Search Skills
Find the perfect capability for your agent.
common-issues
Known issues and their solutions in the Trezor Suite monorepo. Use when encountering build failures, test failures, or environment problems.
codemod
Use Codemod CLI whenever the user wants to migrate, upgrade, update, or refactor a codebase in a repeatable way. This includes framework migrations, library upgrades, version bump migrations, API surface changes, deprecations, and large-scale mechanical edits. First search the Codemod Registry for an existing package, prefer deterministic codemods before open-ended AI rewrites, run dry-runs before apply, and create a codemod package only when no suitable package exists.
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
hugging-face-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
hugging-face-tool-builder
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
issue-review-reply
Review PigeonPod GitHub issues end to end. Use when the user asks what an issue means, whether it is valid, how to reply, whether to add it to the GitHub Project, or to turn it into a tracked task. Read the issue and comments, inspect relevant local docs and code, explain the real requirement or bug precisely, draft a maintainer reply, and only after explicit approval perform GitHub writes. When creating a task, first recommend `Priority`, `Size`, and `Estimate`, wait for maintainer confirmation or overrides, then write those values into the project task fields.
release-issue-responder
Find open GitHub issues that are covered by a specific release note, draft issue replies in the issue author's language, post approved comments with `gh issue comment`, and recommend whether each issue should be closed. Use when Codex needs to turn a shipped release into structured GitHub issue follow-up, especially for PigeonPod release-note-driven maintainer workflows.
release-note-publisher
Draft, refine, and publish bilingual PigeonPod GitHub release notes from commits on the `release` branch. Use when Codex needs to compare commits since the latest published GitHub release, write a new local release note under `dev-docs/release-notes`, align English and Chinese release-note sections after user edits, or create/update a GitHub Release while keeping the markdown H1 as the GitHub release title instead of the release body.
open-source-maintainer
End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.
gastown
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
pdd
This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable implementation plan. The process is designed to be iterative, allowing movement between requirements clarification and research as needed.
codebase-summary
This sop analyzes a codebase and generates comprehensive documentation including structured metadata files that describe the system architecture, components, interfaces, and workflows. It can create targeted documentation files like AGENTS.md (README for AI agents), README.md, CONTRIBUTING.md, or generate a complete documentation ecosystem. The documentation is organized to make it easy for AI assistants to understand the system and help with development tasks.
eval
EvalKit is a conversational evaluation framework for AI agents that guides you through creating robust evaluations using the Strands Evals SDK. Through natural conversation, you can plan evaluations, generate test data, execute evaluations, and analyze results.
assassination-as-desperate-measure
Use when analyzing last-resort strategies against existential threats where all conventional and diplomatic options have failed. Covers agent recruitment, pretext creation, close-range execution, and critical risk assessment of retaliatory consequences.
