New: 98,000+ 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

Zcode Large Task Fixture

by zai-org in zai-org/ZCode

Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing.

Apache-2.0Auto-check passedTesting & QA

Install Zcode Large Task Fixture

skills CLI
$ npx skills add zai-org/ZCode --skill zcode-large-task-fixture -a claude-code

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

GitHub CLI
$ gh skill install zai-org/ZCode zcode-large-task-fixture --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/zai-org/ZCode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/zcode-large-task-fixture .claude/skills/zcode-large-task-fixture && 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
zcode-large-task-fixture
GitHub stars
7.7k
Token cost
~698 tokens
SKILL.md length
265 words
Files
2 (incl. scripts)
Skills in repo
5
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing.

  • Works in 5 steps: Confirm the target workspace path. Use… → Generate with --turns 3000 for a large… → Read the script output and report the… → …
  • Testing big conversation/task rendering
  • SKILL.md covers Quick Commands, Workflow, Safety and Coverage
  • Runs JavaScript scripts from its folder; calls node

What it does

Zcode Large Task Fixture is an agent skill from zai-org/ZCode. Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing. Use when testing big conversation/task rendering, task list performance, snapshot recovery, tool-call rendering, reasoning, patches, todos, and model usage without spending time chatting manually.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts.

It sits in Testing & QA, covering Task breakdown and Load testing. It works with SQLite. The repository describes itself as: Z.ai's coding agent harness. Powerful, intelligent, extensible. The licence is Apache-2.0.

When your agent uses it

  • Testing big conversation/task rendering
  • Task list performance
  • Snapshot recovery
  • Tool-call rendering

Example prompts

  • “/zcode-large-task-fixture”

Requirements

  • Node.js

Workflow steps

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

  1. Confirm the target workspace path. Use the repository root unless the user names another workspace.
  2. Generate with --turns 3000 for a large fixture. This creates roughly 6,000 messages and 20,000 parts.
  3. Read the script output and report the sessionId, manifest path, counts, and backup directory.
  4. Verify with --verify .
  5. Tell the user to restart or refresh the app if it was already running, then open the pinned task titled Performance Fixture Large Mixed…

What it can do on your machine

Read from SKILL.md and the folder at commit aac4755. 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

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    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

Zcode Large Task Fixture loads about 698 tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 265 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~698

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); the scripts in this folder are not scanned.

SKILL.md

The full file from zai-org/ZCode at commit aac4755, republished under its Apache-2.0 licence (© zai-org). 265 words, ~698 tokens.

Download SKILL.mdSave it as .claude/skills/zcode-large-task-fixture/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
zcode-large-task-fixture
description
Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing. Use when testing big conversation/task rendering, task list performance, snapshot recovery, tool-call rendering, reasoning, patches, todos, and model usage without spending time chatting manually.
disable-model-invocation
true

ZCode Large Task Fixture

Use this skill to create a large local task that behaves like a long-running ZCode Agent task. It writes both persistence layers:

  • App task index: ~/.zcode/v2/tasks-index.sqlite
  • Agent session DB: ~/.zcode/cli/db/db.sqlite

The generated task is synthetic test data. Always back up before writing and record the manifest path.

Quick Commands

From the z-code repository root:

bash
node .agents/skills/zcode-large-task-fixture/scripts/generate-large-task-fixture.mjs \
  --workspace "$PWD" \
  --turns 3000

Verify an existing generated task:

bash
node .agents/skills/zcode-large-task-fixture/scripts/generate-large-task-fixture.mjs \
  --verify sess_perf_large_YYYYMMDDHHMMSS_xxxxxxxx

Remove a generated task:

bash
node .agents/skills/zcode-large-task-fixture/scripts/generate-large-task-fixture.mjs \
  --delete sess_perf_large_YYYYMMDDHHMMSS_xxxxxxxx

Workflow

  1. Confirm the target workspace path. Use the repository root unless the user names another workspace.
  2. Generate with --turns 3000 for a large fixture. This creates roughly 6,000 messages and 20,000 parts.
  3. Read the script output and report the sessionId, manifest path, counts, and backup directory.
  4. Verify with --verify <sessionId>.
  5. Tell the user to restart or refresh the app if it was already running, then open the pinned task titled Performance Fixture Large Mixed Task.

Safety

  • The script uses SQLite .backup before generation unless --no-backup is passed.
  • Backups are stored under ~/.zcode/perf-task-backups/<timestamp>/.
  • Manifests are stored under ~/.zcode/perf-task-manifests/<sessionId>.json.
  • Use --delete <sessionId> for generated fixtures. It deletes from tasks-index.sqlite and cascades the agent session rows.
  • Do not delete manually unless you have checked the manifest and confirmed the task id starts with sess_perf_large_.

Coverage

Generated sessions include:

  • User text and file parts
  • Assistant text and reasoning parts
  • Tool parts with completed, running, pending, and error states
  • Bash, Read, Grep, Glob, Edit, Write, TodoWrite, AskUserQuestion, Agent, WebSearch, and WebFetch tool shapes
  • Patch, compaction, subtask, agent, retry, step-start, and step-finish parts
  • Todo rows, session target rows, model usage rows, turn usage rows, and task index searchable text

© zai-org, 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

SKILL.md and 1 other file (scripts) in .agents/skills/zcode-large-task-fixture of zai-org/ZCode.

  • SKILL.md
  • scripts/generate-large-task-fixture.mjs

Open the folder on GitHubat commit aac4755

Compare with similar skills

Zcode Large Task Fixture 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.

Zcode Large Task Fixture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Zcode Large Task Fixture this skillzai-org/ZCode7.7k—~698Automated safety check: PassApache-2.0
Testingar-io/ar-io-node127—~2.8kAutomated safety check: NotesAGPL-3.0
Adding LLM MCP ToolsTriliumNext/Trilium38k—~2.5kAutomated safety check: PassAGPL-3.0
Challengeblueberrycongee/termcanvas405—~1.5kAutomated safety check: PassMIT
Feature Next Task Workflowmylukin/agent-foreman250—~927Automated safety check: NotesNone
Agent Task Backlog Initializermylukin/agent-foreman250—~681Automated safety check: NotesNone

Similar skills

  • Testing

    ar-io/ar-io-node

    Decision guide for testing in the ar-io-node repo — which test layer to use, how to run it, and which helpers to reach for.

    127 GitHub stars~2.8k tokensUpdated today
    Testing & QAAuto-check: notes

  • Adding LLM MCP Tools

    TriliumNext/Trilium

    A skill your agent uses when adding, changing, or reviewing an LLM/MCP tool in Trilium (the defineTools definitions under packages/trilium-core/src/services/llm/tools/ —…

    38k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed

  • Challenge

    blueberrycongee/termcanvas

    Adversarial review skill. An agent skill from blueberrycongee/termcanvas.

    405 GitHub stars~1.5k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

  • Feature Next Task Workflow

    mylukin/agent-foreman

    Enforces a strict next-implement-check-done cycle through the agent-foreman CLI so an agent works one backlog task at a time, with optional TDD gating.

    250 GitHub stars~927 tokensUpdated 8 mo ago
    Testing & QAAuto-check: notes

  • Agent Task Backlog Initializer

    mylukin/agent-foreman

    Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.

    250 GitHub stars~681 tokensUpdated 8 mo ago
    Testing & QAAuto-check: notes

  • Workflow Review

    nabeelhyatt/coworkpowers

    Run parallel multi-agent review on completed knowledge work.

    113 GitHub stars~1.3k tokensUpdated 7 mo ago
    Testing & QAAuto-check passed

More from zai-org/ZCode

All 25 skills in this repo

  • DOCX

    zai-org/ZCode

    Complete DOCX document creation, editing, and analysis capabilities with support for revisions, comments, formatting preservation, and text extraction.

    7.7k GitHub stars~4.9k tokensUpdated yesterday
    Auto-check: notes

  • Visualize

    zai-org/ZCode

    Create visualizations and interactive tools directly in conversation.

    7.7k GitHub stars~8.7k tokensUpdated yesterday
    Auto-check passed

  • PDF

    zai-org/ZCode

    Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.

    7.7k GitHub stars~18k tokensUpdated yesterday
    Auto-check: notes

  • Restore Legacy Sessions

    zai-org/ZCode

    A skill your agent uses when ZCode needs to inspect, plan, or execute restoration of old ACP-era ZCode sessions from ~/.zcode/v2/sessions into the new ZCode task/session stores.

    7.7k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Architecture Governance

    zai-org/ZCode

    Check ZCode module and layer boundaries for code changes. An agent skill from zai-org/ZCode.

    7.7k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • XLSX

    zai-org/ZCode

    Use this skill any time a spreadsheet file is the primary input or output.

    7.7k GitHub starsUsed in 1 repo~4.4k tokens
    Auto-check: notes

Works with

Categories

Questions about Zcode Large Task Fixture

What does Zcode Large Task Fixture do?

Generate, verify, or remove large synthetic ZCode task fixtures in local ~/.zcode persistence for UI/session performance testing. Zcode Large Task Fixture is an agent skill from zai-org/ZCode.zcode persistence for UI/session performance testing.

When should I use Zcode Large Task Fixture?

Zcode Large Task Fixture fits situations like: testing big conversation/task rendering; task list performance; snapshot recovery; tool-call rendering.

How do I install Zcode Large Task Fixture in Claude Code?

Run `npx skills add zai-org/ZCode --skill zcode-large-task-fixture -a claude-code`. Or copy the skill folder (.agents/skills/zcode-large-task-fixture in zai-org/ZCode) into .claude/skills/zcode-large-task-fixture in your project. Claude Code loads it when a task matches its description.

How do I install Zcode Large Task Fixture in Codex?

Run `npx skills add zai-org/ZCode --skill zcode-large-task-fixture -a codex`. Or copy the skill folder (.agents/skills/zcode-large-task-fixture in zai-org/ZCode) into .agents/skills/zcode-large-task-fixture in your project. Codex loads it when a task matches its description.

Can I use Zcode Large Task Fixture 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 zai-org/ZCode --skill zcode-large-task-fixture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zcode-large-task-fixture, .gemini/skills/zcode-large-task-fixture, .github/skills/zcode-large-task-fixture and .opencode/skills/zcode-large-task-fixture in your project.

What does Zcode Large Task Fixture need to run?

Going by SKILL.md and its folder, Zcode Large Task Fixture needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.

Does Zcode Large Task Fixture 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 Zcode Large Task Fixture 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Zcode Large Task Fixture use?

Zcode Large Task Fixture 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 Zcode Large Task Fixture use?

About 698 tokens (SKILL.md is roughly 2.8k 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 Zcode Large Task Fixture?

Skills that share tags, products or a category with Zcode Large Task Fixture: Testing (ar-io/ar-io-node, 127 stars), Adding LLM MCP Tools (TriliumNext/Trilium, 38k stars), Challenge (blueberrycongee/termcanvas, 405 stars) and Feature Next Task Workflow (mylukin/agent-foreman, 250 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Zcode Large Task Fixture?

zai-org (a GitHub organization) maintains it in zai-org/ZCode, which has 7,659 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 2026.

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