Claude Code Skills · page 15

AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.

Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rot Use when: context window, token limit, context management, context engineering, long context.

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

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.

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

Deep research skill powered by NotebookLM MCP. Conducts structured multi-source research (market analysis, competitive intel, trend analysis, prospect research) using Google NotebookLM as the research engine, then delivers formatted briefs and optional studio artifacts (slides, audio podcasts, videos, infographics, reports, mind maps).

Run autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

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.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

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.

Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

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.

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

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Comprehensive OWASP-aligned security guidance across six standards - Top 10 (2021) for web apps, ASVS 5.0, MASVS v2.1.0 for mobile, API Security Top 10 (2023), Kubernetes Top 10 (2022), and the Agentic Applications 2026 edition for AI/LLM. Use for security reviews, vulnerability audits, secure auth/crypto/access-control implementation, Kubernetes manifest hardening, and LLM/agent prompt-injection defense - including indirect requests like "is this login flow secure?", "review this endpoint", or "audit my pod spec".

Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making documentation token-efficient for LLM input; or rewriting text in compressed notation.

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

Optimize the description prompts an AI agent reads to learn its built-in tools (the `.md` files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool prompt vs what stays in code. Use when auditing, trimming, writing, or reviewing tool prompts, deciding what schema field descriptions already cover, or testing schema-vs-prompt overlap before deleting prompt lines.

Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.

3D Morph PPT — extends morph-ppt with GLB model insertion, cinematographic camera, model-content layout, and enriched visual design system.

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style transition', 'animated slide sequence', 'shape continuity across slides'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate 1–5a). DO NOT invoke for a generic deck, pitch deck, or board review without cross-slide motion — route those to officecli-pptx base or officecli-pitch-deck.

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 cross-references, footnotes/endnotes, bibliography, or multi-column journal layout. Trigger on: 'research paper', 'journal paper', 'conference paper', 'manuscript', 'thesis', 'APA', 'MLA', 'Chicago', 'IEEE two-column', 'bibliography', 'hanging indent', 'citation style', 'abstract + keywords', 'equation numbering', 'cross-reference', paper with footnotes/endnotes. Output is a single .docx.

Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to dashboard', 'data visualization'. Output is a single .xlsx. Scene-layer on officecli-xlsx: inherits every xlsx hard rule. DO NOT invoke for: a single budget tracker / one-sheet CSV-with-formatting (use xlsx), a 3-statement / DCF / LBO financial model (use financial-model), a weekly report with ≤ 1 chart and < 10 rows (use xlsx).

Use this skill any time a .docx file is involved -- as input, output, or both. This includes: creating Word documents, reports, letters, memos, or proposals; reading, parsing, or extracting text from any .docx file; editing, modifying, or updating existing documents; working with templates, tracked changes, comments, headers/footers, or tables of contents. Trigger whenever the user mentions 'Word doc', 'document', 'report', 'letter', 'memo', or references a .docx filename.

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 — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits every xlsx v2 rule (4-color code, visual floor, number formats, cache-drift, Known Issues, Delivery Gate minimum cycle). DO NOT invoke for a simple budget tracker, CSV dump, or operational KPI sheet — route those to officecli-xlsx base.

Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate). DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base.

Use this skill any time a .pptx file is involved -- as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file; editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions 'deck', 'slides', 'presentation', 'pitch', or references a .pptx filename.

Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document', 'onboarding form', 'HR intake', 'survey template', 'contract / SOW template', 'mail-merge template', 'compliance checklist', 'medical intake questionnaire'. Output is a single .docx where specific fields are editable and the rest is locked. This skill is INDEPENDENT, not a scene layer on docx — payload is `<w:sdt>` + `<w:ffData>` + `<w:fldChar>` + `documentProtection`, none of which docx base skill covers. Do NOT trigger for regular reports, letters, memos, academic papers, pitch decks, or any document with no user-fillable fields — route those to officecli-docx or its scene layers.

Use this skill any time a .xlsx file is involved -- as input, output, or both. This includes: creating spreadsheets, financial models, dashboards, or trackers; reading, parsing, or extracting data from any .xlsx file; editing, modifying, or updating existing workbooks; working with formulas, charts, pivot tables, or templates; importing CSV/TSV data into Excel format. Trigger whenever the user mentions 'spreadsheet', 'workbook', 'Excel', 'financial model', 'tracker', 'dashboard', or references a .xlsx/.csv filename.

Validate a Composio CLI beta release and promote it to a stable release by dispatching the CLI binary workflow with an existing beta tag.

Write end-to-end tests for CLI commands using the Docker-based test framework in ts/e2e-tests/cli/.

CLI design guidelines — arguments, flags, subcommands, help, output, errors, interactivity, config precedence. Apply when designing new commands or reviewing CLI UX.

Implement new CLI commands in ts/packages/cli/ using Effect.ts patterns, service wiring, and @effect/cli declarations.

Release and recover first-party Composio CLI binaries through Build CLI Binaries, including automatic beta builds, promote-stable dispatches, beta-tag selection, asset and installation verification, and failed release recovery. Use when a contributor asks to build a CLI beta, publish or promote a stable CLI version, choose a release candidate, monitor a CLI release, or diagnose a failed CLI release. Do not use for TypeScript SDK Changesets releases or CLI source implementation.

Trigger a CI binary build via workflow dispatch, monitor it, download the artifact, and test the CLI binary locally.

Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.

Design, implement, or review Composio CLI commands under ts/packages/cli using Effect, @effect/cli, services, output conventions, configuration and environment variables, and local vendor references. Use for CLI command UX, command wiring, service changes, or CLI source edits. Do not use for CLI E2E-only work; use cli-e2e there.

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

Keep TypeScript and Python SDK behavior, generated client usage, public API naming, and docs examples aligned. Use when a change affects both SDKs, when generated client pins move, when comparing TS/Python behavior, or when a backend API contract changed. Do not use for single-language internal-only changes.

Work on Composio documentation content, Fumadocs configuration, changelogs, docs automation prompts, docs decisions, ADR-style records, and docs review guidance. Use for files under docs/, documentation workflows, or requests to record or update a docs decision. Do not use for SDK runtime changes unless docs are the main deliverable.

Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.

Audit a doc, guide, README, or block of prose against the good-docs-writing style guide and report violations. Use when the user asks to review, critique, lint, or check the voice and tone of documentation or text. Produces a structured findings report (file:line, rule violated, offending text, suggested rewrite) and does NOT edit files unless explicitly asked.

Writing style guide derived from Modal's documentation voice. Apply when writing or editing docs, guides, tutorials, or technical prose that should read direct, second-person, confident, low-jargon, and example-first. Use to draft new docs in this voice or to revise existing prose toward it.

Create, modify, test, or package Python provider adapters under python/providers, including framework-specific dependencies, public imports, type inference, and provider metadata. Use for Python provider work only; use python-sdk for core SDK changes.

Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.

Implement or modify Python SDK behavior under python/composio, including tools, toolkits, sessions, auth configs, connected accounts, client integration, and shared Python models. Use for Python core runtime/API work; pair with python-testing and cross-sdk-parity when TypeScript must match.

Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.

Navigate the Composio SDK monorepo, branch and PR workflow, repo layout, generated-file boundaries, changesets, and shared maintenance rules. Use when work spans multiple packages, when deciding where code belongs, when preparing a PR, or when the user asks about repository conventions rather than a specific SDK implementation.

Create, update, validate, or reorganize repo-local Agent Skills under .agents/skills, including SKILL.md frontmatter, first-level references, compatibility symlinks, and validation scripts. Use only for skill-tree maintenance, skill taxonomy changes, or agent-guidance validation work.

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, and Claude Agent SDK. Use for provider-specific TS work; do not use for core-only changes.

Implement or modify TypeScript SDK behavior in @composio/core or shared TypeScript packages, including tools, toolkits, sessions, auth configs, connected accounts, modifiers, and generated SDK surfaces. Use for TS runtime/API work; pair with typescript-testing for verification and cross-sdk-parity when Python must match.

Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.

Route and complete Composio work across Composio For You and Composio Platform. Use when the user mentions Composio; wants an agent to use apps such as Gmail, Slack, GitHub, Notion, Calendar, or Linear; needs first-time setup, an SDK or MCP integration, CLI operation, migration guidance, current documentation, or help diagnosing a connection or tool call.

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, or Hermes Agent, apply an author's frameworks while working, or build a reusable knowledge base from a file.

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

当用户需要弃用一个工作流节点（保留向后兼容、隐藏出模板面板）时触发该 skill。FastGPT 工作流节点的弃用流程标准化封装，覆盖模板、Dispatcher、UI 引用等所有需要改动的位置。

将 FastGPT 文档从中文翻译为面向北美用户的英文。当用户提到翻译文档、i18n、国际化、translate docs、新增/修改了中文文档需要同步英文版时，使用此 skill。也适用于用户要求检查文档翻译缺失、批量翻译、或对比中英文文档差异的场景。

为 FastGPT 新资源接入权限管理。当用户需要为新资源（如 AgentSkill、Plugin 等）添加权限支持时触发。

FastGPT API 开发规范。重点强调使用 zod schema 定义入参和出参,在 API 文档中声明路由信息,编写对应的 OpenAPI 文档,以及在 API 路由中使用 schema.parse 进行验证。