发现 AI Agent Skills

撰写民主党派、政协、统战系统“社情民意信息”“信息专报”“参政议政信息”“建言材料”的技能。用户提到社情民意、民主党派建言、政协信息、信息稿、履职材料、问题建议稿，或只给出一个公共治理/民生/教育/医疗/科技/营商环境主题，希望你代写、补充调研、联网搜集资料、按报送层级筛题、生成初稿并多轮校验后定稿，或要求最终交付一个符合中国大陆机关公文常见版式的 `docx` 正式稿时，必须使用本技能。尤其在用户要求“像正式报送稿”“要最新政策和数据”“要按民主党派/政协写法”“要从党委政府决策视角提出问题和建议”“最后给我一个 Word 文档”时，必须调用本技能。

Dify dataset retrieve API for knowledge base chunk search/testing. Use when integrating or debugging Dify knowledge base retrieval requests, retrieval_model options, or response shaping.

Add or modify Commerce and external event subscriptions, configure event field extraction and filter rules in an Adobe Commerce app. Use when the user wants to set up event-driven workflows triggered by Commerce operations (such as order placement or catalog changes) or third-party systems. Requires a base app initialized with commerce-app-init.

Use this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations before runtime configuration or quick-start setup.

Run a Python training/eval script directly in an existing local virtualenv — no docker, no container. Implements the four-verb consumer contract (submit/status/logs/cancel) over a vendored process-lifecycle runner with durable on-disk state, PID-reuse-safe identity, and process-group cleanup. Use for docker-free local execution, plain-Python model scripts, fast HPO/AutoML trial smokes, or hosts where containers are unavailable. Trigger phrases include "run in my venv", "no docker", "virtualenv execution", "local python training", "run this training script directly".

Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations. Use when users need competitive analysis, market positioning strategy, differentiation tactics, or "how do I stand out?" guidance across any domain (portfolios, products, services). NOT for market size estimation or financial forecasting.

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8. Use after a checkpoint passes promotion, when choosing a quantization format for a target device, or when an exported model fails its smoke test.

Standardized error response handling between frontend and backend. Covers error structure, status codes, and consistent error handling. USE WHEN: user asks about "error handling", "API errors", "error response format", "status codes", "error messages", "validation errors" DO NOT USE FOR: logging - use logging skills, exception handling - use language-specific skills

Optimize Apify Actor performance: crawl speed, memory usage, concurrency, and proxy rotation. Use when Actors are slow, consuming too much memory, or being blocked by target sites, or when a crawl is too expensive per run. Trigger with "apify performance", "optimize apify actor", "apify slow", "crawlee concurrency", "apify memory tuning", "scraper performance".

Agent skill for repo-architect - invoke with $agent-repo-architect

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation. Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end.

Video enhancer that upscales resolution and improves video quality using AI. Upload low-quality, blurry, or old footage and the AI enhances it: upscale 480p to 1080p, sharpen blurry frames, reduce noise and grain, improve lighting in dark scenes, and restore detail in compressed videos. Handles AI video upscaling for old family videos, security camera footage enhancement, low-light footage brightening, compression artifact removal, and resolution upscaling for printing or large displays. Describe what needs fixing: "make this sharper" or "upscale to 4K" or "brighten the dark parts" or "remove the grain." Combine enhancement with editing in one session: enhance quality, then trim, add subtitles, or adjust colors. No video restoration software needed. Export enhanced video as MP4. Supports mp4, mov, avi, webm, mkv.

Use Tailwind CSS to style React Native components across web and native

Write a project brief — problem space, constraints, audience, and success criteria. Use at kickoff for one specific project. For long-horizon aspiration use `north-star-vision`; for reusable decision rules use `design-principles`.

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

Migrates Kotlin Multiplatform (KMP) projects to Android Gradle Plugin 9.0+. Handles plugin replacement (com.android.kotlin.multiplatform.library), module splitting, DSL migration, and the new default project structure. Use when upgrading AGP, when build fails due to KMP+AGP incompatibility, or when the user mentions AGP 9.0, android multiplatform plugin, KMP migration, or com.android.kotlin.multiplatform.library.

Shared PR opener for the auto pipeline — commits the worktree, pushes, reuses an existing PR or opens a ready (non-draft) PR against the configured base branch with the unified body template, applies the full SDLC label set with rationale comments, and for issue-driven runs hands the issue back and releases the lock. Emits the `PR:`/`Issue:` chaining reference lines.

Use when a user asks to write or revise fiction in the Hemingway manner, or asks for strong de-AI on a story; applies Sepia's built-in Hemingway voice profile.