Skills

Workflow orchestrator that chains existing skills for feature development

Multi-agent orchestration with container-isolated workspaces — each agent session runs in its own Docker container with independent git branches

Guided, section-by-section Art Bible authoring. Creates the visual identity specification that gates all asset production. Run after /brainstorm is approved and before /map-systems or any GDD authoring begins.

Unified team skill for architecture optimization. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team arch-opt".

Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

Use when the workflow feels too complex, has accumulated cruft, or has redundant steps and overlapping tools that need consolidation.

Install and verify a local llama.cpp server for optional Deus local-generation experiments. Keeps Ollama as the required default for embeddings and judge work.

Create a concise plan. Use when a user explicitly asks for a plan related to a coding task.

>-

Generate Minervini-style breakout trade plans from VCP screener output with worst-case risk calculation, portfolio heat management, and Alpaca-compatible order templates (stop-limit bracket for pre-placement, limit bracket for post-confirmation). Use when user has VCP screener results and wants actionable trade plans with entry/stop/target levels and position sizing.

Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.

When the user wants to optimize their Google Play Store listing — title, short description, full description, keywords, ratings, or Play Store-specific features. Use when the user mentions "Google Play", "Android", "Play Store", "Play Console", "short description", "full description indexed", "Google Play ASO", or wants Google Play-specific keyword, creative, or ratings strategy. For iOS App Store optimization, see aso-audit and metadata-optimization.

Systematic debugging approach for identifying and fixing issues

>

|

Turn hunches into accepted results: worthiness score, evidence bar, research-to-rules. Use when vetting ideas. Not for QA; use night-market-validation-and-qa.

Git提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、智能提交、生成调试报告、commit with reflection。

Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.

Add Google Calendar integration to Deus. Agents can list, create, update, and delete calendar events. Guides through GCP OAuth setup, token generation, keep-alive timer, and CLI command installation.

>

Generate candlestick price charts for any asset from existing OHLC data, without handling data fetching.

Use this skill to track institutional investor ownership changes and portfolio flows using 13F filings data. Analyzes hedge funds, mutual funds, and other institutional holders to identify stocks with significant smart money accumulation or distribution. Helps discover stocks before major moves by following where sophisticated investors are deploying capital.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

分析营养数据、识别营养模式、评估营养状况，并提供个性化营养建议。支持与运动、睡眠、慢性病数据的关联分析。

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

>

Use when rewriting or refreshing an existing page that's underperforming. The agent fetches the URL, analyzes the current content, researches the SERP, and rewrites using the full anti-AI-slop ruleset — no data exports needed.

Use when managing Apple Ads with asc, including auth, org lookup, campaigns, ad groups, ads, keywords, reports, raw API calls, and safe live testing.

Brownfield onboarding — audits existing project artifacts for template format compliance (not just existence), classifies gaps by impact, and produces a numbered migration plan. Run this when joining an in-progress project or upgrading from an older template version. Distinct from /project-stage-detect (which checks what exists) — this checks whether what exists will actually work with the template's skills.

Schema awareness - read before coding, type generation, prevent column errors

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

>

Workflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.

Specialized guide for adding new MCP tools to the UniFi MCP Server following project standards, UniFi API patterns, and test-driven development practices. Use when implementing new UniFi Network Controller features as MCP tools.

Create and manipulate Animation Montages — sections, slots, segments, branching points, notifies, and blend settings (AnimMontageService). Use when the user asks to create a montage (from an animation or empty), add or link montage sections, set up slots/segments, add branching points, or adjust montage blend timing.

Orchestrate coding work by delegating well-specified implementation tasks to xAI's Grok Build CLI (grok) running headlessly, while the coding assistant plans, writes the task specs, reviews every diff, and owns the result. Use when user says: 'use grok', 'grok build', 'delegate to grok', 'have grok implement', 'have grok execute', 'have grok build', 'send to grok', 'execute this plan with grok'. Executes a Markdown implementation plan task-by-task, or ad-hoc tasks with an inline spec.

钉钉待办 / TODO。Use when 用户说 创建待办/TODO/任务提醒/指派任务/标记完成/查待办/紧急待办/循环待办/批量建待办/逾期待办。Distinct from dingtalk-report(日报周报)、dingtalk-oa(审批)、dingtalk-calendar(日程)。命令前缀：dws todo。

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.

万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl read_only 流式读取（iter_rows 支持 10 万行以上）、Parquet 转换加速、内存优化、分块处理和大文件写入模式。**遇到以下任一情况就主动使用本 skill**：①数据行数 ≥ 10k（由 sn-da-excel-workflow 的行数评估步骤触发）；②用户出现触发词：大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing；③直接使用 pd.read_excel() 导致超时或内存溢出；④用户明确要求对大规模数据集进行高性能处理。仅不用于：小于 10k 行的常规 Excel 分析（使用 sn-da-excel-workflow 即可）。

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Conduct FMEA to systematically identify, prioritize, and mitigate potential failure modes. Use this skill when the user needs to assess product or process risks, prioritize corrective actions, or build a risk register — even if they say 'failure mode analysis', 'risk assessment', 'what could go wrong', or 'RPN calculation'.

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".

Iris is Redis's umbrella for AI-focused products. Use this skill when integrating with the Iris Redis Agent Memory (RAM) data plane on Redis Cloud — recording session events for an AI agent, creating or searching long-term memories, configuring a memory store, or tuning background memory promotion. Code examples use the official `redis-agent-memory` (Python) and `@redis-iris/agent-memory` (TypeScript) SDKs.

Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or when the codebase has changed enough that the rules file may be stale. Scans the repository for every rules file, grades each against a quality rubric, outputs a quality report, and applies targeted edits only after user approval.

Computational chemistry with RDKit for molecular analysis, descriptors, fingerprints, and substructure search. Use when working with SMILES, drug discovery, or cheminformatics tasks.

Use when the workflow works but needs polish, or as the final step in a diagnose → fix → refine cycle before shipping.