Results for “tool-use”

Design and implement CI/CD pipelines and automation — fast checks on every PR, safe releases, and repeatable workflows. Load when setting up GitHub Actions (or similar), adding pre-merge gates, automating releases, or the user asks "add CI", "set up workflows", "automate checks", "CD pipeline". Not for one-off local scripts (use task-specific tooling).

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.

Generate heightmaps, map reference images, and water feature splines (rivers, lakes, oceans) from real-world geographic data (terrain_data tool). Use when the user asks to build terrain from a real location/coordinates, download a real-world heightmap, or add rivers/lakes/oceans from map data. Downloads Mapbox tiles server-side and produces UE5-compatible heightmaps + landscape splines.

Orchestrates multi-step content operations on Xiaohongshu, including competitive analysis, trend tracking, content creation, and engagement management through a CLI toolchain. All operations require user confirmation before publishing or commenting.

OI-3 spike harness — heavy consumer skill, BASELINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow by reading a file directly, with NO Skill-tool call. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the Task tool for architecturally enforced context isolation. Supports Jest, Vitest, pytest, Go test, cargo test, PHPUnit, and RSpec.

Self-contained code review checklist — formatting, type safety, duplication, readable conditions, logic-out-of-UI, test coverage, comment quality. Adapts to whatever tooling the project actually has (skips Prettier/TypeScript/test-runner checks if unconfigured). Use before merging, after completing a feature, or any time you want a second pass on code quality. In Claude Code, prefer the official `code-review` skill or `pr-review-toolkit`/`feature-dev` code-reviewer agents instead — both are real, installed, and go deeper than this checklist. This copy exists for Codex/Cursor portability, where those agents aren't available.

Agent-driven RAG patterns. Self-RAG, Corrective RAG (CRAG) with web fallback, Adaptive RAG with routing classifier, ReAct with retrieval tool, multi-hop retrieval, plan-and-execute, LangGraph state machines for RAG. USE WHEN: user mentions "agentic RAG", "Self-RAG", "Corrective RAG", "CRAG", "Adaptive RAG", "multi-hop retrieval", "LangGraph RAG", "ReAct RAG", "plan and execute RAG" DO NOT USE FOR: static retrieval pipelines - use `rag-architecture`; query rewriting only - use `query-transformations`; evaluation - use `rag-evaluation`

Expert knowledge for Azure Copilot development including troubleshooting, decision making, architecture & design patterns, security, configuration, and integrations & coding patterns. Use when sizing VMs, generating Bicep/Terraform, configuring Cosmos DB storage, or debugging App Service/VM disks, and other Azure Copilot related development tasks. Not for Azure AI services (use microsoft-foundry-tools), Azure Machine Learning (use azure-machine-learning), Azure AI Search (use azure-cognitive-search), Azure AI Bot Service (use azure-bot-service).

Persistent cross-session memory for AI agents. Mem0 stores user preferences, past decisions, domain knowledge, and agent learnings across all sessions, all tools, and all users. Complements planning-with-files (task-level memory) with long-term agent intelligence (CRM + personal knowledge base layer). Use when asked to "remember this", "store preference", "mem0", "long-term memory", "user memory", "agent memory", or when building multi-session agents that need to recall past interactions.

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Use when auditing a CAV (Computer Aided Verification) submission for portal readiness, covering the four submission categories (Regular / Short Tool / Short Application / Industrial Experience & Case Studies), the LNCS page limits, the per-category anonymization matrix, the artifact-intent declaration, and desk-reject triage before the AoE paper deadline.

Orchestrate persistent agent memory across coding sessions, repos, and tools. Load when the user asks to remember, recall context, save project memory, create a handoff, manage global memory, update memory, compact memory, audit memory, forget memory, continue from prior sessions, or before commit/push/git operations that checkpoint project state.

Use when provisioning a headless Windows 11 VM in Docker for testing, running Windows-only tools, or installing Claude Code on Windows. Triggers on: 'windows vm', 'windows docker', 'headless windows', 'windows 11 container', 'windows vm ssh', 'kvm windows', 'dockur windows', 'windows dev environment', 'windows claude code', 'windows test environment'.

Guide for accessing financial and economic data in MATLAB using the Datafeed Toolbox. Covers Bloomberg (market data via bloomberg/blp/bloombergHypermedia), FRED (Federal Reserve economic data via fredrs), and Haver Analytics (economic data via haver/haverdirect/haverview). Use when connecting to any of these data providers from MATLAB.

C++-specific library development patterns. Use when creating C++ libraries, designing header-only vs compiled libraries, configuring CMake for library targets, managing ABI stability and versioning, integrating with Conan/vcpkg, documenting with Doxygen, or testing with GoogleTest/Catch2. Extends meta-library-dev with C++ tooling and idioms.

Elm-specific library/package development patterns. Use when creating Elm packages, designing pure functional APIs, configuring elm.json for libraries, writing documentation comments, publishing to package.elm-lang.org, or managing semantic versioning in pure functional context. Extends meta-library-dev with Elm tooling and ecosystem patterns.

Reads from, writes to, and manages relational databases using MATLAB Database Toolbox. Use when connecting to databases, reading data with sqlread or fetch, filtering with rowfilter, writing with sqlwrite, updating with sqlupdate, executing SQL statements, managing transactions with commit and rollback, mapping MATLAB classes to tables with ORM (Mappable, ormread, ormwrite, ormupdate), or performing any database operation from MATLAB. Triggers on: database, SQL, sqlread, sqlwrite, sqlupdate, fetch, execute, rowfilter, RowFilter, ORM, Mappable, ormread, ormwrite, ormupdate, orm2sql, transaction, commit, rollback, Database Toolbox, PostgreSQL, MySQL, SQLite, SQL Server, Oracle, database connection, database table, query database, insert data, update rows, delete rows, stored procedure, prepared statement, odbc, databaseConnectionOptions, datasource, data source, DSN, connection string, multithreaded, parallel.

Router for Google Stitch design-to-code in this pack. Use when starting any Stitch workflow, choosing Stitch vs Aura vs Figma vs Claude Design, or before calling generate/edit MCP tools. Enforces ~400 Stitch credits/day. Points to phased pack skills: enhance-prompt → generate-design → extract → build → loop.

VS-Enhanced Evidence Quality Appraiser - Prevents Mode Collapse with context-adaptive quality assessment Enhanced VS 3-Phase process: Avoids automatic tool application, delivers research-specific evaluation strategies Use when: appraising study quality, assessing risk of bias, grading evidence Triggers: quality appraisal, RoB, GRADE, Newcastle-Ottawa, risk of bias, methodological quality

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Design antennas, arrays, and PCB antennas using MATLAB Antenna Toolbox. Covers catalog antenna design and pattern analysis, custom antenna construction (customAntenna + shape.*), PCB antenna design (pcbStack + antenna.*), finite and infinite array design, AI-accelerated design exploration (AIAntenna, patternFromAI), and optimization (SADEA/TR-SADEA). Use when the user wants to design, create, model, analyze, optimize, or fabricate an antenna or array.

PPC financial calculator and modeling tool. CPA, ROAS, CPL calculations, break-even analysis, impression share opportunity sizing, budget forecasting, LTV:CAC ratio analysis, and MER (Marketing Efficiency Ratio) assessment. Requires zero API access. Works with pasted data from exports. Use when user says PPC math, ad calculator, break-even, budget forecast, ROAS calculator, CPA calculator, impression share, LTV CAC, or MER.

Greenfield development path for products, tools, and systems that do not yet exist. G Stack validates the idea before anything is planned or built. Use when starting from zero: no existing codebase, no existing schema, no existing API that this extends. AUTO-FIRE immediately when the user says any of: - "new development", "/new-development [description]" - "I have an idea for [X]", "I want to build [X] from scratch" - "new product", "new tool", "new platform", "new application" - "build [X] — it doesn't exist yet", "start a new project" Do NOT use when an existing codebase already exists for the work — use /full-development for large brownfield work. If unsure: ask "Does any part of this already exist in code?" If yes → /full-development. This is the most token-intensive command. Use it when the investment is justified by the scope of what is being built.

A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.

Find and query PI assets using MATLAB's Industrial Communication Toolbox. Two paths: (1) direct PI tag lookup via piclient + tags when user provides a tag name or description (R2022a+), (2) Asset Framework navigation via afclient when user needs element/attribute hierarchy (R2026a+). Use when working with PI AF servers, PI Data Archive tags, asset hierarchies, element templates, attribute lookup, or historical data from OSIsoft PI systems.

Expert MCP (Model Context Protocol) server developer creating safe, performant, production-ready servers with proper security, error handling, and developer experience. Activate on 'create MCP', 'MCP server', 'build MCP', 'custom tool server', 'MCP development', 'Model Context Protocol'. NOT for using existing MCPs (just invoke them), general API development (use backend-architect), or skills/agents without external state (use skill-coach/agent-creator).

Universal data-source assistant. Use this skill when the user wants external structured data such as stocks, financial reports, technical indicators, A-share/HK/US markets, global macroeconomics, Chinese enterprise registry information, arXiv papers, Google Scholar results, Chinese laws/regulations and judicial cases, Wind financial data (intraday/minute quotes, funds, bonds), IMF macro datasets (FX rates, CPI, GDP forecasts), Gildata smart screening, US SEC filings (10-K/10-Q, Form 4, 13F), or S&P Capital IQ fundamentals (top holders, consensus estimates, valuation ratios). This plugin exposes tools via MCP server `plugin-pythinker-datasource_data`; call them in the flow `mcp__plugin-pythinker-datasource_data__get_data_source_desc` → `mcp__plugin-pythinker-datasource_data__call_data_source_tool`.

Audits game user experience across HUD clarity, menu navigation, tutorial effectiveness, control responsiveness, camera systems, feedback loops, loading screens, and settings completeness. Detects game engine (Unity UGUI/UI Toolkit, Unreal UMG, Godot Control, web-based), maps all UI screens and input contexts.

Summarizes, condenses, or extracts text, transcripts, and key points from URLs, articles, web pages, PDFs, podcasts, YouTube videos, and local files. Acts as a fallback transcription tool when the user asks to transcribe, digest, recap, or get the gist of a link, video, or document.

Deterministic mathematical computation using SymPy. Use for ANY math operation requiring exact/verified results - basic arithmetic, algebra (simplify, expand, factor, solve equations), calculus (derivatives, integrals, limits, series), linear algebra (matrices, determinants, eigenvalues), trigonometry, number theory (primes, GCD/LCM, factorization), and statistics. Ensures mathematical accuracy by using symbolic computation rather than LLM estimation.

OS command injection occurs when user input is passed unsanitized to a system shell via dangerous APIs: Java `Runtime.exec()`, Python `os.system/subprocess`, PHP `system/shell_exec/exec/proc_open`, C `system/exec`. Detect via pipe `|`, semicolon `;`, `&&`, `||`, backtick, `$()` operators, and time-delay payloads (`sleep 5`). Tools: Commix, Burp Suite, OWASP WebGoat.

Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content calendars, or developing content strategy. For deep SEO writing optimization, see the seo-content-writer skill.

You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.