Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Graftty Open

ASecurity

Open a finished file made for the user's review, or a requested HTTP(S) page, with graftty open. Graftty routes it to the current pane leader's device.

5 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentsgoshell

Works with

cli

Security Analysis

A100/100

Scanned 9/30/2026

$npx -y skills add btucker/graftty --skill graftty-open --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Graftty Open?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Graftty Open
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/btucker-graftty-open/badge)](https://www.skillsdirectory.com/skills/btucker-graftty-open)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: graftty-open
description: Open a finished file made for the user's review, or a requested HTTP(S) page, with graftty open. Graftty routes it to the current pane leader's device.
---

# Graftty open

Run `graftty open` for each finished artifact you made for the user to review, such as a generated image, HTML report, CSV, PDF, or presentation. Do this even when the user has not asked to open it and you do not know which device they are using. Do not open source files you edited as part of a coding task or routine intermediate files. Also use the command when the user asks to open a file or HTTP(S) URL, including a local development site.

Run the command from the Mac's tracked worktree and pane where you are working. Graftty checks that pane's current display leader when the command runs. If Graftty Mobile leads, it offers the resource in that worktree's Open menu for 15 minutes. Otherwise macOS opens it with the default app or browser. Quote paths and URLs so spaces and shell metacharacters remain literal:

```sh
graftty open './output/chart.png'
graftty open 'http://localhost:3000'
graftty open 'https://example.com/report'
```

Use the Graftty CLI that matches the running app. If `graftty` is absent from `PATH`, locate that app's bundled CLI and check `graftty help open`. An older app build without the `open` subcommand cannot make the offer.

For mobile previews, `graftty open` accepts a readable regular file up to 20 MB. It snapshots that one file for 15 minutes. Graftty Mobile uses iOS Quick Look when available and otherwise offers the share sheet. An HTML file does not bring along its linked assets; serve a multi-file site on the Mac and open its HTTP URL instead.

For URLs, use HTTP or HTTPS without credentials embedded in the URL. When mobile leads, the page renders in Graftty Mobile's browser, while its connections and DNS go through the directly paired Mac. This lets `localhost` name a server on the Mac and also works for public sites the Mac can reach. A relay worktree cannot browse these URLs. The mobile browser has its own cookies and login state. When Mac leads, the URL opens in the Mac's default browser, including its existing session.

On mobile, command success means the resource was offered, not that the user opened it. Tell the user to choose it from the Open menu in that worktree if they are on mobile. If the offer expires, run the command again. Report a command error as an error; do not say the preview is ready.

Attribution

btuckerbtucker
View sourceSee grades on GitHubMore from btucker →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

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', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →