AI Ml AI Skills

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion…

Starting a FEATURE (multi-symbol work): the plan, the API boundary, the scope — how big does this change get — from the codebase's real structure. Implementing an EXISTING interface? --lego=Iface…

File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report. Creates a GitHub issue on tinyfish-io/tinyfish-cookbook with the user's…

Guide developers through creating and updating ChatGPT and MCP apps. Covers the full lifecycle: brainstorming ideas against UX guidelines, bootstrapping projects, implementing tools/views, debugging,…

Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.

在创建新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发（TDD），要求包括单元测试、集成测试和 E2E 测试在内的测试覆盖率达到 80% 以上。

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence…

Install shared Codex pet packages into Omnibot with the official codex-pets npm CLI. Use when the user asks to add, install, download, import, or sync a pet by slug or collection, especially requests…

【何时用:仅当用户明确指向飞书/Lark(发到飞书、飞书文档等)时使用;泛指做个文档或PPT或表格或方案默认走本地工具,不要误用飞书】飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、BaseApp 应用模式（页面与组件）、Workspace 目录、workflow、角色权限、模板中心（模板分类/列表/搜索）；遇到…

Manage ScriptableObject assets

Use when evaluating investments through Zhang Lei / Hillhouse Capital's long-term research-driven value lens: deep research, do time's friend, invest in great companies, and actively help them grow.

Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices…

Answer weather queries with a fixed demo response.

Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products),…

Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications

【套装内部技能 · 全流程用户通常无需直接调用；直接说需求给总控 short-drama-director 即可，总控会自动路由到本技能】【漫剧老李 V7.4.26 套装 · 子技能】导演决策引擎（分镜选型依据层）：情境映射 E01~E15 + 80/15/5 权重机制 + 情绪锚点表 + 构图雷区 A/B…

Search X (Twitter) posts, pull user profiles, fetch specific tweets, and read reply threads for sentiment, news, and event research. Triggers on 'X', 'Twitter', 'tweets about', 'sentiment on', 'what…

Draft and review contributions to existing MEX project knowledge in the repo wiki. Use when the user wants to capture a team decision, convention, or architecture note, propose an addition or…

This skill should be used when need prioritize what changed code in repository human must review.

Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the…

Turn new AI names or unstructured AI market signals into a keyword priority table. For each name it finds the generic search terms downstream of it, screens them for relevance, and checks novelty,…

Für Automatische Verlängerung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

RedClaw 空间首次创作前的自媒体定位与写作风格定义。用“账号首页截图 + 文章/对标内容截图”两步证据流完成定位和文风学习。

Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file. Use for systematic…

生成教育/科普类流程图、概念图、原理演示的动画 HTML 页面。用 CSS/SVG 绘制节点和连线，支持流动箭头、逐步出现、hover 高亮等动画效果。适合技术讲解、视频科普、PPT 配图场景。

Chinese opera playwriting for the qupai (曲牌体) system — 元杂剧, 明清传奇, 昆曲, 川剧高腔, where sung text is filled into fixed tune patterns (填词) rather than built from paired lines varied by metre. Covers stage vs…

AI DevKit · Manage running AI agents with ai-devkit agent commands. Use when an agent needs to identify itself, list agents, start workers, inspect agent detail, assign work, group agents, resume…

Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.

Synthesize durable KTX wiki pages from staged Google Drive document pulls. Load when a WorkUnit contains Google Doc raw files from `docs/**`.

Analyze your own local Claude Code session transcripts to find what you actually use the agent for, how effective it is, where it fails, and what it costs. Use when asked to mine Claude Code sessions,…

Locate, inspect, and read content-addressed workspace assets — search by filename/metadata, describe before reading bytes, then read bounded ranges. Use whenever the user references an uploaded file,…

Use when the user types /agentlas-browser <url-or-query>, /agentlas browser, or /hep-browser for browser-required tasks, rendering pages, form flows, or visual evidence.

Generating rich inline SVG diagrams to visually explain systems, processes, architectures, and abstract concepts.

Skill for using the KnowledgeIndex registry to discover which directories contain `.knowledge.yaml` files without walking the filesystem. KnowledgeIndex is a lightweight SQLite cache. It maps…

Set up the project file an AI agent keeps for work that runs over days or weeks: the goal, the definition of done, milestones, the current state, decisions made, open questions, and the exact point to…

Manage old recordings — find large files, archive old meetings, delete processed originals. Use when the user says "clean up recordings", "how much space are meetings using", "delete old recordings",…

Regenerate a Context Room brief from the room's current documents and context. Use for brief-refresh tasks.

CRITICAL guideline - Never introduce breaking changes to the private API without explicit user approval. Always warn and ask for validation first.

Verify an agent's live address and billing account before sharing a chat link, diagnosing a deploy mismatch, or deciding why two hosts share an identity.

内容工厂专用写作 Skill，生成批量文案、短视频脚本和图片提示词，并输出可回写的 workspacePatch。

Review, approve, request changes on, or reject pending wiki edit drafts in Arkon. Requires editor or admin role. Triggers on: review drafts, pending reviews, check draft queue, approve draft, reject…

Produce an experiment blueprint from a research hypothesis

Fix Interface and Controller compilation errors

GraphQL pentest playbook — find the endpoint, dump the schema (introspection or field-suggestion fallback), then test for authorization gaps, query batching, alias overload, depth-based DoS, and…

Use this skill to build academic-style .docx output: journal / conference / thesis chapters carrying formal citation style (APA, Chicago, IEEE, MLA), numbered equations, figure & table…

可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用。

Help users navigate product failure by diagnosing root causes, evaluating conviction, and executing successful pivots or turnarounds based on proven industry frameworks.

Stock quotes and daily price history. Trigger phrases: stock quote, alphavantage, stock price.

Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider,…

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods. Integrates with provider factory in src/llm/index.ts, config detection in src/llm/config.ts, and error…