Claude Code Skills · page 47

AI DevKit · Guide structured debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when users ask to debug bugs, investigate regressions, triage incidents, diagnose failing behavior, handle failing tests, analyze production incidents, investigate error spikes, or run root cause analysis (RCA).

AI DevKit · Test-driven development — write a failing test before writing production code. Use when implementing new functionality, adding behavior, or fixing bugs during active development.

AI DevKit · Review and improve documentation for novice users. Use when users ask to review docs, improve documentation, audit README files, evaluate API docs, review guides, or improve technical writing.

AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing any task, fixing a bug, finishing a phase, running tests, building, deploying, or making any "it works" claim.

Make your agent plan before code, verify work, and review changes with a repeatable engineering workflow.

AI DevKit · Design phase guidance for reviewing feature design against requirements. Use when the user wants to validate architecture, review design docs, resolve design trade-offs, or run dev-lifecycle phase 3.

AI DevKit · Implementation phase guidance for executing feature plans and checking implementation against design. Use when the user wants to implement planned tasks, update implementation docs, verify code matches design, or run dev-lifecycle phases 5 and 7.

AI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create an implementation plan, update planning docs, mark task progress, capture blockers or new tasks, or run dev-lifecycle planning work.

AI DevKit · Requirements phase guidance for starting features and reviewing requirements. Use when the user wants to capture a new requirement, clarify product scope, initialize feature docs, review requirements, or run dev-lifecycle phases 1-2.

AI DevKit · Final code review phase guidance for holistic pre-push review. Use when the user wants code review, final lifecycle review, design alignment checks, integration risk review, or dev-lifecycle phase 9.

AI DevKit · Testing phase guidance for adding and validating feature test coverage. Use when the user wants to write tests, update testing docs, run coverage, close coverage gaps, or run dev-lifecycle phase 8.

AI DevKit · Worktree setup and resume guidance for isolated feature work. Use when starting, resuming, switching, or verifying a feature branch/worktree for lifecycle, debugging, implementation, review, or multi-agent workflows.

>-

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.

Create, track, and read team goals + KPIs via Hivemind from openclaw. Use whenever the user mentions a goal, objective, KPI, target, milestone, or asks to track progress on something measurable. ALSO use when the user says "task", "todo", "work item", "remind me to", "fix X", or any actionable work item — the goal system replaced the legacy `hivemind tasks` CLI and now covers both objectives and tasks.

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).

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

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

Use when answering a question that needs data from a ktx-connected database - investigating, analyzing, "how many", "show me", "what's the breakdown of", finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say "analytics"; if the answer requires querying a configured ktx connection, this skill applies.

Map dbt `schema.yml` / `properties.yml` models and sources into ktx semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement manifest backfill from git sync. Load when the WorkUnit's `skillNames` includes `dbt_ingest` or when raw files are dbt YAML under `models/` / `sources/`.

Identify recurring cross-table historic-SQL analytical intents from a bounded pattern shard and emit typed pattern evidence for deterministic wiki projection.

Convert one changed historic-SQL table usage bucket into typed table usage evidence for deterministic _schema projection.

Classify and resolve conflicts detected during bundle ingest (structural duplicates, definitional contradictions, near-duplicate clusters, re-ingest changes, evictions).

Capture semantic-layer and knowledge updates from a live database schema snapshot.

Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Load for WorkUnits whose raw files are under explores/, dashboards/, or looks/.

Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from derived_table, standalone with sql_always_where). Load when the turn contains `.lkml` content.

Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions. Covers result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and how to react to priorProvenance from earlier ingest syncs. Load when the WorkUnit contains `cards/<id>.json` files under a Metabase bundle.

Map a MetricFlow semantic_model or metric into ktx semantic layer sources. Covers the MetricFlow to ktx primitive table, `extends:` inheritance flattening, metric-type handling (simple / derived / ratio / cumulative / conversion), `model: ref('x')` resolution, and four worked examples. Load when the turn contains `.yml`/`.yaml` files with top-level `semantic_models:` or `metrics:`.

Synthesize durable ktx wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.

ktx's semantic layer - a structured catalog of sources (tables/views), measures, joins, and segments expressed as YAML. Covers the schema and how to query it via `sl_query`. Use when the task involves querying pre-defined metrics (ARR, churn, retention, LTV, MAU) or reading SL source YAML to understand the catalog. Capture is handled by the `sl_capture` skill (memory-agent only).

How to capture new reusable patterns into ktx's semantic layer - when a measure, segment, or join belongs in the catalog and how to write it generically so it stays small and useful over time. Loaded by the post-turn memory-agent only. The research agent does not write to the SL.

ktx's knowledge base - wiki pages for durable, reusable business knowledge. Covers capture workflow for user preferences, metric definitions, organizational conventions, and cross-references between wiki pages and semantic-layer sources. Loaded by the post-turn memory-agent only. The research agent reads wiki via `wiki_read`/`wiki_search` but does not write it.

Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent integration, and verifies readiness. Use when the user asks an agent to add ktx to a project, connect data sources, install agent rules, ingest schema, or troubleshoot a local ktx install.

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

>

Generate a Python code skeleton from an experiment blueprint

Search academic literature and generate research hypotheses

Produce an experiment blueprint from a research hypothesis

Draft a LaTeX research paper from all previous stage outputs

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Use this skill when the user wants to install, configure, download, or synchronize online resumes for candidates who applied to currently open BOSS/Zhipin recruiter jobs. Provides a cross-platform boss-agent-cli setup, standard CDP/Chrome conventions, persistent resume root, job/candidate JSON indexes, full and per-job incremental sync, and randomized delay during bulk downloads.

Configure CC Safety Net rulebooks for user, project, or shareable GitHub scope.

对当前文本、对话或显式文件内容做结构化分析，并区分事实、判断与待确认项。

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 contentFactoryWorkspacePatch。

将品牌定位、价值观、受众画像、语气风格、内容样例、危机回应和表达禁区，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的品牌人设知识库。适用于用户要求“整理品牌人设”“沉淀品牌口吻”“把品牌资料变成可复用语气库”“维护品牌 persona pack”的场景。

将品牌产品资料、规格参数、卖点证据、FAQ、价格权益、竞品区别和合规边界，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的产品资料知识库。适用于用户要求“整理产品知识库”“沉淀产品 FAQ”“把品牌产品资料变成项目资料”“维护产品资料包”的场景。

将文章整理为可转播客音频的源文本（下游负责真实音频合成）。

将活动目标、用户路径、渠道分工、物料资产、时间节奏、风险预案和复盘结论等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理活动 / Campaign 运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

将选题日历、栏目矩阵、素材资产、发布节奏、复盘结论和内容边界等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理内容运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。

内容工厂专用复核 Skill，检查事实依据、平台适配、AI 味、风险和人工确认建议。

生成可直接发布的内容主稿（默认公众号长文风格）并自动生成 1 张头图，最终以 write_file 落盘。

为文章或视频生成平台封面图，并写回主稿（封面场景优先使用本技能）。

根据目标说明生成一份可直接在聊天区渲染的 A2UI 表单，复用 Lime 现有表单协议。

将增长目标、指标体系、渠道策略、实验计划、复盘结论、资源约束和停止条件，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的增长策略知识库。适用于用户要求“整理增长知识库”“沉淀增长策略”“把增长计划变成项目资料”“维护增长实验资料包”的场景。

仅在用户显式使用 @配图/@修图/@重绘/@image，或已明确确认调用画图功能后，根据文本描述生成配图素材（非封面场景）。

兼容旧版 Agent Knowledge 编译流程的 deprecated 兜底 Builder。仅用于未知或历史 pack 类型；标准 persona / data pack 必须优先委托内置专用 Builder Skill。

【外部资产库】读取项目参考资料（/project）或风格参考（/styles）。

将直播排期、货盘节奏、场控流程、主播话术、互动机制、异常预案和复盘指标等资料，整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理直播运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。