Index of all PAI skills.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add nirholas/PAI --skill skills --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of pai-skills-root?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nirholas-pai-skills-root)More formats (shields.io, HTML) on the badges page.
---
name: pai-skills-root
description: Index of all PAI skills.
version: 0.1.0
---
# 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](../SKILLS.md). For how agents consume skills, see
[../AGENTS.md](../AGENTS.md). For the underlying primitives skills are
built from, see [../TOOLS.md](../TOOLS.md).
## Catalog
| Name | Description | Status | Link |
| ---- | ----------- | ------ | ---- |
| `example-tool` | Template skill demonstrating the PAI `SKILL.md` format. | stable | [example-tool/SKILL.md](example-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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling