Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.
中文简介正在准备中。当前显示英语简介。
- Screening third-party data before training
- Checking downloaded model weights before deployment
- Investigating unexpected behavior on specific inputs
mukul975/Anthropic-Cybersecurity-Skills☆ 3.5万2026年8月31日 更新
Set up AI email screening that compares writing style and communication habits to identify impersonation and suspicious payment requests. Connect detection policies to quarantine, warning banners, and analyst review workflows.
中文简介正在准备中。当前显示英语简介。
- Detecting executive impersonation in emails
- Reviewing vendor payment change requests
- Flagging unusual employee email behavior
mukul975/Anthropic-Cybersecurity-Skills☆ 3.5万2026年8月31日 更新
Analyze endpoint, cloud storage, and email logs for signs of insider data theft. Use pandas to compare upload volumes with normal user behavior and examine data loss prevention alerts, unusual file access, and activity outside working hours.
中文简介正在准备中。当前显示英语简介。
- Investigating suspected insider data theft
- Finding users with unusually large uploads
- Reviewing file access outside working hours
mukul975/Anthropic-Cybersecurity-Skills☆ 3.5万2026年8月31日 更新
Structure Avalonia interfaces with Zafiro.Avalonia using shared styles, reusable components, and purpose-built layout containers. Guides reductions in duplicated XAML, the interface markup, and deeply nested layouts, while covering themes, icons, and interaction behavior.
中文简介正在准备中。当前显示英语简介。
- Consolidating repeated visual settings into shared styles
- Simplifying deeply nested screen layouts
- Extracting repeated layouts into reusable components
davila7/claude-code-templates☆ 3.3万2026年10月20日 更新
Guide an RxJS 7 project to RxJS Next by testing existing behavior, reviewing how subscriptions start and end, and validating small batches of changes. Record approved behavior choices, verification results, and unresolved blockers in migration reports.
中文简介正在准备中。当前显示英语简介。
- Assess RxJS usage and test coverage before migration
- Plan how subscriptions and cleanup should behave
- Migrate code and TestScheduler tests in small batches
ReactiveX/rxjs☆ 3.2万2026年8月9日 更新
Investigate errors and unexpected behavior through reproduction, isolation, diagnosis, and a proposed fix. Receive a structured report covering the root cause, necessary code or configuration changes, and suggested tests to prevent the issue from returning.
中文简介正在准备中。当前显示英语简介。
- Investigate an error message or stack trace
- Diagnose behavior that differs between staging and production
- Trace a failure that appeared after deployment
anthropics/knowledge-work-plugins☆ 3.1万2026年10月20日 更新
Review a design or web page against WCAG 2.1 AA, an accessibility standard. Organize findings on contrast, keyboard access, forms, and screen reader behavior, with severity levels and practical recommendations for fixes.
中文简介正在准备中。当前显示英语简介。
- Review accessibility before design handoff
- Check text and interface color contrast
- Review keyboard navigation and focus behavior
anthropics/knowledge-work-plugins☆ 3.1万2026年10月20日 更新
Implement or change behavior in Composio’s TypeScript SDK, the library used to integrate Composio into applications. Covers tools, sessions, authentication settings, connected accounts, and generated interfaces in @composio/core and shared TypeScript packages.
中文简介正在准备中。当前显示英语简介。
- Change tool or toolkit behavior
- Implement session or authentication changes
- Update connected account handling
ComposioHQ/composio☆ 3.1万2026年10月20日 更新
Fix defects in Composio SDK through focused reproduction, root-cause analysis, regression tests that check for recurrence, and targeted verification. Use it for reported bugs, failing tests, CI regressions, runtime errors, or incorrect SDK behavior.
中文简介正在准备中。当前显示英语简介。
- Reproducing and fixing reported SDK bugs
- Investigating failing tests
- Fixing regressions in automated CI checks
ComposioHQ/composio☆ 3.1万2026年10月20日 更新
Helps build or improve reusable OpenCLI website commands in JavaScript. It uses observed page behavior, captured requests, and existing adapters to guide implementation, then checks definitions and tests real command behavior and failure handling.
中文简介正在准备中。当前显示英语简介。
- Turning repeated website tasks into OpenCLI commands
- Improving an existing website adapter
- Investigating API requests before implementation
jackwener/OpenCLI☆ 3万2026年10月20日 更新
Plan and, after explicit approval, run controlled checks of software behavior. Compare baseline and failure cases, repeat sensitive measurements, and report observed results with execution context, comparison conditions, and the status of temporary evidence files.
中文简介正在准备中。当前显示英语简介。
- Investigating a suspected runtime regression
- Checking retries, interruptions, and concurrent operations
- Comparing latency or cost under matched conditions
openai/openai-agents-python☆ 3万2026年10月20日 更新
Plan SDK behavior changes by defining required outcomes, compatibility boundaries, and unsupported cases. Reuse existing implementation paths, assess review feedback, and reconsider designs when repeated fixes introduce complexity beyond the original requirement.
中文简介正在准备中。当前显示英语简介。
- Define the scope of an SDK behavior change
- Assess compatibility with released APIs
- Reconsider a design after repeated review findings
openai/openai-agents-python☆ 3万2026年10月20日 更新
Compare a feature implemented in Qwen Code with Codex or Claude Code under the same scenario. Capture communication and terminal records, inspect tool definitions and outputs, and guide fixes toward matching observable behavior.
中文简介正在准备中。当前显示英语简介。
- Checking a reproduced feature against its reference agent
- Comparing tool definitions and required arguments
- Investigating differences in terminal output
QwenLM/qwen-code☆ 2.9万2026年10月20日 更新
Investigate difficult bugs through explicit hypotheses, targeted logs, and repeated checks against actual data. Keep an investigation journal to track findings, examine environment differences and leftover state, and confirm the root cause before applying a fix.
中文简介正在准备中。当前显示英语简介。
- Investigate a bug that survived an initial fix
- Trace tests that fail intermittently
- Compare local behavior with a user's report
QwenLM/qwen-code☆ 2.9万2026年10月20日 更新
Build a Table v9 plugin when built-in settings and typed metadata are insufficient. Guides custom state, options, and methods, with initialization hooks and runtime checks to ensure declared APIs actually exist and reset correctly.
中文简介正在准备中。当前显示英语简介。
- Add reusable custom table behavior
- Design plugin state and reset behavior
- Keep declared APIs consistent with runtime behavior
TanStack/table☆ 2.9万2026年10月13日 更新
Keep Kilo-specific changes small in files shared with upstream OpenCode. The skill guides where to place custom logic and tests, how to mark changes, and how to check annotations while preserving behavior.
中文简介正在准备中。当前显示英语简介。
- Add Kilo-specific features to shared upstream code
- Move additive logic into Kilo-owned files
- Clean up outdated or overly broad change markers
Kilo-Org/kilocode☆ 2.8万2026年10月20日 更新
Update NemoClaw documentation after merged changes or audit it for outdated guidance. Verify current behavior against source and tests, edit the pages responsible for that guidance, and check affected links and generated variants.
中文简介正在准备中。当前显示英语简介。
- Catch up documentation after merged changes
- Audit documentation for outdated guidance
- Update guides for changed user behavior
NVIDIA/NemoClaw☆ 2.3万2026年10月20日 更新
Create or modify Handsontable plugins using the project's plugin rules. Covers settings, hooks that respond to events, enable and disable behavior, conflicts between plugins, row index mapping, UI focus management, and required documentation and tests.
中文简介正在准备中。当前显示英语简介。
- Creating a new Handsontable plugin
- Adding plugin settings and event hooks
- Reviewing enable, disable, and settings update behavior
handsontable/handsontable☆ 2.2万2026年10月20日 更新
Write and review Handsontable tests that check intended behavior. The skill guides bug reproduction, meaningful assertions, failure diagnosis, and fresh test runs, while covering mock boundaries and migration of broken legacy tests to Playwright.
中文简介正在准备中。当前显示英语简介。
- Reproducing a bug with a failing test
- Diagnosing whether code or test expectations are wrong
- Reviewing assertions for meaningful behavior checks
handsontable/handsontable☆ 2.2万2026年10月20日 更新
Develop and test Windows-specific Screenpipe changes on a disposable Azure virtual machine. The workflow verifies native behavior, preserves logs and desktop video, and handles branch and pull request delivery when authorized.
中文简介正在准备中。当前显示英语简介。
- Test Windows-specific capture and permission behavior
- Investigate compiler, process, or service issues
- Preserve desktop video and logs for a pull request
screenpipe/screenpipe☆ 2.2万2026年10月20日 更新
Turn a recorded software failure into a draft bug report with timestamps, reproduction steps, expected and actual behavior, and relevant evidence. Separate visible symptoms from possible causes and remove sensitive details from shareable evidence.
中文简介正在准备中。当前显示英语简介。
- Drafting a bug report from recorded activity
- Recovering steps taken before and after a failure
- Comparing expected behavior with observed results
screenpipe/screenpipe☆ 2.2万2026年10月20日 更新
Analyze a single discovery interview to understand actual behavior, needs, workarounds, and open questions. Receive a concise account tied to sources, separating participant actions from hypothetical intentions, interviewer suggestions, and interpretation.
中文简介正在准备中。当前显示英语简介。
- Summarize actual behavior from an interview
- Identify needs and current workarounds
- Prepare follow-up research questions
screenpipe/screenpipe☆ 2.2万2026年10月20日 更新
Implement, fix, refactor, or remove repository code through a defined workflow. It connects each change to an acceptance criterion, checks effects on existing behavior, and guides focused testing, change review, and verification.
中文简介正在准备中。当前显示英语简介。
- Implementing a feature within an agreed scope
- Fixing bugs while preserving existing behavior
- Checking impacts before removing code
apache/shardingsphere☆ 2.1万2026年10月20日 更新
Guide changes to the published @kortix/sdk package with rules for preserving public APIs, writing failing tests before behavior changes, keeping the core independent of frameworks, and checking package installation. It also covers exports, streaming transport, and release version handling.
中文简介正在准备中。当前显示英语简介。
- Adding a public SDK feature or export
- Renaming public types while preserving compatibility
- Changing streaming or transport behavior
kortix-ai/suna☆ 2万2026年10月20日 更新