Pinme Share logo

Pinme Share

OrganizationPopular
glitternetwork
pinme-share

Use this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享/发布/上传分享页 request that should end with `pinme upload`.

Overview

Publisherglitternetwork
Repositorypinme
Skill namepinme-share
Stars
3.7K
Forks
276
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by glitternetwork on GitHub. Read the source before you install it.

Installation

Install the Pinme Share AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/glitternetwork/pinme.git /tmp/pinme
mkdir -p .claude/skills
cp -r /tmp/pinme/skills/pinme-share .claude/skills/pinme-share
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pinme Share in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pinme Share on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pinme Share is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PinMe Share

Create a polished static share artifact, upload it with pinme upload, and return the final URL.

When to Use

Use this skill when the user asks to:

  • Share or publish a result using PinMe.
  • Create a static page that wraps a deployed project link, demo, report, or artifact.
  • Summarize a Codex conversation/session and share it as a page.
  • Turn a project handoff into a public landing or summary page.
  • Upload an existing static file or folder for lightweight distribution.

If the user needs a backend, database, auth, email, or LLM functionality, use the main pinme skill and any relevant PinMe integration skill first. Use pinme-share at the end to package and publish the result.

Core Workflow

  1. Identify what is being shared:
    • PinMe/full-stack project: deployed URL, short description, key features, tech stack, usage notes.
    • Codex conversation: goal, decisions, implementation summary, important outputs, next steps.
    • Static file/report/demo: title, purpose, file contents or preview, context for the recipient.
  2. Create a static share artifact:
    • Prefer a single self-contained index.html.
    • Use share/<slug>/index.html in the current workspace unless the repo has an existing output/share convention.
    • Keep CSS inline for portability.
    • Do not require JavaScript unless interaction is valuable.
  3. Sanitize before publishing:
    • Remove secrets, tokens, API keys, .env values, internal-only URLs, private user data, and unrelated logs.
    • For conversation summaries, summarize rather than dumping raw transcript unless the user explicitly asks for verbatim sharing.
    • Make links explicit and clickable.
  4. Upload with PinMe:
    bash
    pinme upload share/<slug>
  5. Return the URL printed by PinMe. If PinMe outputs multiple URLs, prefer DNS domain, then PinMe subdomain, then short URL, then full preview URL. Never truncate hash fragments.

Share Page Content

For a project share page, include:

  • Project name and one-sentence description.
  • Primary launch/demo link as the first action.
  • What it does, who it is for, and why it matters.
  • Feature list focused on user-visible behavior.
  • Build/deploy details only when useful to the recipient.
  • Date and provenance such as "Created with Codex" only if appropriate.

For a conversation share page, include:

  • Conversation title.
  • Initial goal or question.
  • Key context and constraints.
  • Decisions made.
  • Work completed or answer summary.
  • Files changed, commands run, links produced, or artifacts created when relevant.
  • Follow-up items.

For a file/report share page, include:

  • Clear title and short abstract.
  • Download/open link to the uploaded artifact if there is a separate file.
  • Important excerpts or generated summary.
  • Source/context notes.

HTML Guidelines

  • Build a real share page, not a generic placeholder.
  • Make the most important link visible in the first viewport.
  • Use clean, responsive HTML/CSS that works as a standalone static file.
  • Keep the design restrained and readable; avoid overdecorated marketing layouts for technical handoffs.
  • Use semantic sections, accessible contrast, descriptive link text, and sensible mobile spacing.
  • Escape user-provided text before inserting it into HTML.
  • If showing code or command output, wrap it in <pre><code> and keep it short.

PinMe Upload Checklist

Before upload:

bash
pinme --version

If PinMe is missing or stale, install or update it according to the main pinme skill. Authentication is required for upload:

bash
pinme login
# or: pinme set-appkey <AppKey>

Upload examples:

bash
pinme upload share/my-project
pinme upload share/conversation-summary
pinme upload ./report.html
pinme upload ./dist

Do not upload:

  • .env, .git, node_modules, source trees, private datasets, raw logs with credentials, or unrelated build cache.
  • Raw conversation transcripts that may include secrets or private context unless the user explicitly approves the exact content.

Final Response

Tell the user:

  • What share artifact was created.
  • The PinMe URL returned by upload.
  • Any important caveat, such as skipped upload because PinMe was not authenticated or unavailable.

Keep the response short. The URL is the main deliverable.

Frequently asked questions

What does the Pinme Share AI skill do?

Use this skill when the user wants to share, publish, or upload a static result through PinMe, especially by generating a static HTML share page for a PinMe project link, deployed full-stack app, Codex conversation summary, report, file, demo, or any 分享/发布/上传分享页 request that should end with `pinme upload`.

Why use Pinme Share on TypingMind?

Because you install it once and use it with any model. Pinme Share is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pinme Share in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glitternetwork/pinme/tree/main/skills/pinme-share. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pinme Share?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pinme Share?

As many as you like. As long as a model supports skills, you can use Pinme Share with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pinme Share AI skill free?

Yes. It is published on GitHub by glitternetwork under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇