Agent skill

Tsz Project Bench

by tsz-org in tsz-org/tsz

Work on TSZ benchmark and project-corpus compatibility. An agent skill from tsz-org/tsz.

Apache-2.0Auto-check passedFrontend & Design

Install Tsz Project Bench

skills CLI
$ npx skills add tsz-org/tsz --skill tsz-project-bench -a claude-code

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

GitHub CLI
$ gh skill install tsz-org/tsz tsz-project-bench --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/tsz-org/tsz.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tsz-project-bench .claude/skills/tsz-project-bench && 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
tsz-project-bench
GitHub stars
577
Token cost
~533 tokens
SKILL.md length
149 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

Work on TSZ benchmark and project-corpus compatibility. An agent skill from tsz-org/tsz.

  • Works in 5 steps: Identify row, phase, and first failure:… → Required/canary/all set:… → Reproduce with the narrowest filter. → …
  • Investigating bench.yml failures
  • SKILL.md covers Rules, Sources, Workflow and Commands
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tsz Project Bench is an agent skill from tsz-org/tsz. Work on TSZ benchmark and project-corpus compatibility. Use when investigating bench.yml failures, project compile guard rows, benchmark dashboard data, PGO bench setup, fixture metadata drift, or real-project blockers such as utility-types, ts-toolbelt, ts-essentials, rxjs, type-fest, zod, kysely, Next, or Vite.

Its SKILL.md is about 530 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 Frontend & Design, covering Forms and validation. It works with Vite, RxJS and Zod. The repository describes itself as: An experiment in fully hand-off software engineering: A performance-first TypeScript checker. The licence is Apache-2.0.

When your agent uses it

  • Investigating bench.yml failures
  • Project compile guard rows
  • Benchmark dashboard data
  • PGO bench setup

Example prompts

  • “/tsz-project-bench”

Workflow steps

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

  1. Identify row, phase, and first failure: prepare, tsc validation, tsz check,
  2. Required/canary/all set: TSZ_PROJECT_COMPILE_SET=.
  3. Reproduce with the narrowest filter.
  4. If typecheck fails, reduce to owning compiler operation before optimizing.
  5. For speed work, name repeated operation and complexity change. No

What it can do on your machine

Read from SKILL.md and the folder at commit 153b25a. 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

Tsz Project Bench loads about 533 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~533

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 tsz-org/tsz at commit 153b25a, republished under its Apache-2.0 licence (© tsz-org). 149 words, ~533 tokens.

Download SKILL.mdSave it as .claude/skills/tsz-project-bench/SKILL.md (or your agent's skills folder).
name
tsz-project-bench
description
Work on TSZ benchmark and project-corpus compatibility. Use when investigating bench.yml failures, project compile guard rows, benchmark dashboard data, PGO bench setup, fixture metadata drift, or real-project blockers such as utility-types, ts-toolbelt, ts-essentials, rxjs, type-fest, zod, kysely, Next, or Vite.

TSZ Project Bench

Use for project-corpus rows, benchmark harness, fixture metadata, PGO bench setup, and website benchmark data.

Rules

  • Read AGENTS.md and docs/plan/ROADMAP.md for durable benchmark/project work.
  • Inspect overlapping PRs/issues.
  • Red row = correctness blocker before speed problem unless failure is runtime, residency, timeout, or OOM.
  • Keep fixture metadata shared across project-fixtures.sh, bench-vs-tsgo.sh, and project-compile-guard.sh.
  • Wrap long/heavy local commands with scripts/safe-run.sh.

Sources

  • scripts/bench/project-fixtures.sh
  • scripts/bench/bench-vs-tsgo.sh
  • scripts/ci/project-compile-guard.sh
  • crates/tsz-website/src/_data/benchmark_data.js
  • .github/workflows/bench.yml

Workflow

  1. Identify row, phase, and first failure: prepare, tsc validation, tsz check, emit scope, crash, timeout, OOM, metadata, website ingestion, timing.
  2. Required/canary/all set: TSZ_PROJECT_COMPILE_SET=<required|canary|all>.
  3. Reproduce with the narrowest filter.
  4. If typecheck fails, reduce to owning compiler operation before optimizing.
  5. For speed work, name repeated operation and complexity change. No fixture-name special cases.

Commands

bash
./scripts/bench/bench-vs-tsgo.sh --prepare-only
./scripts/bench/bench-vs-tsgo.sh --quick --filter "<row>" --json-file /tmp/bench.json
TSZ_PROJECT_COMPILE_FILTER="<row>" TSZ_PROJECT_COMPILE_SET=required scripts/ci/project-compile-guard.sh
TSZ_PROJECT_COMPILE_ALLOW_FAILURES=1 TSZ_PROJECT_COMPILE_SET=all scripts/ci/project-compile-guard.sh

PR notes: goal (green, fast, or grow), row, before/after failure class, first broken phase, owner layer, fixture metadata changes, whether timing is meaningful, commands/CI links.

© tsz-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

Just SKILL.md in .agents/skills/tsz-project-bench of tsz-org/tsz.

Open the folder on GitHubat commit 153b25a

Compare with similar skills

Tsz Project Bench 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.

Tsz Project Bench compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tsz Project Bench this skilltsz-org/tsz577—~533Automated safety check: PassApache-2.0
Arkenvyamcodes/arkenv147—~2.5kAutomated safety check: PassMIT
Tanstack RouterMindrally/skills271—~1.9kAutomated safety check: PassApache-2.0
World Book Skillecho-xianyu/worldbook-skill212—~1.8kAutomated safety check: PassCustom licence
Reglevictorgarciaesgi/regle506—~840Automated safety check: PassMIT
Buzzformbuildnbuzz/buzzform102—~1.5kAutomated safety check: PassMIT

Similar skills

  • Arkenv

    yamcodes/arkenv

    Answer questions about ArkEnv and help implement environment variable validation.

    147 GitHub stars~2.5k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Tanstack Router

    Mindrally/skills

    Type-safe, file-based routing for React with TanStack Router.

    271 GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • World Book Skill

    echo-xianyu/worldbook-skill

    Create and manage SillyTavern Character Cards (角色卡) and World Books (世界书).

    212 GitHub stars~1.8k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Regle

    victorgarciaesgi/regle

    Core Regle form validation in Vue 3 — setup with useRegle, the reactive r$ object, validation properties, displaying errors, and modifiers.

    506 GitHub stars~840 tokensUpdated 11 days ago
    Frontend & DesignAuto-check passed
  • Buzzform

    buildnbuzz/buzzform

    A skill your agent uses when working with BuzzForm schema-driven forms, @buildnbuzz/form-core, @buildnbuzz/form-react, or any related APIs like defineSchema, InferType, FormProvider, useDataField…

    102 GitHub stars~1.5k tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed
  • Regle Migrate Vuelidate

    victorgarciaesgi/regle

    Migrate Vuelidate form validation to Regle. An agent skill from victorgarciaesgi/regle.

    506 GitHub stars~752 tokensUpdated 11 days ago
    Frontend & DesignAuto-check passed

More from tsz-org/tsz

All 12 skills in this repo
  • Run a deep DRY + code-hygiene audit of the Rust workspace and turn the findings into verified, deduplicated, hierarchical GitHub tech-debt issues.

    577 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Audit TSZ repo iteration speed and quality. An agent skill from tsz-org/tsz.

    577 GitHub stars~557 tokensUpdated 1 mo ago
    Auto-check passed
  • A skill your agent uses when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot…

    577 GitHub stars~746 tokensUpdated 1 mo ago
    Auto-check passed
  • Create, refresh, and publish TSZ pull requests with correct body and state.

    577 GitHub stars~555 tokensUpdated 1 mo ago
    Auto-check passed
  • Start TSZ work safely in a crowded multi-agent checkout. An agent skill from tsz-org/tsz.

    577 GitHub stars~518 tokensUpdated 1 mo ago
    Auto-check passed
  • Tsz Architecture

    tsz-org/tsz

    Preserve TSZ architecture boundaries while changing checker, solver, binder, emitter, LSP, WASM, or CLI code.

    577 GitHub stars~547 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Tsz Project Bench

What does Tsz Project Bench do?

Work on TSZ benchmark and project-corpus compatibility. An agent skill from tsz-org/tsz. Tsz Project Bench is an agent skill from tsz-org/tsz. Work on TSZ benchmark and project-corpus compatibility.

When should I use Tsz Project Bench?

Tsz Project Bench fits situations like: investigating bench.yml failures; project compile guard rows; benchmark dashboard data; PGO bench setup.

How do I install Tsz Project Bench in Claude Code?

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

How do I install Tsz Project Bench in Codex?

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

Can I use Tsz Project Bench 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 tsz-org/tsz --skill tsz-project-bench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsz-project-bench, .gemini/skills/tsz-project-bench, .github/skills/tsz-project-bench and .opencode/skills/tsz-project-bench in your project.

What does Tsz Project Bench need to run?

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

Does Tsz Project Bench 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 Tsz Project Bench 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 Tsz Project Bench use?

Tsz Project Bench 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 Tsz Project Bench use?

About 533 tokens (SKILL.md is roughly 2.1k 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 Tsz Project Bench?

Skills that share tags, products or a category with Tsz Project Bench: Arkenv (yamcodes/arkenv, 147 stars), Tanstack Router (Mindrally/skills, 271 stars), World Book Skill (echo-xianyu/worldbook-skill, 212 stars) and Regle (victorgarciaesgi/regle, 506 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tsz Project Bench?

tsz-org (a GitHub organization) maintains it in tsz-org/tsz, which has 577 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 9, 2026.

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