skill-creator
Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 2.0k
- Forks
- 233
01 前言 Front Matter
- name
- skill-creator
- description
- Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.
02 资源文件 5
- 参考文档CHANGELOG.md688 B
- 许可证LICENSE1.0 KB
- 参考文档package.json597 B
- 参考文档README.md166 B
- 脚本scripts/validate_skill.py6.3 KB
03 SKILL.md 正文
Skill Creator
Provide guidance for creating effective Pi skills.
Principles
- Conciseness: the agent is already very capable - only domain-specific knowledge, workflows, and tooling it can't infer earn their token cost.
- Progressive disclosure: Pi loads skills in tiers - frontmatter (always in context), body (on trigger), bundled resources (on demand) - so splitting content across them keeps context lean.
- Activation: Pi decides whether to load a skill based solely on the frontmatter
description. "When to use" information in the body comes too late. - Context over directives: the agent makes better decisions when it understands why. For tasks requiring judgment, context like "X helps Y because Z" is more robust than instructions like "You MUST do X".
Pi Agent Skills format
- Required frontmatter:
name,description. Directory name must equalname. - Name rules: 1–64 chars, lowercase letters/digits/hyphens, no leading/trailing/consecutive hyphens.
- Optional frontmatter:
license,compatibility,metadata(arbitrary key-value pairs for tooling),allowed-tools(restrict which tools the skill may invoke). disable-model-invocation: when set, Pi won't auto-trigger the skill; the user must invoke it explicitly with/skill:name.- Paths are relative to the skill directory;
{baseDir}placeholders are not supported. - Skill locations:
~/.pi/agent/skills/,.pi/skills/,skills/in a package, settingsskills, or--skill <path>.
Recommended structure
pi-skill/
├── SKILL.md
├── README.md # Optional: human summary + installation
├── scripts/ # Optional executables
├── references/ # Optional docs loaded on demand
└── assets/ # Optional templates/assets
Workflow
1) Clarify use cases
2-4 concrete example requests usually suffice to scope triggers and functionality.
2) Plan reusable resources
For each example, decide if you need:
- scripts/ for deterministic tasks
- references/ for long docs or schemas
- assets/ for templates or boilerplate
3) Create the skeleton
A skill needs a directory containing a SKILL.md. Only add resource sub-directories that are actually needed.
mkdir -p ~/.pi/agent/skills/my-skill
touch ~/.pi/agent/skills/my-skill/SKILL.md
4) Optional: Write README.md (humans + installation)
If you plan to share the skill with humans, a README.md helps discovery and installation. If you have a README, installation info can live there to save space in SKILL.md.
# My Skill
Short summary for humans discovering the skill.
## Installation
`pi install git:github.com/org/my-skill`
5) Write frontmatter
Use only the fields you need.
---
name: my-skill
description: What it does + when to use it.
---
If you need to hide auto-invocation, set:
disable-model-invocation: true
6) Write the body
- Imperative phrasing works well for procedural instructions; context framing works better for guidance (see Principles).
- ~500 lines is a practical ceiling for SKILL.md; beyond that, split content into references.
- The agent won't know a reference file exists unless SKILL.md says when to read it.
7) Add resources
SKILL.md is the agent's interface to the skill — usage examples and input/output descriptions let it call scripts without needing to understand internals.
- scripts/: usage examples in SKILL.md inform the agent how to call them; scripts should be executable.
- references/: a table of contents helps the agent navigate files longer than ~100 lines. References work best one level deep from SKILL.md, and each fact should live in one place (SKILL.md or a reference, not both).
- assets/: templates, boilerplate, or data used in final output — typically not loaded into context.
8) Validate and test
- Run the validator script:
scripts/validate_skill.py /path/to/my-skill
- Load only the skill to spot warnings:
pi --no-skills --skill /path/to/my-skill
- Invoke it explicitly:
/skill:my-skill
- After edits, use
/reload.
9) Publish (optional)
To share beyond a single machine, publish as a Pi package (package.json-based, not a .skill archive).
- Add
package.jsonwith apimanifest (or rely on the conventionalskills/directory). - Add
"keywords": ["pi-package"]for discoverability. - Publish to npm or host in git; install with
pi install <source>and enable viapi configif needed.
{
"name": "my-pi-skills",
"keywords": ["pi-package"],
"pi": { "skills": ["./skills"] }
}
04 同仓库更多 Skills
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
neuropixels-analysis
Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL curation, AI-assisted visual analysis, for Neuropixels 1.0/2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.
skill-creator
Guide for creating effective 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.
notebooklm
Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.