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 Aโ€“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

ASecurity

Use in Graftty agent sessions to report a short Attention recap before stopping.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/30/2026

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

Installs into .claude/skills of the current project.

Are you the author of Graftty?

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

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

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
description: Use in Graftty agent sessions to report a short Attention recap before stopping.
---

# Graftty

## Report the stopped turn

Before ending a top-level turn in a tracked worktree, report what the user will need to recognize it later. Run `graftty attention report --stdin` with one small JSON object. The CLI stages the report in a private file that the Stop hook hands to Graftty; this does not require control-socket permission. A SessionStart hook asks you to load this skill; if that was missed, the Stop hook may request this report once before allowing the turn to end.

If `graftty` is not on `PATH`, use the helper inside the installed Graftty app bundle, for example `/Applications/Graftty.app/Contents/Helpers/graftty`. Sessions started before Graftty registered its wrapper may show the report immediately because their Stop hook may be unavailable.

```sh
graftty attention report --stdin <<'GRAFTTY_ATTENTION_7F3A91C2'
{"title":"Posting detail model evals","context":"Finding a smaller model that can extract job posting details reliably.","completed":"v3 scored 0.910 against a700's 0.935.","next":"Run four evals on the new holdout, prod200, and us1000.","emoji":"๐Ÿงช","emojiAlternatives":["๐Ÿ”ฌ","๐Ÿ“Š"]}
GRAFTTY_ATTENTION_7F3A91C2
```

Use a recognizable task title, not the worktree name or a generic status. Set `"context"` to one sentence (aim for under 120 characters) about what this worktree is trying to accomplish. Set `"completed"` to one sentence on recent verified progress and `"next"` to one sentence on the remaining concrete work. Include one task-specific `"emoji"` and up to three distinct, task-related `"emojiAlternatives"`. Graftty assigns the first unused choice as the worktree's enduring emoji on its first report; later reports cannot change it. Favor a concrete subject of the work, such as ๐Ÿ”” for push notifications or ๐Ÿงช for model evals, over generic status symbols. Add `"need":"<brief question or action for the user>"` only when the user must decide or provide something; preserve the real question instead of inventing one. If results or validation are unknown, say so. Keep each field brief. If the report command fails, mention the failure in your final response; Graftty will still show a generic stopped card.

Other `graftty` commands use Graftty's main control socket. If a sandbox denies one with `EPERM` or `errno 1`, load the `graftty-team` skill for the socket check and narrowly scoped permission request. Do not request socket permission for `graftty attention report`.

Attribution

btuckerbtucker
View sourceSee grades on GitHubMore from btucker โ†’
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 โ†’