AI Agent Skills

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic…

Data Curator - share usable open data

Synthetic data curation for post-training and structured data extraction

用于把游戏设计文章、视频、作者、栏目和网站策展为可持续的本地知识库：包括来源调研、候选筛选、证据门审核、规范入库、增量更新、来源目录、HTML 归档和灵感卡。不要用于一次性摘要、随手推荐、普通新闻浏览或不入库的纯翻译任务。

Codex skill for curating GitHub starred repositories into safe, meaningful GitHub Stars Lists.

Role 01 of the Phoenix Security spec pipeline. Cleans raw input — notes, tickets, Slack threads, customer call transcripts — into a structured CLEAN_CONTEXT block of FAC…

Recommend high-taste Google Fonts for websites based on brand tone, page type, and visual direction. Use when the user needs font selection, font pairing, or aesthetic j…

Use at session-close when a session captured several new memories, or on-demand, to consolidate, deduplicate, prune, and structure the beads memory store. Triggers on "c…

Curate Codex skills with a Hermes-style maintenance pass: usage telemetry, stale/archive candidates, pins, backups, dry-run reports, and rollback guidance.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI proje…

Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software, SDKs

docs-site structure map for the oss-docs harness structure-curator: exact paths and schemas for hugo.toml, per-locale content/<locale>/_meta.yaml, data/menu/main.yaml (4…

Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill,…

Operate skilld CLI for Skill discovery, use, installation, inspection, updates, authentication, configuration, restoration, and removal, including Repository, curator, a…

Expert guide for AI Safety, Governance, and Responsible AI in production — Constitutional AI enforcement, runtime guardrails (NeMo Guardrails 2.0, Llama Guard 3), bias a…

Role 02 of the Phoenix Security spec pipeline. Converts CLEAN_CONTEXT into an explicit, minimal SCOPE_DEFINITION — goals, non-goals, in/out boundaries, assumptions, succ…