1.9K skills · sorted by relevance
Build Claude Code hooks, automated checks triggered by events such as tool use or session start. The guidance covers prompt-based decisions, command scripts, configuration, testing, and debugging for validation and workflow automation.
Set up and use gstack in Capy or Claude Code for planning, code review, debugging, and release work. It checks the local environment, handles installation or repairs when needed, and selects the workflow instructions for the task.
Limit file edits to a chosen directory and block Edit, Write, and NotebookEdit operations outside it. Keep debugging or module changes within scope, with the restriction remaining active until explicitly removed.
Build a narrative project history from records stored in claude-mem. The report traces architectural changes, breakthroughs, debugging efforts, and work patterns, with timeline statistics and estimates of token savings from reusing recorded knowledge.
Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.
Fetch execution traces, records of an agent’s actions, from LangSmith Studio to debug LangChain and LangGraph agents. Inspect errors, tool calls, memory operations, execution times, and token usage, or export records for further review.
Investigate failed GAIA benchmark questions by inspecting execution records and classifying causes such as missing tools, reasoning errors, or answer extraction bugs. Follow targeted fixes, verify them through another run, and save findings for future debugging.
Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.
Research existing code, documents, and relevant sources before producing a practical plan for implementation, migration, debugging, or evaluation. The plan explains key decisions, ordered steps, and validation checks, giving users something concrete to review before execution.
Test changes interactively in Codex's terminal interface. The skill explains how to launch it, save detailed logs for debugging, and send test messages programmatically with text and Enter submitted separately.
Guide implementation and debugging of visual Sequence editing in Remotion Studio. It documents how sequence identifiers, node paths, and stack traces behave during hot reload, and suggests how to track expanded UI state.
Retrieve current documentation and code examples from Context7 for libraries, frameworks, and developer tools. Use the results to answer questions about API syntax, configuration, installation, version migration, and library-specific problems.
Find current documentation and code examples through the Context7 MCP server. Look up library setup, API usage, migration steps, and library-specific problems, using documentation for the requested version when available.
Debug programs with LLDB while keeping session state across commands. Set breakpoints, inspect variables and memory, and examine core dumps, with JSON results for agents and a debug adapter interface for editor clients.
Inspect NSLogger logs from iOS and macOS apps, filter messages by severity, tag, text, or thread, summarize counts, export text, JSON, or CSV, and receive live logs for debugging.
Analyze software protections during authorized reverse engineering, the examination of compiled programs. Helps identify mechanisms that hinder debugging, obscure code, or prevent tampering, then choose safe analysis methods, document findings, and develop defensive recommendations.
Investigate errors and unexpected behavior by finding related code, following function calls, and checking source files. GitNexus helps trace execution paths, while the diagnosis identifies the repository and reports how current its code index is.
Automate Electron desktop apps with agent-browser through CDP, a browser debugging connection. Click controls, enter text, extract content, and capture screenshots while switching between app windows or embedded pages for routine work and testing.
Develop exploit code from a known memory corruption flaw, then investigate differences between local and remote execution. Covers stack, heap, and Linux kernel cases, with attention to library versions, debugging, and repeatable results.
Investigate bugs and slow applications through reproducible examples, logs, environment comparisons, and hypothesis testing. The skill structures root cause analysis and performance measurement, helping developers narrow down failures and verify that a fix works.
Build end-to-end tests with Playwright and Cypress to check complete user workflows, such as login and checkout. Improve test reliability through stable element selection, independent test data, appropriate waits, and debugging with traces and screenshots.
Generate independent options for design, implementation, explanations, or debugging, then compare them using one shared rubric. Code candidates use separate working copies and undergo independent verification before a winner is presented for review.
Use OpenViking MCP tools to retrieve relevant knowledge before substantial tasks and save lasting preferences, decisions, and lessons during or after work. Import documents as searchable resources so later tasks can draw on previous findings.
Build web apps connecting a CopilotKit React interface to agents hosted in Microsoft Foundry. Covers AG-UI, the communication protocol between them, plus tool approvals, conversation history, shared state, deployment, debugging, and dependency upgrades.