Agent skill

Slay Pty

by debuglebowski in debuglebowski/slayzone

Interact with PTY terminal sessions via the slay CLI. An agent skill from debuglebowski/slayzone.

GPL-3.0Auto-check passed

Install Slay Pty

skills CLI
$ npx skills add debuglebowski/slayzone --skill slay-pty -a claude-code

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

GitHub CLI
$ gh skill install debuglebowski/slayzone slay-pty --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/debuglebowski/slayzone.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/slay-pty .claude/skills/slay-pty && 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
slay-pty
GitHub stars
191
Token cost
~916 tokens
SKILL.md length
480 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
GPL-3.0

At a glance

Interact with PTY terminal sessions via the slay CLI. An agent skill from debuglebowski/slayzone.

  • SKILL.md covers Commands and Orchestration patterns
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Slay Pty is an agent skill from debuglebowski/slayzone. Interact with PTY terminal sessions via the slay CLI

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The licence is GPL-3.0.

Example prompts

  • “/slay-pty”

What it can do on your machine

Read from SKILL.md and the folder at commit e912716. 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 (its code samples are bash).

    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

Slay Pty loads about 916 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~916

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 debuglebowski/slayzone at commit e912716, republished under its GPL-3.0 licence (© debuglebowski). 480 words, ~916 tokens.

Download SKILL.mdSave it as .claude/skills/slay-pty/SKILL.md (or your agent's skills folder).
name
slay-pty
description
Interact with PTY terminal sessions via the slay CLI
trigger
auto

PTY commands interact with terminal sessions managed by the SlayZone app — the actual terminal tabs you see in each task. Use these to read output, send input, and orchestrate AI coding agents programmatically.

All commands support ID prefix matching.

Commands

  • slay pty list [--json] — list active PTY sessions.

    • Shows session ID, task ID, terminal mode, current state, and age
  • slay pty buffer <id> — dump the full terminal buffer content to stdout.

    • Useful for reading what an AI agent has output without streaming
  • slay pty follow <id> [--full] — stream PTY output in real time.

    • --full replays the existing buffer first before streaming new output
    • Streams until the session exits
  • slay pty submit <id> [text] [--wait] [--no-wait] [--timeout <ms>] — default for sending input. High-level text submission with AI-mode awareness.

    • If no text argument is given, reads from stdin (pipe-friendly)
    • Appends a trailing newline to submit
    • For AI modes like claude-code, internal newlines are encoded as Kitty shift-enter sequences (\x1b[13;2u) so multi-line text is submitted as a single input
    • Wait behavior: by default waits for the session to reach the idle state (= AI CLI ready for input) before sending. Automatic for AI modes. Use --no-wait to send immediately (default for plain terminal modes)
    • Timeout defaults to 60 seconds
  • slay pty type <id> <data> (alias: write) — send raw bytes to PTY stdin. Use only when submit is wrong — e.g. appending text mid-prompt without submitting, or sending exact byte sequences. No newline added, no encoding.

  • Key helper subcommands (slay pty <key> <id>) — send a single control sequence:

    • arrow-up, arrow-down, arrow-left, arrow-right — cursor / history nav
    • tab, shift-tab — autocomplete; shift-tab cycles claude-code modes (plan/auto-accept/normal)
    • backspace — delete char
    • escape — ESC key (double-invoke to cancel a claude-code generation)
    • cancel — Ctrl+C interrupt
  • slay pty wait <id> [--state <state>] [--timeout <ms>] [--json] — block until a session reaches a specific state.

    • Default state: idle (AI ready for input)
    • Default timeout: 60 seconds
    • Exit codes: 0 = reached state, 2 = timeout, 1 = session died
  • slay pty respawn <task-id> — kill + remount a task's main PTY. Task must be open in the app. Task-id prefix supported.

  • slay pty create <task-id> [--mode <m>] [--label <l>] [--no-wait] [--timeout <ms>] — create a new terminal tab (new group) for a task.

    • Auto-opens the task in the app (PTY only spawns when the renderer mounts the tab)
    • --mode defaults to terminal (plain shell). Use claude-code, codex, etc. for agent tabs
    • Waits for the PTY to appear in /api/pty by default (5s timeout). --no-wait returns immediately
    • Prints the new session id
  • slay pty split <id> [--no-wait] [--timeout <ms>] — add a new pane to the same group as an existing tab/session.

    • <id> accepts a full session id (taskId:tabId) or just the tab id; prefix matching supported
    • New pane is always plain terminal mode
    • Wait behavior identical to create
  • slay pty kill <id> — terminate a PTY session.

Show full SKILL.md (17 more words)Show less

Orchestration patterns

Submit a prompt to a Claude Code session and wait for completion:

bash
slay pty submit <id> "Fix the failing tests in src/auth.ts"
slay pty wait <id> --state idle --timeout 300000
slay pty buffer <id>  # read the result

Pipe multi-line input:

bash
cat prompt.md | slay pty submit <id>

© debuglebowski, GPL-3.0. 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 .agents/skills/slay-pty of debuglebowski/slayzone.

Open the folder on GitHubat commit e912716

Compare with similar skills

Slay Pty 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.

Slay Pty compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Slay Pty this skilldebuglebowski/slayzone191—~916Automated safety check: PassGPL-3.0
Vellum Terminal Sessionsvellum-ai/vellum-assistant1.4k—~704Automated safety check: PassMIT
Session Handoffsickn33/agentic-awesome-skills47k—~1.8kAutomated safety check: NotesMIT
Sessionanthropics/claude-for-legal9.6k3 repos~478Automated safety check: PassApache-2.0
Session History Searchslopus/happy24k—~3.1kAutomated safety check: PassMIT
Terminal Openeraffaan-m/ECC274k—~635Automated safety check: PassMIT

Similar skills

  • Vellum Terminal Sessions

    vellum-ai/vellum-assistant

    Manage persistent tmux terminal sessions: create, read, write to, list, and close named shell sessions.

    1.4k GitHub stars~704 tokensUpdated 3 days ago
    Auto-check passed
  • Session Handoff

    sickn33/agentic-awesome-skills

    A skill your agent uses when context approaches capacity, before /clear or /compact, when switching tasks, or when ending a coding session: produces a structured handoff artifact for the next session.

    47k GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Session

    anthropics/claude-for-legal

    Official

    Run a focused N-question study session on a subject — MBE, essay, or flashcards.

    9.6k GitHub starsUsed in 3 repos~478 tokens
    EducationAuto-check passed
  • Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.

    24k GitHub stars~3.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Terminal Opener

    affaan-m/ECC

    Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery…

    274k GitHub stars~635 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Session Handoff

    davila7/claude-code-templates

    Creates comprehensive handoff documents for seamless AI agent session transfers.

    32k GitHub starsUsed in 2 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

More from debuglebowski/slayzone

All 16 skills in this repo
  • Comparison Page

    debuglebowski/slayzone

    Create or update objective website comparison pages and head-to-head pages from the comparison canon.

    191 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Slay Artifacts

    debuglebowski/slayzone

    Manage task artifacts (files, folders) via the slay CLI. An agent skill from debuglebowski/slayzone.

    191 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Slay Automations

    debuglebowski/slayzone

    Create and manage automations via the slay CLI. An agent skill from debuglebowski/slayzone.

    191 GitHub stars~627 tokensUpdated 1 mo ago
    Auto-check passed
  • Slay Orchestrate

    debuglebowski/slayzone

    Supervise a set of slay tasks through planning, execution, and verification

    191 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Slay Context

    debuglebowski/slayzone

    Ensure root instruction files include SlayZone environment context

    191 GitHub stars~448 tokensUpdated 1 mo ago
    Auto-check passed
  • Commit

    debuglebowski/slayzone

    Commit the changes that has been worked on in this session. An agent skill from debuglebowski/slayzone.

    191 GitHub stars~718 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Slay Pty

What does Slay Pty do?

Interact with PTY terminal sessions via the slay CLI. An agent skill from debuglebowski/slayzone. Slay Pty is an agent skill from debuglebowski/slayzone.

How do I install Slay Pty in Claude Code?

Run `npx skills add debuglebowski/slayzone --skill slay-pty -a claude-code`. Or copy the skill folder (.agents/skills/slay-pty in debuglebowski/slayzone) into .claude/skills/slay-pty in your project. Claude Code loads it when a task matches its description.

How do I install Slay Pty in Codex?

Run `npx skills add debuglebowski/slayzone --skill slay-pty -a codex`. Or copy the skill folder (.agents/skills/slay-pty in debuglebowski/slayzone) into .agents/skills/slay-pty in your project. Codex loads it when a task matches its description.

Can I use Slay Pty 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 debuglebowski/slayzone --skill slay-pty -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slay-pty, .gemini/skills/slay-pty, .github/skills/slay-pty and .opencode/skills/slay-pty in your project.

What does Slay Pty need to run?

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

Does Slay Pty 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 Slay Pty 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 Slay Pty use?

Slay Pty is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Slay Pty use?

About 916 tokens (SKILL.md is roughly 3.7k 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 Slay Pty?

Skills that share tags, products or a category with Slay Pty: Vellum Terminal Sessions (vellum-ai/vellum-assistant, 1.4k stars), Session Handoff (sickn33/agentic-awesome-skills, 47k stars), Session (anthropics/claude-for-legal, 9.6k stars) and Session History Search (slopus/happy, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Slay Pty?

debuglebowski (a GitHub user) maintains it in debuglebowski/slayzone, which has 191 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 3, 2026.

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