using-skills

Provides sub agents important information on how to use skills

16 stars

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

$curl -o ~/.claude/skills/using-skills/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/tools/using-skills/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/using-skills/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How using-skills Compares

Feature / Agentusing-skillsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

(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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

Use when syncing skills from local folders, GitHub URLs, or skillsmp.com pages to multiple AI coding tool directories

skills-scaffolding

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

Memory sidecar for agent work: recall before tasks, record learnings after tasks, review recommendations, optional backport bundles.

sc-pull-request-skills

16
from diegosouzapw/awesome-omni-skill

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

16
from diegosouzapw/awesome-omni-skill

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.