Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
github-pr-review
Post PR review comments using the GitHub API with inline comments, suggestions, and priority labels.
OpenHands/extensions 78
-
agent-sdk-builder
Guided workflow for building custom AI agents using the OpenHands Software Agent SDK. Use when you want to create a new agent through an interactive interview process that gathers requirements and generates implementation plans.
OpenHands/extensions 78
-
npm
Handle npm package installation in non-interactive environments by piping confirmations. Use when installing Node.js packages that require user confirmation prompts.
OpenHands/extensions 78
-
docker
Run Docker commands within a container environment, including starting the Docker daemon and managing containers. Use when building, running, or managing Docker containers and images.
OpenHands/extensions 78
-
skill-creator
This skill should be used when the user wants to "create a skill", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices.
OpenHands/extensions 78
-
magic-word
A test skill that responds to the magic word "alakazam" with a specific phrase
OpenHands/extensions 78
-
score-quality
Score code migration quality based on coverage and correctness. Evaluates how well target code represents source functionality.
OpenHands/extensions 78
-
migration-report
Generate a comprehensive migration report summarizing quality scores and providing recommendations. Use after scoring a migration project.
OpenHands/extensions 78
-
migration-scoring
Evaluate code migration quality with coverage, correctness, and style scoring. Generates executive reports with actionable recommendations.
OpenHands/extensions 78
-
migration-mapping
Create a mapping from source language files to target language files for code migrations. Use when evaluating or documenting a migration project.
OpenHands/extensions 78
-
score-style
Score migrated code against style guidelines and best practices. Evaluates code quality independent of functional correctness.
OpenHands/extensions 78
-
phase-task-verification
Shared branch creation and verification logic for sequential and parallel task execution - handles git operations, HEAD verification, and MODE-specific behavior
arittr/spectacular 10
-
understanding-cross-phase-stacking
Use before starting any new phase - explains how sequential and parallel phases automatically chain together through base branch inheritance (main worktree tracks progress, parallel phases inherit from current branch, no manual intervention needed)
arittr/spectacular 10
-
executing-sequential-phase
Use when orchestrating sequential phases in plan execution - executes tasks one-by-one in main worktree using git-spice natural stacking (NO manual upstack commands, NO worktree creation, tasks build on each other)
arittr/spectacular 10
-
troubleshooting-execute
Use when execute command encounters errors - diagnostic guide for phase failures, parallel agent failures, merge conflicts, worktree issues, and recovery strategies
arittr/spectacular 10
-
executing-plan
Use to execute an implementation plan with automatic sequential/parallel orchestration - handles worktree verification, resume detection, phase dispatch, and quality verification
arittr/spectacular 10
-
testing-workflows-with-subagents
Use when creating or editing commands, orchestrator prompts, or workflow documentation before deployment - applies RED-GREEN-REFACTOR to test instruction clarity by finding real execution failures, creating test scenarios, and verifying fixes with subagents
arittr/spectacular 10
-
validating-setup-commands
Use before creating worktrees or executing tasks - validates that CLAUDE.md defines required setup commands (install, optional postinstall) and provides clear error messages with examples if missing
arittr/spectacular 10
-
versioning-constitutions
Use when architectural patterns evolve, tech stack changes, or foundational rules need updates - creates new constitution version directory, migrates/organizes content into modular files, updates symlink, and documents changes
arittr/spectacular 10
-
validating-environment
Use to validate spectacular environment - checks superpowers plugin, git-spice, git repo, and project structure before running spectacular workflows
arittr/spectacular 10
-
decomposing-tasks
Use when you need to create an execution plan from a feature spec - handles worktree context, dispatches subagent for task decomposition, validates quality, analyzes dependencies, groups into phases, and commits the plan
arittr/spectacular 10
-
writing-specs
Complete spec workflow - generates Run ID, creates isolated worktree, brainstorms requirements, writes lean spec documents that reference constitutions, validates architecture quality, and reports completion
arittr/spectacular 10
-
executing-parallel-phase
Use when orchestrating parallel phases in plan execution - creates isolated worktrees for concurrent task execution, installs dependencies, spawns parallel subagents, verifies completion, stacks branches linearly, and cleans up (mandatory for ALL parallel phases including N=1)
arittr/spectacular 10
-
using-git-spice
Use when working with stacked branches, managing dependent PRs/CRs, or uncertain about git-spice commands (stack vs upstack vs downstack) - provides command reference, workflow patterns, and common pitfalls for the git-spice CLI tool
arittr/spectacular 10