1.9K skills · sorted by relevance
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Test and debug REST and GraphQL APIs using curl, httpie, Postman collections, or scripted tests. Check authentication, invalid inputs, pagination, and response details to identify failures that a successful status code alone may miss.
Analyze records of an AI agent’s decisions and tool use to find repeated failures, lost goals, and misunderstood instructions. Use the findings to refine prompts, rerun tasks, and turn debugging lessons into reusable skills.
Investigate software errors, version conflicts, and API questions across official documentation, GitHub, technical Q&A, and Chinese developer communities. Results distinguish matching errors, source authority, and reported environments, giving you documented leads and next checks for debugging.
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.
Review lessons from difficult tasks, debugging, and failed attempts, then turn them into reusable guidance. Update relevant skill instructions or shared memory so future tasks can benefit from what was learned.
Find, add, and combine shadcn/ui components to build forms, dashboards, and other interfaces. Use project settings and component documentation to guide styling, debugging, preset changes, and updates that preserve local modifications.
Use LangSmith to record LLM application inputs, outputs, and timing, investigate failures, evaluate answers against test datasets, and monitor production usage. It also guides automated quality checks and analysis of token usage and costs.
Write and debug code for further training large language models with TRL. Match training methods to dataset formats, configure supervised or preference-based training, and set up reward functions through Python or the command line.
Split debugging, audits, searches, and code questions into read-only tasks for sub-agents. Combine their structured reports into an evidence-based answer, requesting follow-up investigations when findings conflict or leave important gaps.
Investigate production incidents and bugs using logs, metrics, and code evidence. The skill guides hypothesis testing, root cause analysis, fix validation, and reusable investigation notes, with access to configured observability tools such as Axiom.
Investigate bugs, failing tests, and unexpected behavior through reproducible steps, logs, and comparisons with working code. Follow four stages to identify the root cause, test a hypothesis, apply a focused fix, and verify the result.
Review how an AI agent loads, retains, summarizes, and shares working information. This historical guide helps examine forgotten constraints, repeated actions, tool selection, and handoffs using context engineering practices published in 2024–2025.
Investigate bugs, failed tests, and unexpected behavior through reproducible steps, evidence gathering, and comparison with working code. Test one hypothesis at a time, then implement a focused fix and verify it with tests.
Coordinate temporary agents for code exploration, independent implementation tasks, verification, reviews, or complex debugging. Define self-contained assignments, run independent work in parallel, and check returned evidence before combining the results.
Set up libFuzzer to test C/C++ code with varied inputs guided by which code paths run. Build test harnesses, manage sample inputs and dictionaries, enable error detectors, and reproduce crashes or investigate stalled coverage.
Support shellcode development for security testing: small machine-code programs executed in memory. The skill covers x86/x64 implementation, code that works regardless of its memory address, loaders, executable conversion, debugging, and platform-specific execution constraints.
Plan a browser game's architecture before coding. Choose an engine, separate game rules from rendering, and define input, assets, menus, saves, debugging, and performance checks within a shared design.
Test and debug rendered web apps by reproducing interaction bugs, checking layouts and console errors, making focused fixes, and validating again. Results include screenshots, observed state changes, and a QA report explaining coverage and remaining gaps.
Build and debug Python agents with Swarms, a framework for coordinating multiple AI agents. Covers tool connections, saved memory, autonomous execution, and workflow choices such as sequential steps, parallel work, specialist delegation, and combined answers.
Build and maintain interfaces with shadcn/ui by finding, adding, and combining components. The skill uses project settings, component documentation, and change previews to guide styling, debugging, preset changes, and updates that preserve local edits.
Inspect and control live Chrome pages to investigate display problems, console errors, failed requests, and slow loading. Capture screenshots, automate page interactions, and record performance traces to identify where delays or layout shifts occur.
Design specialized assistants that work with their own separate context. Define responsibilities, delegation conditions, working steps, and report formats for reusable subagents handling verification, debugging, security audits, or code reviews.
Create specialized assistants for Cursor that work with their own context, separate from the main conversation. Define responsibilities, instructions, output formats, model choices, and execution settings for reusable workflows such as verification, debugging, and documentation.