PA

pai-skills-root

Machine-readable index file for discovering agent-supported skills.

Install

mkdir -p .claude/skills/pai-skills-root && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14315" && unzip -o skill.zip -d .claude/skills/pai-skills-root && rm skill.zip

Installs to .claude/skills/pai-skills-root

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Index of all PAI skills.
24 charsno explicit “when” trigger
Beginner

Key capabilities

  • Enumerate every `SKILL.md` under `/skills/`
  • Parse the YAML frontmatter of each `SKILL.md` file
  • Build an in-memory registry keyed by `name` with `triggers`
  • Match user intent with skill `triggers`
  • Load the full `SKILL.md` body when a user request matches
  • Report problems if `SKILL.md` fails to parse or frontmatter is incomplete

How it works

The skill acts as a root index for all PAI skills, discovering them by enumerating `SKILL.md` files, parsing their frontmatter, and building an in-memory registry. It then matches user intent to skill triggers to load the relevant skill documentation.

Inputs & outputs

You give it
A user request or a new `SKILL.md` file
You get back
A list of available skills, or a loaded `SKILL.md` body

When to use pai-skills-root

  • List available skills
  • Validate skill configuration
  • Debug skill discovery

About this skill

PAI Skills — Root Index

This file is the machine-readable index of every skill shipped in PAI. Agents scan /skills/*/SKILL.md at session start and use this file as the canonical list of what is available.

For the human-facing overview of the skill convention, see ../SKILLS.md. For how agents consume skills, see ../AGENTS.md. For the underlying primitives skills are built from, see ../TOOLS.md.

Catalog

NameDescriptionStatusLink
example-toolTemplate skill demonstrating the PAI SKILL.md format.stableexample-tool/SKILL.md

How skills are discovered by agents

At session start, an agent should:

  1. Enumerate every SKILL.md under /skills/ (excluding this root index itself).
  2. Parse the YAML frontmatter of each file.
  3. Build an in-memory registry keyed by name, with triggers used to match user intent.
  4. When a user request matches one or more triggers, the agent loads the full SKILL.md body and follows its instructions.

Agents MUST NOT invoke a skill whose SKILL.md failed to parse or whose frontmatter is incomplete. Report the problem to the user instead.

When not to use it

  • When invoking a skill whose `SKILL.md` failed to parse
  • When invoking a skill whose frontmatter is incomplete

Limitations

  • Agents MUST NOT invoke a skill whose `SKILL.md` failed to parse
  • Agents MUST NOT invoke a skill whose frontmatter is incomplete

How it compares

This skill functions as a centralized, machine-readable index for skill discovery, providing a structured way for agents to find and load skills based on user intent, which is more automated and consistent than manual skill management.

Compared to similar skills

pai-skills-root side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
pai-skills-root (this skill)03moNo flagsBeginner
sequential-thinking1369moNo flagsIntermediate
planning-with-files2336moReviewIntermediate
ralph-plan146moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

sequential-thinking

mrgoonie

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.

136386

planning-with-files

davila7

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

233106

ralph-plan

mastra-ai

Interactive planning assistant that helps create focused, well-structured ralph-loop commands through collaborative conversation

1463

autonomous-agents

davila7

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b

1041

ai-wrapper-product

davila7

Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific problems with AI. Covers prompt engineering for products, cost management, rate limiting, and building defensible AI businesses. Use when: AI wrapper, GPT product, AI tool, wrap AI, AI SaaS.

536

token-budget

toonight

Manages token budget estimation and tracking to prevent context overflow

426

Search skills

Search the agent skills registry