356 skills · sorted by relevance
当需要为 AI 定义工具接口、设计调用规范、实现工具发现与编排机制时调用此 skill。典型场景包括：设计 AI agent 的工具集、定义 JSON Schema/XML/TypeScript 格式的工具描述、实现工具权限控制与并行调度、设计子代理委托架构。 不适用于：定义 AI 身份（persona-design）、安全规则（safety-guardrails）、记忆存储（memory-system）。 关键 trigger 信号：AI 需要调用外部 API 或服务、工具数量超过 10 个需要发现机制、需要区分工具权限层级、需要子代理并行执行、工具调用涉及敏感操作需要审批。
The English summary is being prepared. Showing the original description.
Cerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.
The English summary is being prepared. Showing the original description.
Vulnerability audit and dataflow analysis built on the neug CPG engine. file_audit (default, recommended): first builds a function-level summary graph (tier1) over the entire project, then incrementally builds detailed CPGs (tier2) on demand for chosen functions; both tiers coexist in a single neug database (unified schema, cross-layer refines edges; C/Java/Python/Rust). All capabilities are exposed as CLI tool subcommands (audit/overview/build/query/methods/paths), so an agent can drive the audit step by step via shell; the audit subcommand can also run the built-in LLM loop. The same tooling also supports a dataflow analysis mode (Workflow C): no vulnerability hunting, only variable-level dataflow tracing for functions of interest, producing dataflow_analysis.json. repo_audit: multi-round LLM/Cypher audit over a full-repo CPG. Use when the user asks to audit a codebase/project for vulnerabilities, scan a project with CPG/neug, run repo_audit/file_audit, find source-to-sink taint paths, or analyze dataflow inside a function. Supports C, Java, Python, and Rust.
The English summary is being prepared. Showing the original description.
Translate existing blog posts into one or more target languages with SEO-optimized localization. Produces native-quality translations that preserve markdown structure, frontmatter, schema JSON-LD, image and chart embeds, and citation capsules. Localizes keywords, meta tags, numbers, dates, currencies, and quote styles per locale. Flags machine-translation artifacts for review. Run BEFORE blog-localize: this handles language conversion; localize handles cultural adaptation after translation completes. Use when user says "translate blog", "blog translate", "uebersetzen", "traduire", "traducir", "translate post", "blog auf Deutsch", "blog en espanol".
The English summary is being prepared. Showing the original description.
Extract a design system from a screenshot (PNG/JPG/WEBP) or a live URL and produce a schema-compliant `design.v1.json` file plus a ready-to-use agent prompt for applying the design to any website/app. When run inside the sleek-ui repository, offers to add the extracted design to the public catalog as a PR — updating `public/designs/`, `src/data/designs/`, `src/data/designs.ts`, and generating a preview. Use when users ask to "extract a design from this screenshot", "clone this site's design", "reverse-engineer the design tokens", "reskin my app to look like {site}", "generate a sleek-ui design from this URL", or provide an image/URL and want a reusable design system.
The English summary is being prepared. Showing the original description.
Create, compose, migrate, and review TypeScript runtime type guards with is-kit. Use when adding reusable guards; replacing typeof, null checks, or handwritten type predicates; narrowing unknown values; validating JSON or API responses; building collection or object schemas with struct or typedStruct; or reviewing existing is-kit usage. Do not use for one-off environment checks or validation that requires data transformation or rich error reporting.
The English summary is being prepared. Showing the original description.
Configure and operate the Neo4j Connector for Kafka (sink + source) and the native Neo4j CDC API. Covers Cypher/Pattern/CUD sink strategies, CDC-based and query-based source, exactly-once semantics, DLQ error handling, Confluent Cloud managed connector, schema registry (Avro/JSON), and native db.cdc.query cursor-loop patterns (Neo4j 5.13+ Enterprise/Aura BC/VDC). Use when streaming Kafka events into Neo4j, streaming Neo4j changes to Kafka, or querying Neo4j change events without Kafka. Does NOT handle Cypher query authoring — use neo4j-cypher-skill. Does NOT handle bulk CSV/file import — use neo4j-import-skill. Does NOT handle GDS algorithms — use neo4j-gds-skill.
The English summary is being prepared. Showing the original description.
SEO + Generative Engine Optimization (GEO) for 2026 — technical SEO, on-page optimization, structured data (JSON-LD, schema.org), Core Web Vitals, citability scoring (llms.txt, entity clarity), AI search engine optimization (ChatGPT, Gemini, Perplexity, Claude, Google AI Overviews), and brand authority building. Use when user asks to optimize a site for search engines, improve SEO, write SEO content, implement structured data, optimize for AI search/GEO, audit a page, or improve Google rankings. Do NOT use for content writing strategy (use content-marketing), performance optimization beyond Core Web Vitals (use performance-profiler), or paid ad strategy.
The English summary is being prepared. Showing the original description.
Audits and optimizes websites for search engine visibility (SEO) and AI search citation (GEO), covering technical health, E-E-A-T content scoring, domain authority, structured data, rich results, and entity signals. Use when running SEO audits, diagnosing traffic drops or ranking losses, generating Schema.org JSON-LD, checking Core Web Vitals, crawlability, robots.txt, sitemaps, hreflang, backlinks, planning content strategy or site migrations, fixing indexing issues, or optimizing for AI Overviews, ChatGPT, and Perplexity. NOT for paid ads (PPC/SEM), social media strategy, email marketing, or general web development unrelated to search.
The English summary is being prepared. Showing the original description.
Developer reference for building applications, tools, and agents on the Pi Durable agent harness (@earendil-works/pi-durable) and the pi-ai model layer. Use when writing or debugging code that imports @earendil-works/pi-durable or pi-ai: assembling a Harness over memory/SQLite/JSONL/Durable Object storage, submitting input and waiting for answers, defining tools with TypeBox schemas and structured output, calling tools from tools, hooks and guards, durable tasks with checkpoints and ownership, subagents and child tasks, documents and migrations, code mode, tool search, per-conversation environments, compaction, recovery after a crash, storage and environment conformance tests, or choosing models and providers. Also use when a durable/agent-runtime behavior question comes up: what survives a restart, why an input stayed queued, why a task is blocked or orphaned, how abort cascades, or what the Pico5 specification requires.
The English summary is being prepared. Showing the original description.
Generate Marp-compatible slide decks from structured JSON schema. Converts context into presentations for tech talks, sprint demos, and tutorials.
The English summary is being prepared. Showing the original description.
Generate MaaFramework Pipeline nodes and recognition snippets from screenshots or observed UI state. Use for OCR node generation, ROI sweep, choosing TemplateMatch/OCR/ColorMatch/CustomRecognition, preserving target-file schema style, and designing `next`/`[JumpBack]` links before merging generated nodes into pipeline JSON.
The English summary is being prepared. Showing the original description.
Cross-platform hooks reference for AI coding assistants — Claude Code, OpenAI Codex, GitHub Copilot, Cursor, Windsurf, and Amp. Covers hook authoring in Node.js (ESM and CJS) and Python, per-platform event schemas, inline-agent hooks and MCP in agent frontmatter, common JSON I/O, exit codes, best practices, and a fetch script to refresh docs from official sources. Use when writing, reviewing, or debugging hooks for any AI assistant.
The English summary is being prepared. Showing the original description.
Use when exploring unknown structured data files with dasel v3 — discover schema, list keys, find nested values, sample arrays, identify data types across JSON, YAML, TOML, XML, CSV, HCL, INI formats
The English summary is being prepared. Showing the original description.
Design, create, inspect, update, attach, detach, preview, execute, and verify reusable Vapi Structured Outputs through public API or Server SDK workflows. Use for post-call extraction, typed call artifacts, AI-versus-regex extraction, JSON Schema design, backfilling existing calls, or retrieving structured results programmatically.
The English summary is being prepared. Showing the original description.
AI content generation with OpenAI and Claude, callAIWithPrompt usage, prompt storage in app_settings, structured outputs, response format validation, multi-criteria scoring, rate limiting, JSON schema, and AI API best practices. Use when generating content, creating prompts, scoring articles, or working with OpenAI/Claude APIs.
The English summary is being prepared. Showing the original description.
Classifies raw pilot request → structured JSON {task_type, class, artifact, budget_estimate, confidence, routing_tag, resolution_path, schema_version, result_type, expected_result_kind, result_kind_resolution, hypothesis_relation}. Keyword-fast (<200ms) or Haiku fallback (<60s). Does NOT create WP or call executor.
The English summary is being prepared. Showing the original description.
Build, register, and gate AI-callable tool endpoints using the OpenSea Tool Registry (ERC-8257) on Base. Scaffold HTTPS tools with JSON Schema interfaces, register them onchain, gate access via NFT ownership, subscriptions, trait gating, or x402 pay-per-call (USDC), and call gated tools. For querying OpenSea marketplace data use opensea-api instead.
The English summary is being prepared. Showing the original description.
Normalizes and enriches AWS CloudTrail JSON logs into OCSF (Open Cybersecurity Schema Framework) format. Maps eventSource/eventName pairs to MITRE ATT&CK technique IDs using the MITRE ATT&CK STIX API.
The English summary is being prepared. Showing the original description.
显式触发的 Claude Code → Codex CLI 桥接 skill。把对话上下文 / plan / 相关文件 / 项目约定外化为 bundle 目录，调用 codex exec 并用 response.schema.json 作结构参考 + Claude Code jq 后处理校验。适用 4 场景（v1.1 起）：plan 审阅、Codex 编码、Claude-Codex 互审最多 2 轮迭代、verification-round 验证轮。
The English summary is being prepared. Showing the original description.
Research, implement, modify, and audit behavior inside Bricks Builder sites using the bundled Bricks Academy corpus, stable development workflows, and version-aware verification against an authorized active Bricks installation. Use when the requested outcome concerns Bricks elements, controls, schema, hooks, templates, styling, responsive settings, dynamic data, queries, forms, interactions, custom elements, or page JSON. Do not use merely because Bricks Builder is mentioned, for generic WordPress, PHP, CSS, or JavaScript work, or for maintaining, naming, versioning, documenting, or releasing this Skill repository.
The English summary is being prepared. Showing the original description.
Use when working on or testing imp-server and its HTTP APIs - OpenAI/Anthropic endpoints, /v1/chat/completions, /v1/messages, /v1/responses, SSE streaming, tool calling, json_schema/regex/GBNF constrained decoding, thinking/reasoning_content, cache_control/prefix cache, model loading and swapping, request priority, X-Request-Id, OTLP tracing / traceparent / Jaeger, /metrics, container env (IMP_SET), "server returns 404/garbage", API compliance. Do NOT use for CLI-only inference (imp-cli), kernel work (sm120-cuda-expert), or pure output-quality checks (check-degeneration).
The English summary is being prepared. Showing the original description.
Independent re-derivation gate for proposed changes during autonomous execution. Evaluates a change (code diff, config edit, engine evolution, schema change) against the work's authority matrix and a 4-check protocol: invariant compliance, scope authorization, detection narrowness, and regression risk. Returns structured JSON with pass/fail per check, an overall verdict (APPROVE / REQUEST_CHANGES / REJECT), and blockers. Profile-driven thresholds (strict for unattended runs, lenient for desk supervision). Use when an autonomous agent proposes an engine change, when reviewing a Claude Code-authored modification before merge, or when an unattended profile requires independent re-derivation. Trigger on: "review/approve this proposed change," "critic-gate this," "is this change safe," "is this safe to merge," "should I let this land," "run the critic." Do NOT use for handoff-readiness checks (use rootnode-handoff-trigger-check), general code review, or design-time correctness. Authority matrix required.
The English summary is being prepared. Showing the original description.
Generative Engine Optimization plus agent readiness. Use this skill whenever the user asks about GEO, AEO, LLMO, optimizing content for AI search engines (ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot), getting cited by LLMs, brand mentions in AI responses, llms.txt, robots.txt for AI crawlers, Schema.org JSON-LD, FAST framework, agent readiness, MCP server discovery, Web Bot Auth, OAuth for agents, API Catalog, agentic commerce (x402, ACP, UCP), Markdown content negotiation, or auditing a site or page for AI visibility. Also trigger when the user says "AI SEO", asks how to "rank in ChatGPT", "show up in Perplexity", "appear in AI Overviews", or wants a site to "speak to AI agents". Trigger even when the request is implicit, such as "review this article so AI search picks it up" or "make our docs agent-friendly".
The English summary is being prepared. Showing the original description.