3.5K skills · sorted by relevance
Add a Remotion command-line or configuration option, or convert a hardcoded flag into a shared option definition. Connect parsing, configuration setters, help entries, and generated documentation so the option is consistently available and documented.
Create integration tests for syncable metadata entities in Twenty itself. Cover invalid inputs, validation errors, and successful data operations, using reusable GraphQL request helpers, error snapshots, and cleanup routines to organize the test suite.
Write or improve marketing pages, from headlines and body text to buttons that prompt action. Preserve an existing brand voice, explain product benefits clearly, and keep claims grounded in the evidence provided.
Create sales materials tailored to the buyer and deal stage, including pitch outlines, one-page summaries, objection responses, and demo scripts. Use evidence from won and lost deals to improve the materials sales teams rely on.
Run a brainstorming session with creative techniques suited to a topic and goal. Choose guided questioning, collaborative ideation, or autonomous idea generation, while keeping a session log that supports resuming work after an interruption.
Guide cross-platform app development with Avalonia UI and Zafiro using consistent architecture and coding conventions. Keep screen logic separate from UI dependencies, handle errors explicitly, and reuse existing helpers with ReactiveUI and DynamicData.
Guide code that consumes PSL parser output by choosing the right syntax tree layer. Use typed AST classes for structure and navigation helpers for positions, while avoiding text parsing shortcuts and direct access to internal storage.
Create automated shell script tests with Bats, a Bash testing tool. Check exit codes, output, and failure cases, organize reusable test helpers and data, and run checks across shells or in CI/CD pipelines.
Inspect OpenCode sessions with helper scripts that list sessions and retrieve their latest messages. Use the last message’s sender as a rough guide to task status when checking activity across multiple OpenCode sessions.
Convert GitHub resource links into proxy URLs for cloning repositories and downloading files when access is slow. Covers release attachments, raw files, repository archives, and Gist files, with a Python helper for URL conversion.
Create and review CSV geofeeds, files that publish location information for public IP addresses. Check formatting, country and region codes, and privacy concerns, then review suggested improvements in an HTML report.
Turn official command documentation into a concise tldr page, an example-based command reference. Provide a command name and documentation URL to get five to eight common usage examples with consistent formatting and placeholders.
Keep code changes small by checking whether they are needed, reusing existing helpers, and choosing standard or available tools first. It guides planning and implementation while preserving validation, security, accessibility, and the functionality the user requested.
Guide changes and reviews for SGLang’s Scheduler, TokenizerManager, and ModelRunner classes. Keep initialization in small, replaceable helpers and separate computation from coordination so large classes retain clear responsibilities and explicit dependencies.
Use built-in tools to ask another agent for advice, a plan, or a review. Choose from available agents, preserve context across follow-up conversations, and send longer tasks to the background with status checks and configurable time limits.
Find installable agent skills for a specific task, check their sources and adoption, and present relevant options with explanations, links, and installation commands. Help install a selected skill when the user wants to proceed.
Investigate suspicious privilege increases, including Windows UAC approval bypasses and Linux sudo or setuid abuse. Use registry changes, process relationships, and permission changes to identify possible abuse and document affected hosts, methods, and risk levels.
Present results returned by a Codex helper while preserving findings, severity, file references, and uncertainty. This internal guidance also covers reporting edited files, failed runs, and setup requirements, with user confirmation before fixing review findings.
Apply consistent architecture and coding conventions when building cross-platform apps with Avalonia UI and Zafiro. The skill guides separation of interface and logic, reactive data handling, explicit error results, and reuse of existing helpers.
Turn a project idea into a detailed system plan before coding. Organize architecture, data flows, dependencies, and file-level tasks in a linked Markdown workspace, with research references, consistency checks, and saved state for resuming later.
Helps plan and improve marketing campaigns across social media, email, and landing pages. Guides audience selection, messaging, content creation, schedules, budgets, and performance measurement so teams can organize execution and identify improvements from results.
Design pricing and subscription plans around customer value and willingness to pay. The skill guides pricing surveys, billing units, feature bundles, free plans, trials, and price increases, helping organize options and define how to evaluate changes.
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.
Finish a NanoClaw v1-to-v2 migration after the migration script completes. The skill checks real message routing, assigns owner access, coordinates legacy memory migration, reviews container settings, and helps decide how to carry over customizations.