes build setup, model download & conversion, chat/inference modes, performance tuning, and API integration patterns.

Fast, accurate, and comprehensive multiline text measurement and layout library for JavaScript/TypeScript — without DOM reflow. Use when the user needs to calculate paragraph heights, line counts, manual line layouts (text flowing around floated images), or rich text rendering (emoji, CJK, RTL) on DOM, Canvas, or SVG targets. Covers npm install, core API (prepare/layout, prepareWithSegments/layoutWithLines), and options (whiteSpace, wordBreak, letterSpacing). Triggers on: pretext, text measurement, text layout, paragraph height, line layout, text reflow, canvas text measurement, DOM reflow.

Turn any GitHub repo, local folder, PR, or markdown/Obsidian vault into an interactive architecture map with CodeFlow — a zero-build single index.html browser app (React 18 + D3.js from pinned CDNs) that runs 100% client-side with no backend and no data collection. Pick an input (public repo, private repo with a local token, local files, PR URL, markdown vault), choose a visualization mode (folder/layer/churn/blast), and read the analysis — dependency graph, blast radius, code ownership, heuristic security scanner, pattern/anti-pattern detection, A–F health score, activity heatmap, PR impact — then export JSON/Markdown/text/SVG/PDF or wire the self-updating CodeFlow Card SVG onto a README.

Route goalflow (wanmol/goal-flow) work — a LangGraph framework that combines workflow graphs with agent loops — into exactly one mode: fit check, transpiling a Dify DSL export into runnable LangGraph Python, authoring workflow nodes and edges, building an `agent_kit` loop with middleware and a harness, wiring the serving layer (data adapters, SSE streaming, HITL, Redis/MySQL, API-key registration), or running the pre-publish security gate. Use when the user wants Dify's visual design without Dify's runtime, a graph node that hosts an agent loop, an OpenAI-compatible wire protocol over their own workflows, or prompt-injected `SKILL.md` capabilities. Triggers on: goalflow, goal-flow, dify to langgraph, dify transpiler, dify DSL export, BaseWorkflow, agent_kit, AgentBaseNode, DataAdapter, chunk processor, HITL interrupt, dify2langgraph. Route plain graph-API questions to `langgraph-fundamentals` and `langgraph-workflow`.

Claude Code hook library — pre-built PreToolUse/PostToolUse hooks for common guardrails, auto-formatting, workflow automation

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

Install, configure, and use the Unity Command Line Interface (CLI) for automated production workflows, project management, and cloud integration. Use when setting up CLI-based build automation, CI/CD pipelines, Editor/module management, authentication, or localhost API calls via the experimental Unity Pipeline package. Designed for verifiable, machine-readable game production workflows where the build machine must be describable and tests must return evidence. Triggers on: Unity CLI, unity command line, unity automation, unity ci/cd, unity build script, unity pipeline, unity production workflows.

Reuse a running Chrome session for browser automation via Playwriter CLI + MCP. Use when the task depends on the browser the user already has open — existing logins, cookies, extensions, passkey-friendly flows, or live-tab continuity. Route repeatable fresh-browser or CI-style checks to `browser-harness` instead.

Turn a PR, diff, merge request, or patch stack into one evidence-first review brief with severity, missing-proof checks, and route-outs.

Route academic-figure work into the lightest workable PaperBanana mode instead of jumping straight to a full multi-agent generation run. Use when the user needs publication-quality methodology diagrams, statistical plots, figure evaluation, polishing an existing figure, batch/sweep generation, or a full-paper figure package from text or PDF. Even if the user does not say "paperbanana" — also triggers on: academic figure, methodology diagram, publication figure, generate diagram from paper, statistical plot from CSV, figure evaluation, polish figure, NeurIPS/ICML figure, arxiv illustration, plan-then-refine diagram pipeline.

Make any software agent-native with HKUDS CLI-Anything — four routed modes: install ready-made harnesses via CLI-Hub (cli-hub list/search/info/install/launch), give agents the cli-hub-meta-skill for autonomous discovery, generate a new harness from any codebase/repo via the 7-phase /cli-anything pipeline, or iterate with :refine/:test/:validate; 40+ harnesses, 2,461 tests, Click CLIs with REPL + --json.

Generates game-ready sprite bundles from a text description, including character animations, 8-direction sprite sets, and exports to sprite sheets, manifest.json, Aseprite JSON, GIF/APNG, and individual PNG frames.

Turns vague features, bug clusters, roadmap items, or launch work into an execution-ready planning packet by choosing the right packet type, separating discovery from delivery, and making blockers, dependencies, and the next move explicit.

Detect and exploit Server-Side Template Injection vulnerabilities across multiple template engines including Jinja2, Twig, Freemarker, and Velocity, with payloads for sandbox escape and remote code execution. Includes detection methodology, bypass techniques, and fix patterns.

Detect and exploit DOM-based XSS vulnerabilities by auditing JavaScript for tainted data flow from controllable sources to dangerous sinks, with payloads and bypass techniques for client-side testing.

Stored XSS (persistent XSS) occurs when attacker-supplied input is saved server-side and later rendered unencoded to other users. Common injection points include profile fields, comments, forum posts, file upload filenames, and application logs. Detect via PHP `$_GET/$_POST/$_REQUEST/$_FILES`, ASP `Request.Form`, JSP `request.getParameter`, and BeEF hook injection. Tools: Burp Suite, OWASP ZAP, BeEF, PHP Charset Encoder, Hackvertor.

OS command injection occurs when user input is passed unsanitized to a system shell via dangerous APIs: Java `Runtime.exec()`, Python `os.system/subprocess`, PHP `system/shell_exec/exec/proc_open`, C `system/exec`. Detect via pipe `|`, semicolon `;`, `&&`, `||`, backtick, `$()` operators, and time-delay payloads (`sleep 5`). Tools: Commix, Burp Suite, OWASP WebGoat.

Open redirect playbook. Use when URL parameters, form actions, or JavaScript sinks control navigation targets and may redirect users to attacker-controlled destinations.

PHP type juggling and weak comparison (`==`) bypass. Use when authentication, HMAC/signature checks, or token validation uses loose equality, numeric coercion, or hash comparisons without strict types — common in legacy PHP and CTF-style code paths.

CRLF injection playbook. Use when user input reaches HTTP response headers, Location redirects, Set-Cookie values, or log files where carriage-return/line-feed characters can split or inject content.

Exploit path traversal and local/remote file inclusion (LFI/RFI) via URL parameters, cookies, and hidden fields using ../ sequences, URL encoding (%2e%2e%2f), double encoding (%252e%252e%255c), Unicode bypasses (..%c0%af), and Windows UNC paths. PHP include/require with $_GET/$_POST/$_COOKIE pattern. Target /etc/passwd, boot.ini, web.config. Tools: DotDotPwn, WFuzz, Burp Suite, ZAP.

Entry P1 category router for file access and upload workflows. Use when testing download endpoints, file paths, local file inclusion, upload flows, preview pipelines, archive extraction, or storage and sharing boundaries.

Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities

DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers

Catches type errors before runtime using static type checking with gradual typing, strict mode, and Protocol support for Python projects.

Systematic workflow for verifying bug fixes to ensure quality and prevent regres...

shadcn/ui component library for React with Tailwind CSS - copy-paste accessible components with full code ownership

Creates elaborate, multi-component HTML artifacts using React, Tailwind CSS, and shadcn/ui, then bundles them into a single self-contained HTML file.

Phoenix operations and deployment: releases, runtime configuration, clustering, libcluster, telemetry/logging, secrets, assets, background jobs, and production hardening on the BEAM.

Kysely type-safe SQL query builder - End-to-end type safety from schema to queries, migrations, transactions, plugins

LangGraph framework for building stateful, multi-agent AI applications with cyclical workflows, human-in-the-loop patterns, and persistent checkpointing.

Reporting pipelines for CSV/JSON/Markdown exports with timestamped outputs, summaries, and post-processing.

Minimal, unopinionated state management library for React with simple hook-based API, no providers, and minimal boilerplate for global state without Redux complexity.

Vue 3 - Progressive JavaScript framework with Composition API, reactivity system, single-file components, Vite integration, TypeScript support

Environment variable validation, security scanning, and management for Next.js, Vite, React, and Node.js applications

Supabase open-source Firebase alternative with Postgres, authentication, storage, and realtime subscriptions. Use when building full-stack applications requiring integrated backend services with Next.js, React, or Vue.

Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context

Vendor-neutral framework for scoring software health, estimating technical debt, assessing cloud readiness and open-source safety, and communicating quality to business stakeholders. Use when you need to quantify code health at the application or portfolio level rather than fix individual findings.

Severity-tagged code review checklist (CRITICAL/HIGH/MEDIUM/LOW) used by code-critic agent

Production Fastify (TypeScript) patterns: schema validation, plugins, typed routes, error handling, security hardening, logging, testing with inject, and graceful shutdown

Test quality inspection framework for reviewing test coverage, identifying gaps, and ensuring comprehensive validation

Automated guided vehicle route planner. Use when json agv tasks, csv agv tasks, checking agv status.

bcc reference tool

Use when calculating CNC speeds and feeds, selecting cutting tools, referencing G-code commands, looking up material cutting data, or computing machining parameters.

Crl reference tool. Use when working with crl in security contexts.

Distributed control system manager

Plan resources, track inventory, and coordinate departments with reporting. Use when allocating resources, managing stock, or tracking department KPIs.

Generate GPT API request payloads. Use when building chat completions, embeddings, fine-tuning data, or estimating API costs.

ISO standard compliance checker

Manufacturing execution system tracker

Process text with NLP. Use when tokenizing, analyzing sentiment, extracting entities, summarizing documents, or measuring similarity.