Coding standards, frameworks, refactoring, and code review (16.7K skills)
Package workspace skills and their required service integrations into one named, installable capability. Create a manifest that references existing skills, install the capability, and report which integrations still need to be connected.
Build the user interface for a holaOS app whose data resources are already connected through the SDK. Choose a feed, table, kanban board, form, or calendar layout using shared components and workspace styling.
Customize an installed workspace capability, a bundle of agent tools and guidance. It updates the configuration to add MCP servers, which connect agents to tools, or change skills, integrations, and instructions while preserving existing settings.
Compare an installed GEO-SEO toolkit with the latest upstream files, summarize changes, and update skills, agents, scripts, templates, and hooks. Keep files removed upstream and report the outcome of dependency updates.
Create interactive web demos and chat interfaces in Python with Gradio. Connect functions to text, image, audio, and file controls, arrange screen layouts, and define what happens when users click buttons or change inputs.
Write and review Gradio demos for Hugging Face ZeroGPU. Configure GPU time limits and dependencies, and troubleshoot errors caused by separate worker processes, shared state, concurrent requests, or CUDA package installation.
Build reusable command-line scripts that fetch and process Hugging Face API data. Combine multiple requests, enrich model information, and produce outputs for further filtering, with built-in help and usage examples for repeated tasks.
Assess a fixed patch or pull request diff before merging. Trace affected behavior, evaluate regression risks, tests, and recovery options, then provide an evidence-based recommendation and advisory automatic-merge eligibility without modifying or merging the patch.
Handle failed tool calls with a clear recovery process. The skill distinguishes temporary problems from input or setup issues, chooses whether to retry or change approach, and records failures so unsuccessful tasks are not silently lost.
Create a new skill for a Hive agent, with a clear SKILL.md, supporting files, and an appropriate storage scope. Guides validation and discovery checks so the agent can find and use the skill.
Diagnose unexpected terminal-tools results, including empty output, missing exit codes, expired output handles, and busy sessions. Use returned status fields to distinguish ongoing work, output limits, shell behavior, and failures, then choose a recovery step.
Help an agent run terminal commands, follow long-running jobs, retrieve logs, and cancel work. It explains result fields, execution deadlines, retained output, and operating-system differences so the agent can interpret command outcomes and choose appropriate tools.
Guide an agent through searching code, logs, and configuration files by content or filename. It explains which tools to choose, how to filter searches, and how to recognize incomplete results or searches requiring shell commands.
Run builds, tests, and other long commands in the background while continuing other work. Explains how to read new log output, check completion, send input, and stop processes using the available platform controls.
Use persistent virtual terminal sessions to keep directories and environment variables across commands, interact with Python or database consoles, and answer prompts. The skill explains sending input, reading responses, detecting prompts, and closing sessions when finished.
Address trusted human reviewers’ change requests on an existing Otto pull request. It guides fixes on the same branch, verification, replies with supporting evidence, and requests for another review before handing over the results.
Commit a completed feature and prepare a pull request describing its design, tests, and demos. Follow the selected publication mode, and for direct publication, work through automated checks and review feedback before requesting maintainer review.
Implement a feature from its design and connect each covered user journey, a sequence of user actions, to a meaningful test. Run focused checks and assess the full change for effects on existing behavior.
Choose a feature design using the relevant code, requirements, and existing conventions. Record the chosen approach, alternatives, risks, and coverage of key user journeys, and identify decisions that need human input before implementation.
Prepare a structured JSON handoff for feature work, bringing together requirements, design decisions, key user journeys, tests, demo recordings, and pull request status. Clearly distinguish completed work from missing validation, publication steps, and other remaining tasks.
Guide pull request checks for merge readiness, automated checks, and live previews. It points agents to shared instructions at the relevant stage and identifies facts to include when handing work over to maintainers.
Prepare feature work by reading a Linear ticket and its context, checking development tools, and looking for existing implementation or pull requests. Route requested PR changes to a separate review workflow before development proceeds.
Turn a feature ticket into clear requirements and critical user journeys, describing who does what and the expected result. Check the scope before design begins, and propose smaller dependent tickets when the work exceeds one reviewable change.
Run Polly AI Review and Open Code Review repeatedly on a pull request. Track each finding, fix relevant issues, document justified dismissals, and verify that review evidence and recorded decisions cover the latest commit.