2.8K skills · sorted by relevance
Help DeerFlow maintainers investigate GitHub issues and review pull requests, or proposed code changes. It prepares or posts evidence-based comments with fix strategies, risks, and validation guidance, and compares competing proposals for the same issue.
Prepare selected pull requests for maintainer review by comparing failures with their current base, fixing authorized defects, and preserving contributor credit. Report complete or partial validation with evidence and outstanding checks before any separately authorized merge.
Review form validation so users, including people using screen readers, can understand and correct errors. Check field descriptions, required states, and grouped choices in rendered HTML, while accounting for React forms that handle submission in the browser.
Connect syncable entity components within Twenty server internals and expose them through GraphQL, an API query interface. It guides NestJS module registration, business services, response data conversion, and consistent handling of validation and execution errors.
Convert single-plane, single-channel two-photon TIFF images and timestamped behavioral position CSV files into NWB, a neuroscience data format. Preserve metadata, check clock alignment against acquisition evidence, and report format validation findings and source-to-output comparisons.
Keep development work aligned with the original request by recording requirements, protected behavior, and validation checks. Use phase reviews, deviation notices, and a final audit for tasks involving APIs, stored data, or changes that must preserve existing behavior.
Assess REST and GraphQL API security through checks of authentication, access permissions, input validation, and request limits. The workflow guides endpoint discovery, testing, and documentation of findings and remediation within an authorized scope.
Trace how JWT, JWS, and JWE tokens become accepted identities or privileges in a CTF sandbox. Examine headers, key selection, and claims, the token's attributes, then preserve a minimal reproducible path demonstrating validation confusion.
Check Bicep infrastructure definitions before deploying to Azure. Validate syntax, preview resource changes, check deployment permissions, and produce a Markdown report of issues and recommendations using Azure CLI or Azure Developer CLI workflows.
Simulate man-in-the-middle attacks, where traffic is intercepted between communicating systems, in authorized environments. Use Bettercap, Ettercap, and mitmproxy to test encryption enforcement, certificate validation, and network detection, then document findings and recommendations.
Organize Node.js, Express, and TypeScript APIs into layers with clear responsibilities. This guide covers request handling, business logic, database access, input validation, error tracking, configuration, and testing to support consistent implementation and refactoring across services.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Design tools that AI agents can understand and call correctly. Covers JSON Schema, a format for defining inputs, along with clear descriptions, input examples, validation, and error responses that help agents recover from failures.
Create, update, validate, and reorganize Agent Skills stored in a repository. It covers SKILL.md metadata, reference files, compatibility links, and validation scripts, supporting maintenance of skill folders, categories, and instructions for agents.
Build or modify Handsontable cell editors with guidance on editing states, input validation, focus, and element cleanup. Address dropdown positioning during scrolling, right-to-left layouts, and Japanese or other text input using composition.
Review past local Cursor sessions, identify recurring tasks, and propose changes to a project skill. Changes are tested on separate validation tasks and staged for review before adoption, with backups of existing files.
Build workflows that extract structured data from LLM responses, check field types and values with Pydantic, and retry failed extractions. Includes examples for nested data, classification, and receiving results as they are generated.
Implement application security controls, including login, access permissions, password hashing, and input validation. The skill provides code, configuration requirements, and testing guidance for checking protections against unauthorized access, malicious input, and sensitive data exposure.
Move an open pull request, a proposed code change, toward maintainer review by coordinating automated checks, two independent reviews, preview preparation, and live validation instructions, while tracking fixes and unresolved work.
Build Node.js, Express, and TypeScript APIs with consistent structure. Separate request handling, business logic, and database access, while following guidance for input validation, error tracking, configuration, and tests when adding features or refactoring existing services.
Verify Claude Agent SDK build and release scripts without network access. Run command-line workflows in an isolated environment with substitute commands to check version validation, installer handling, and retries without overwriting the developer’s installed Claude binary.
Create dictionaries of keywords and identifying byte sequences for fuzzing, or testing with generated inputs. Extract useful entries from code, binaries, or specifications, then configure fuzzers to explore parsing paths beyond initial input validation.
Assess enterprise Wi-Fi that uses 802.1X, a system for authenticating individual users or devices. Covers identifying authentication methods, testing rogue access points, reviewing certificate trust and storage, and assessing domain access through recovered credentials.
Choose a small validation experiment based on your hypothesis, risks, time, and resources. Compare five methods, from technical checks to user interaction tests, and define pass, fail, and learning criteria before investing in a larger build.