Work with the user's Pad workspaces through the Pad tools. An agent skill from PerpetualSoftware/pad.

Apache-2.0Auto-check passedProductivity & Automation

Install Pad

skills CLI
$ npx skills add PerpetualSoftware/pad --skill pad -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install PerpetualSoftware/pad pad --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/PerpetualSoftware/pad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/integrations/chatgpt/skills/pad .claude/skills/pad && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pad
GitHub stars
185
Token cost
~1.1k tokens
SKILL.md length
672 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

Work with the user's Pad workspaces through the Pad tools. An agent skill from PerpetualSoftware/pad.

  • Works in 4 steps: Call list_workspaces. If it returns… → If there is more than one workspace and… → Call get_workspace_overview for that… → …
  • The user talks about their Pad projects
  • SKILL.md covers Connect to a workspace first, Follow the workspace's…, Find and read and Create and change, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pad is an agent skill from PerpetualSoftware/pad. Work with the user's Pad workspaces through the Pad tools. Find, read, create and update tasks, bugs, ideas, plans and docs; comment on them, link them, and see what to work on next. Use it whenever the user talks about their Pad projects or items.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Project management. It works with Model Context Protocol, SQLite, SvelteKit and Go. The repository describes itself as: Project Management for the agent era. The licence is Apache-2.0.

When your agent uses it

  • The user talks about their Pad projects
  • Tasks that involve Project management

Example prompts

  • “/pad”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Call list_workspaces. If it returns none, tell the user to create a workspace at https://app.getpad.dev and come back. Stop there.
  2. If there is more than one workspace and the user hasn't named one, ask which one they mean.
  3. Call get_workspace_overview for that workspace. It returns the workspace's collections and their fields, its always-on conventions, its…
  4. Pass that workspace's slug as workspace on every later tool call. Nothing remembers it between calls.

What it can do on your machine

Read from SKILL.md and the folder at commit 0f932b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pad loads about 1.1k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 672 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from PerpetualSoftware/pad at commit 0f932b5, republished under its Apache-2.0 licence (© PerpetualSoftware). 672 words, ~1,124 tokens.

Download SKILL.mdSave it as .claude/skills/pad/SKILL.md (or your agent's skills folder).
name
pad
description
Work with the user's Pad workspaces through the Pad tools. Find, read, create and update tasks, bugs, ideas, plans and docs; comment on them, link them, and see what to work on next. Use it whenever the user talks about their Pad projects or items.

Pad

Pad is a project workspace. A workspace holds collections (such as Tasks, Bugs, Ideas, Plans and Docs). Each collection holds items. Every item has a short ref like TASK-12 or BUG-4, fields such as status and priority, optional markdown content, comments, and links to other items.

You work with Pad only through the Pad tools listed below. Refer to items by their ref, never by any other identifier.

Connect to a workspace first

  1. Call list_workspaces. If it returns none, tell the user to create a workspace at https://app.getpad.dev and come back. Stop there.
  2. If there is more than one workspace and the user hasn't named one, ask which one they mean.
  3. Call get_workspace_overview for that workspace. It returns the workspace's collections and their fields, its always-on conventions, its playbooks, and what is happening now.
  4. Pass that workspace's slug as workspace on every later tool call. Nothing remembers it between calls.

If the user switches workspaces, call get_workspace_overview for the new one before continuing.

Follow the workspace's conventions

The overview's conventions are rules this team has written down for how work is done in this workspace. Follow them when you create or change items. They override your own defaults.

Find and read

  • "What's going on?" or "how are we doing?" → project_dashboard.
  • "What should I work on?" → what_next for one recommendation, ready_items for the open, unblocked backlog in priority order.
  • "What changed?" → recent_activity, optionally since a date.
  • "Find anything about X" → search. To browse one collection or one status → list_items. Both return summaries.
  • To read one item in full → get_item. For its discussion → list_comments. For what blocks it and what it blocks → item_dependencies. For its past versions → item_history.
  • To see which collections exist and which values a field accepts → list_collections.

Answer with what the user asked for. Quote refs so they can find the items in Pad. Don't paste whole item bodies unless asked.

Create and change

  • Before create_item, check the collection and its valid field values (from the overview or list_collections). Pick the collection that fits: an idea goes to Ideas, a defect to Bugs, a unit of work to Tasks. If the fit is unclear, ask.
  • Show the user what you are about to create or change, and get a yes, before calling create_item or update_item.
  • update_item changes only what you pass. Every content change is saved as a version first, so the user can undo it from the item's History in Pad.
  • When you change an item's status, also call add_comment saying why. The comment is the record of the decision.
  • If update_item says the item is being edited in Pad right now, tell the user and try again shortly. Don't retry in a loop.
  • link_items records relationships such as one item blocking another.
  • To answer someone in a discussion, use add_comment with reply_to.
Show full SKILL.md (202 more words)Show less

Archive and restore

archive_item hides an item from lists and search. Always ask the user to confirm before archiving, naming the item by ref and title. restore_item brings an archived item back. Archiving is the only way to remove an item here; there is no permanent delete.

Playbooks

Playbooks are step-by-step procedures the team has written down, such as how to triage a bug. When the user asks to do something a playbook covers, use get_playbook (by its ref or invocation slug) and follow its steps with the tools you have, telling the user as you go. If a step needs something these tools cannot do, say so and leave that step to the user in Pad.

What these tools don't do

You can't create or delete workspaces, invite people, change collections or their fields, manage roles, or delete items permanently. When the user asks for one of these, say it is done in Pad at https://app.getpad.dev and don't try to work around it.

Principles

  1. Use refs, never internal identifiers.
  2. Confirm before creating, changing or archiving anything.
  3. Comment on every status change.
  4. Pass the workspace slug on every call.
  5. Keep answers short and specific to the request.

© PerpetualSoftware, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in integrations/chatgpt/skills/pad of PerpetualSoftware/pad.

Open the folder on GitHubat commit 0f932b5

Compare with similar skills

Pad next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pad compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pad this skillPerpetualSoftware/pad185—~1.1kAutomated safety check: PassApache-2.0
Paxmpax-beehive/paxm421—~574Automated safety check: PassApache-2.0
remindb Integration Testsradimsem/remindb129—~1.8kAutomated safety check: PassMIT
Testing Previewboringcomputers/nehemiah338—~822Automated safety check: NotesApache-2.0
Retinuejklthinking/retinue112—~279Automated safety check: PassMIT
Linear Issue Workflowlobehub/lobehub83k—~1.5kAutomated safety check: PassCustom licence

Similar skills

  • Paxm

    pax-beehive/paxm

    Use paxm as Codex's active and passive memory layer. An agent skill from pax-beehive/paxm.

    421 GitHub stars~574 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Explains how to add an end-to-end test scenario to remindb, choosing between a direct API test and an MCP test and using the shared helpers and fixtures.

    129 GitHub stars~1.8k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Testing Preview

    boringcomputers/nehemiah

    Test the preview proxy feature end-to-end. An agent skill from boringcomputers/nehemiah.

    338 GitHub stars~822 tokensUpdated 18 days ago
    Productivity & AutomationAuto-check: notes
  • Retinue

    jklthinking/retinue

    Coordinate work through a local Retinue workspace using its MCP tools.

    112 GitHub stars~279 tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Linear Issue Workflow

    lobehub/lobehub

    Handles Linear issues for the team: reading details and images, checking sub-issues, marking progress, labeling AI-created issues and writing completion comments.

    83k GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Linear

    kv0906/pm-kit

    Interact with Linear for issue tracking — search, create, sync, and link issues to vault notes.

    138 GitHub stars~1.9k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check: notes

More from PerpetualSoftware/pad

  • Pad

    PerpetualSoftware/pad

    Talk to your project. An agent skill from PerpetualSoftware/pad.

    185 GitHub stars~10k tokensUpdated today
    Auto-check: notes

Questions about Pad

What does Pad do?

Work with the user's Pad workspaces through the Pad tools. An agent skill from PerpetualSoftware/pad. Pad is an agent skill from PerpetualSoftware/pad. Work with the user's Pad workspaces through the Pad tools.

When should I use Pad?

Pad fits situations like: the user talks about their Pad projects; tasks that involve Project management.

How do I install Pad in Claude Code?

Run `npx skills add PerpetualSoftware/pad --skill pad -a claude-code`. Or copy the skill folder (integrations/chatgpt/skills/pad in PerpetualSoftware/pad) into .claude/skills/pad in your project. Claude Code loads it when a task matches its description.

How do I install Pad in Codex?

Run `npx skills add PerpetualSoftware/pad --skill pad -a codex`. Or copy the skill folder (integrations/chatgpt/skills/pad in PerpetualSoftware/pad) into .agents/skills/pad in your project. Codex loads it when a task matches its description.

Can I use Pad in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PerpetualSoftware/pad --skill pad -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pad, .gemini/skills/pad, .github/skills/pad and .opencode/skills/pad in your project.

What does Pad need to run?

SKILL.md names no scripts, command-line tools or credentials: Pad is instructions for the agent only.

Does Pad access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pad safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pad use?

Pad is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pad use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pad?

Skills that share tags, products or a category with Pad: Paxm (pax-beehive/paxm, 421 stars), remindb Integration Tests (radimsem/remindb, 129 stars), Testing Preview (boringcomputers/nehemiah, 338 stars) and Retinue (jklthinking/retinue, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pad?

PerpetualSoftware (a GitHub organization) maintains it in PerpetualSoftware/pad, which has 185 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.

Source: PerpetualSoftware/pad on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.