Machine learning

Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.

Use when comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether…

Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing…

Write, maintain, and migrate CHANGELOG.md files using Keep a Changelog format and best practices.

Design, review, migrate, measure, or debug PostgreSQL vector retrieval with pgvector.

Use when the user directly requests efficiency-aware multi-angle unit tests or a test report after code changes.

Manages Volcano Engine ContextSearch control-plane and application-console operations.

Volcengine VOD audio and video processing tools skill.

Use this skill when you need evidence-bounded repeat inputs, version/model/prompt factors, invariants, variance evidence, and comparison boundaries; triggers…

Use this skill when you need evidence-bounded claim-to-source relations, unsupported assertions, abstention, uncertainty, and evidence review; triggers…

Use this skill when you need evidence-bounded grounding, relevance, completeness, citation support, abstention, and answer-level evidence in RAG outputs…

Use this skill when you need evidence-bounded query variants, chunking, filters, recall/precision proxies, ranking, freshness, and retrieval evidence…

RWS (Raw Sources, Wiki & Schema) — arquitetura de base de conhecimento persistente mantida por LLM, baseada no padrão "LLM Wiki" de Andrej Karpathy.

会话观察者（v4.2 草案）：为一段 agent 工作（Claude Code、Codex、Kimi、dsh 会话，可以多个）建立并维护一份认知——任务地图：你要什么 → 走到哪 → 还在主线上吗 → 卡在哪 → 下一步，项目里现成的…

Best practices for LLM-assisted coding.

Refuse an arena.ai scrape.

Lean 4 theorem proving toolkit: search lemmas, verify proofs, repair/simplify code, and get LLM-assisted informal proofs

Test the configured text-generation model with a supplied prompt.

Single fast-execution skill for macOS / Linux / Windows app operations.

Run bounded LLM-led Kinic Wiki maintenance through inspection, evidence-backed edits, and reinspection.

基于 WeData 搭建交互式运营看板（HtmlContent 承载页面/组件 DSL，SqlSlots 承载 Datasets）。中英文环境通用。 触发词：看板/仪表盘/驾驶舱/大盘/监控视图 | dashboard/cloud dashboard/platform…

Build and navigate DSP (Data Structure Protocol) — graph-based long-term structural memory of codebases for LLM agents.

为 openrank2 / OpenRank 可视化平台生成或补齐项目风格的中文代码注释。Use when Codex needs to add, rewrite, audit, or standardize Chinese module comments, function docstrings, route…