using-skills
Provides sub agents important information on how to use skills
Best use case
using-skills is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Provides sub agents important information on how to use skills
Teams using using-skills should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/using-skills/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How using-skills Compares
| Feature / Agent | using-skills | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Provides sub agents important information on how to use skills
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# How to Use Skills Sub agents can invoke skills to get domain specific knowledge on a number of topics. You can invoke a skill using the Skill tool, which you have access to, and specifying a skill name. # When to Use Skills If you have a question or need information on any topic a skill provides information on, invoke the skill. You should also invoke skills at any time that your instructions tell you to. # Available Skills name: archive-ticket description: Archive completed tickets by moving them to .archived/ --- name: check-ushabti-prerequisites description: Verify required Ushabti files exist before proceeding. Use when starting agent work to ensure prerequisites are met. --- name: create-ticket description: Create a new ticket with schema validation --- name: describe-agent-roles description: Agent responsibilities and hard boundaries. Load when determining which agent should act or checking role violations. --- name: describe-canonical-locations description: File locations for laws, style, phases, and docs. Load when locating or creating Ushabti state files. --- name: describe-docs-system description: Documentation system location and maintenance requirements. Load when consulting or updating project documentation. --- name: describe-good-phase description: Phase sizing, scope boundaries, and anti-patterns. Load when evaluating whether a phase is well-formed or needs splitting. --- name: describe-laws-and-style description: Distinction between laws (invariants) and style (conventions). Load when determining if a constraint is a law or style. --- name: describe-phase-directory-structure description: Phase directory layout, naming conventions, and required files. Load when creating or navigating phase directories. --- name: describe-phase-file description: Required sections and format for phase.md. Load when defining phase intent, scope, and acceptance criteria. --- name: describe-phase-loop description: Plan-Build-Review cycle and agent handoffs. Load when transitioning between agents or understanding workflow progression. --- name: describe-progress-file description: Structure and field ownership for progress.yaml. Load when reading or updating phase progress state. --- name: describe-questions-policy description: Guidelines for asking clarifying questions. Load when deciding whether and how to ask the user for clarification. --- name: describe-required-inputs description: Mandatory files agents must read before acting. Load when starting agent work to ensure prerequisites are met. --- name: describe-review-file description: Structure and sections for review.md. Load when creating review scaffolds or recording review findings. --- name: describe-steps-file description: Step format and ordering rules for steps.md. Load when defining implementation steps or checking step requirements. --- name: describe-tickets description: Ticket system overview, schema, and workflows --- name: describe-ushabti description: Core Ushabti concepts and development lifecycle. Load when starting any Ushabti workflow or orienting to the framework. --- name: find-current-phase description: Find the active phase directory based on status. Use when you need to locate which phase to work on. --- name: find-next-phase-number description: Determine the next sequential phase ID for creating a new phase. Use when planning a new phase. --- name: find-next-step description: Find the next unimplemented step in a phase. Use when determining what to work on next. --- name: find-next-ticket-number description: Determine the next sequential ticket ID --- name: get-phase-status description: Check the current status of a phase. Use when you need to understand where a phase is in the workflow. --- name: list-tickets description: List all open (non-archived) tickets
Related Skills
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
using-mcp-tools-with-mcpc
Use mcpc CLI to interact with MCP servers - call tools, read resources, get prompts. Use when working with Model Context Protocol servers, calling MCP tools, or accessing MCP resources programmatically; prefer key:=value bindings over raw JSON bodies.
Using GitHub API with gh CLI
This skill teaches how to access GitHub's REST and GraphQL APIs via gh api for inline PR comments, review threads, and data not available through standard gh commands. Use this when you need PR review comments, thread status, or other GitHub data that gh pr view doesn't provide.
using-git-worktrees
(中文)Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
using-contextd
Use when starting any session with contextd - introduces core tools for cross-session memory, semantic code search, and error remediation. REQUIRES contextd MCP server.
use-skills-npm-package
CLI tool for discovering, installing, and managing reusable agent skills across multiple coding agents. Enables efficient skill discovery from repositories, local sources, and community repositories. Essential resource for discovering new Flutter/Dart skills.
tooluniverse-install-skills
Detect and auto-install missing ToolUniverse research skills by checking common client skill directories and cloning from GitHub if absent. Use when ToolUniverse specialized skills are not installed, when setting up a new project, or when the tooluniverse router skill needs to bootstrap its sub-skills before routing.
sync-skills
Use when syncing skills from local folders, GitHub URLs, or skillsmp.com pages to multiple AI coding tool directories
skills-scaffolding
Guide for creating effective Claude Code skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
self-learning-skills
Memory sidecar for agent work: recall before tasks, record learnings after tasks, review recommendations, optional backport bundles.
sc-pull-request-skills
GitHub PR workflow automation including fetching unresolved comments, resolving review threads, and parallel comment resolution. Use this skill when working with PR reviews, addressing reviewer feedback, or automating PR comment workflows.
reflect-codex-skills
Generate reflections for past Codex session histories using the Reflection CLI. Use when asked to summarize or reflect on previous Codex conversations, list projects/sessions, filter by date or session id, or refresh cached reflections from ~/.codex/sessions.