AI Ml AI Skills

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring…

Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections —…

Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete (listing datasets and data items, reading raw…

Read the user's coding preferences from /memory/coding-prefs.md before making non-trivial style decisions, and append new preferences when the user gives durable feedback.

Generate synonyms for words or phrases. Use this skill when the user needs alternative words with similar meanings, wants to expand vocabulary, or seeks varied expressions for writing.

Turn a recorded software failure into a reproducible bug report with timestamps and observed behavior.

macOS / Windows 只读存储分析助手（自动识别系统）。扫描整机磁盘占用，找出 占空间大户，把每一项分成 🟢可自动清理 / 🟡需人工判断 / 🔴谨慎清理 三级并给出 可执行处置方案，生成排版精美、可折叠、命令可一键复制的交互式 HTML 报告，并可 起本地服务在网页上一键删除（移废纸篓/直接删）。扫描全程只读。务必在以下场景…

AI audio editing pipeline: Whisper word-level transcription → Claude segment classification (KEEP/CUT_FILLER/CUT_FALSE_START/CUT_STUTTER/CUT_DEAD_AIR) → ffmpeg with 40ms qsin crossfades and room-tone…

WebSocket listener that SDK workers connect to. Use to expose the engine to trusted (internal) and untrusted (RBAC-protected) workers, gate function and trigger registration, and audit or transform…

Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative Claude review. Use when the user says "refine my approach",…

TypeScript expert for type system, generics, utility types, and strict mode patterns

数学研究任务路由器。用户提出找问题、查文献、推公式、做计算、写证明或形式化验证，但当前瓶颈尚未明确时使用；每次只选择一个主 skill。

Use when configuring ArgoCD in KubeSphere DevOps, including GitOps deployments, application management, SSO setup, or troubleshooting ArgoCD issues

AI Berkshire skill: 时代α捕手：高增长核心资产的识别-验证-持有框架. Source: skills/era-alpha.md.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with…

用代码制作图形、文字或界面动画视频，输出 MP4 和可编辑源码，最长 20 分钟。适用于动效作品集、产品片、UI 动效、动态排版、Logo 片头、生成艺术与讲解视频；支持独立选择 BGM/音效来源、用户口播，以及用用户提供的口播稿通过 TTS 合成语音。不用于实拍制作、写实人物生成或一般视频剪辑。

Add environment variable

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with…

Draft a complete contract or agreement with a pre-signing risk checklist, not legal advice, delivered as a Word document

Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API…

Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

小说、创意与大纲到可演剧本的改编方法。Used for confirmed script and short-drama production.

Use when choosing an output format for extracted documents — plain text, markdown, djot, HTML, JSON, or DocTags. Maps consumer (LLM, parser, archive) to the right `--format` / `--content-format` pair.

Code review guidelines covering code quality, security, and best practices.

生成 MySQL 查询报表。当用户需要查询 MySQL 数据库并以报表形式展示结果时使用此技能，包括：统计销售数据、分析用户行为、生成业务报表、查询业务指标等。

Single-pass mini research for AwesomeWebpageMetaSkill: produce a short cited topic brief from one bounded web-search round. Not a general deep-research replacement.

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

能力原语+状态空间搜索:read/write/exec/ssrf等原语凑RCE等式A-F,低危映射,正反向搜索,跨域兑现。Use when no single RCE, chaining low-severity vulns, or deriving novel attack chains.

Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.

Lark/Feishu channel output rules. Always active in Lark conversations.

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

Use the enabled Memcode MCP connection to explicitly save approved facts and recall relevant memories across DeepChat conversations. Never save a transcript or retrieve memory automatically.

Daily update check — official Anthropic docs diff + guide/CC releases digest

Run the Nexent requirement or bug lifecycle from SPEC analysis through feature catalog and D1-D5 case design, product implementation, fixed test implementation, local verification, and delivery…

安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。

数学建模竞赛论文撰写阶段，支持 Typst 和 LaTeX 双引擎。根据 ANALYSIS_MODELING_REPORT.md、RESULTS_REPORT.md 和 figures/*.pdf 选择比赛模板、排版引擎、组织章节，并在论文正文中按章节直接插入图表。

AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 Fast 모드(기본)로 실행하고 `--strict`면 정밀 3콜(진단→겨냥 윤문→finalize). 트리거 — "/humanize".

Scaffold a SMART-on-FHIR app (SMART App Launch v2 — EHR launch and standalone launch, OAuth2 PKCE, scopes, token handling, fhirContext) so an OpenMed-powered tool can run inside Epic or Cerner/Oracle…

Implement a GitHub issue end-to-end — create a worktree branch, implement the feature with tests, create a draft PR, then iteratively resolve all CI failures and review comments until the PR is clean.…

This skill should be used when the user asks to "test for SQL injection vulnerabilities", "perform SQLi attacks", "bypass authentication using SQL injection", "extract database information through…

Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths,…

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

Search the built-in assets of the Unity Editor (located at Resources/unity_builtin_extra). Filters by name and/or type; built-in assets have no GUID so GUID-based lookups are not supported.

Investigate a topic against preserved sources and write a draft-status research article under `research/` in a Knowledge Base project (the `knowledge-base` starter pack). Read when asked to research a…

Use this skill when the user wants to deep-read a specific BestBlogs resource (article / podcast / video / tweet) — fetch its metadata + markdown so a local LLM or reader can consume it, and…

Capture a durable engineering decision in Basic Memory with rationale, alternatives, consequences, and affected work. Use when the user makes or asks to record a real choice — "let's go with X",…

Paste any code snippet and get a plain English explanation of what it does and how it works.

Fixture used by PromptLoaderTest to verify frontmatter stripping.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing…

Validate, prepare, or run public CodonFM Encodon masked-codon variant scoring and review compatibility of its scoring workflows. Use only when the user explicitly requests CodonFM or Encodon, or that…

[omh] Public variant claims to cross-check: retrieve and reconcile source-labelled biomedical evidence with identity, conflict and freshness checks. Use when the user says: biomedical-evidence,…