New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Slay Orchestrate

by debuglebowski in debuglebowski/slayzone

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

GPL-3.0Auto-check passedAgent Workflows

Install Slay Orchestrate

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

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

GitHub CLI
$ gh skill install debuglebowski/slayzone slay-orchestrate --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-orchestrate .claude/skills/slay-orchestrate && 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-orchestrate
GitHub stars
191
Token cost
~1.3k tokens
SKILL.md length
649 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
GPL-3.0

At a glance

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

  • Works in 6 steps: Resolve the target set → Create the progress log artifact → Dispatch → …
  • Agent Workflows work in your project
  • SKILL.md covers 1. Resolve the target set, 2. Create the progress log…, 3. Dispatch and 4. Supervise, plus 3 more sections
  • Calls jq

What it does

Slay Orchestrate is an agent skill from debuglebowski/slayzone. Supervise a set of slay tasks through planning, execution, and verification

Its SKILL.md is about 1.3k 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 Agent Workflows. The licence is GPL-3.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/slay-orchestrate”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Resolve the target set
  2. Create the progress log artifact
  3. Dispatch
  4. Supervise
  5. Plan review bar
  6. Completion

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

    Shell commands in SKILL.md call:

    • jq

    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 Orchestrate loads about 1.3k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 649 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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). 649 words, ~1,345 tokens.

Download SKILL.mdSave it as .claude/skills/slay-orchestrate/SKILL.md (or your agent's skills folder).
name
slay-orchestrate
description
Supervise a set of slay tasks through planning, execution, and verification
depends_on
slay-tasks, slay-pty, slay-artifacts
trigger
manual

Orchestrate any set of slay tasks toward completion. The user tells you which tasks to supervise (free-form: ids, tags, a project, a filter, or a description like "all refactor tasks in backlog"); you dispatch each to its own PTY, review plans, keep agents unblocked, and drive them to done. Works equally well for top-level tasks and subtasks — the skill does not care.

Never commit. Your job ends at slay tasks done.

1. Resolve the target set

  1. Parse the user's free-form selector.
  2. Resolve to concrete task IDs via slay --dev tasks list --json (filter client-side as needed), slay --dev tasks search, or slay --dev tasks subtasks <parent>.
  3. If zero tasks match, stop and tell the user no tasks were found for that selector. Do not guess or expand scope.
  4. List matched tasks (id + title) back to the user as confirmation, then proceed.

2. Create the progress log artifact

Create an artifact on the orchestrator's own task ($SLAYZONE_TASK_ID) named orchestration-log.md. Use a markdown table:

markdown
# Orchestration log

| time | task | event | note |
|------|------|-------|------|

Create once:

bash
printf '# Orchestration log\n\n| time | task | event | note |\n|------|------|-------|------|\n' | slay --dev tasks artifacts create "orchestration-log.md"

Append rows throughout the run:

bash
printf '| %s | %s | %s | %s |\n' "$(date -u +%FT%TZ)" "<taskId>" "<event>" "<note>" | slay --dev tasks artifacts append <artifactId>

Event vocabulary: started, plan-ready, plan-refined, plan-approved, question, stuck, done, error.

3. Dispatch

Default: parallel. Override to serial if the user says so (e.g. "one at a time", "serial") or if tasks obviously depend on each other.

Per task:

bash
slay --dev tasks open <id>
slay --dev pty wait <id> --state attention
slay --dev pty submit <id> "Enter plan mode. Read the task with \`slay --dev tasks view\`. Design the most sustainable, robust long-term solution. Preserve all requested functionality — do not drop features to simplify."
slay --dev pty write <id> $'\r'

Log started.

Parallelize by backgrounding each dispatch block with & and wait.

4. Supervise

Poll slay --dev pty list --json on a short interval. Act on each task that enters attention:

  1. Read buffer: slay --dev pty buffer <id>.
  2. Classify what the agent is waiting on and respond per the table below.
  3. Append a log row.
SituationResponse
Plan-mode exit prompt (agent presenting plan)Review plan vs task description. Check: sustainable long-term? preserves all requested functionality? no scope creep? If yes → send 1 (Yes, and use auto mode). If no → send 4 + specific feedback, wait for re-plan, review again. Loop until plan meets the bar.
Edit approval prompt during executionSend 2 (Yes, allow all edits during this session) — plan was already vetted.
Ultraplan trap ("◆ ultraplan ready" or "Run ultraplan in the cloud?")Recovery: pty write <id> $'\x1b[B' → $'\r' → "2" → $'\r', then pty submit <id> "Execute the plan directly, no more planning". For the cloud prompt, just send 2 + enter.
Agent asks a user-directed question it cannot answer from the task descriptionAppend question row to log with the verbatim question, ping the user in chat, and wait. Do not guess on the user's behalf.
Agent appears stuck (no progress for an extended period, repeated same buffer)Append stuck row, ping user with the last buffer snippet.
Agent finished (completion message + no prompt)Verify: read changed files directly, run typecheck/build if the task warrants it. Then slay --dev tasks done <id>. Log done.

After every approval/feedback action, always follow pty submit with slay --dev pty write <id> $'\r' — submit does not reliably press enter.

Show full SKILL.md (173 more words)Show less

5. Plan review bar

Reject a plan and send feedback (option 4) if any of these are true:

  • Proposes a quick hack where a sustainable refactor is possible within scope.
  • Drops, hides, or defers functionality that the task description requests.
  • Introduces abstractions or features the task did not ask for.
  • Skips verification (tests, typecheck, build) when the change warrants it.
  • Assumes state without reading the code.

Feedback should be specific ("use shared helper X instead of inlining", "preserve the Y callback that task description requires"), not vague ("make it better").

6. Completion

When all target tasks are done (or blocked on user), append a final summary row to the log and report back to the user:

  • count done / count blocked / count errored
  • link to the log artifact ([log](artifact:<id>))
  • outstanding questions for the user, if any

Do not commit. Do not open PRs. Do not mark the orchestrator task done — the user does that.

Parallel polling pattern

bash
while :; do
  slay --dev pty list --json | jq -r '.[] | select(.task_id | IN($ids[])) | "\(.task_id) \(.state)"' --argjson ids '["id1","id2"]'
  sleep 5
done

Break when every tracked task reaches a terminal state (done or a user-blocking attention you already handled).

© 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-orchestrate of debuglebowski/slayzone.

Open the folder on GitHubat commit e912716

Compare with similar skills

Slay Orchestrate 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 Orchestrate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Slay Orchestrate this skilldebuglebowski/slayzone191—~1.3kAutomated safety check: PassGPL-3.0
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official37k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k34 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official37k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    37k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 34 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    37k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    794 GitHub starsUsed in 89 repos~8.2k 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 Context

    debuglebowski/slayzone

    Ensure root instruction files include SlayZone environment context

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

  • Slay Pty

    debuglebowski/slayzone

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

    191 GitHub stars~916 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

Categories

Questions about Slay Orchestrate

What does Slay Orchestrate do?

Supervise a set of slay tasks through planning, execution, and verification. Slay Orchestrate is an agent skill from debuglebowski/slayzone.

When should I use Slay Orchestrate?

Slay Orchestrate fits situations like: agent Workflows work in your project.

How do I install Slay Orchestrate in Claude Code?

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

How do I install Slay Orchestrate in Codex?

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

Can I use Slay Orchestrate 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-orchestrate -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-orchestrate, .gemini/skills/slay-orchestrate, .github/skills/slay-orchestrate and .opencode/skills/slay-orchestrate in your project.

What does Slay Orchestrate need to run?

Going by SKILL.md and its folder, Slay Orchestrate needs the command-line tools its instructions call (jq).

Does Slay Orchestrate 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 Orchestrate 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 Orchestrate use?

Slay Orchestrate 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 Orchestrate use?

About 1.3k tokens (SKILL.md is roughly 5.4k 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 Orchestrate?

Skills that share tags, products or a category with Slay Orchestrate: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 37k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Slay Orchestrate?

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.