Agent skill

Pinchbench

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks.

Install Pinchbench

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a claude-code

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

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench --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/dixiyao/FoT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experiment/pinchbench .claude/skills/pinchbench && 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/

Paste into Claude Code

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .claude/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/dixiyao/FoT.git skills-src && mkdir -p .agents/skills && cp -r skills-src/experiment/pinchbench .agents/skills/pinchbench && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .agents/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/dixiyao/FoT.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/experiment/pinchbench .cursor/skills/pinchbench && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .cursor/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/dixiyao/FoT.git --path experiment/pinchbench

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/dixiyao/FoT.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/experiment/pinchbench .gemini/skills/pinchbench && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .gemini/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/dixiyao/FoT.git skills-src && mkdir -p .github/skills && cp -r skills-src/experiment/pinchbench .github/skills/pinchbench && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .github/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add dixiyao/FoT --skill pinchbench -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install dixiyao/FoT pinchbench --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/dixiyao/FoT.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/experiment/pinchbench .opencode/skills/pinchbench && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pinchbench" agent skill from https://github.com/dixiyao/FoT/tree/main/experiment/pinchbench into .opencode/skills/pinchbench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pinchbench", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: pinchbench
GitHub stars: 113
Used in: 1 other repo
Token cost: ~1.1k tokens
SKILL.md length: 266 words
Files: 262 (incl. scripts, assets)
Skills in repo: 1
Repo updated: Sep 29, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks.

Testing model capabilities
SKILL.md covers Prerequisites, Quick Start, Available Tasks (23) and Command Line Options, plus 4 more sections
Calls uv and jq
Comparing models

What it does

Pinchbench is an agent skill from dixiyao/FoT. Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 264 other files, including scripts and assets (for example `.github/benchmark-models.yml`, `.github/workflows/lint.yml` and `.github/workflows/release.yml`).

It sits in Writing & Content. The repository describes itself as: Federation over Text (FoT) is a federated-learning-like paradigm for multi-agent reasoning. The licence is MIT.

When your agent uses it

Testing model capabilities
Comparing models
Submitting benchmark results to the leaderboard
Checking how well your OpenClaw setup handles calendar

Example prompts

“/pinchbench”

Requirements

Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 9761942. 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/, which the agent can run.
Shell commands in SKILL.md call:
- uv
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- pinchbench.com
- docs.astral.sh
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

Pinchbench loads about 1.1k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 266 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~79
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 dixiyao/FoT at commit 9761942, republished under its MIT licence (© dixiyao). 266 words, ~1,050 tokens.

Download SKILL.mdSave it as .claude/skills/pinchbench/SKILL.md (or your agent's skills folder). This skill also uses 261 other files; get the full folder from GitHub.

name: pinchbench
description: Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or checking how well your OpenClaw setup handles calendar, email, research, coding, and multi-step workflows.
metadata.author: pinchbench
metadata.version: 2.0.0-rc1
metadata.homepage: https://pinchbench.com
metadata.repository: https://github.com/pinchbench/skill

PinchBench Benchmark Skill

PinchBench measures how well LLM models perform as the brain of an OpenClaw agent. Results are collected on a public leaderboard at pinchbench.com.

Prerequisites

Python 3.10+
uv package manager
OpenClaw instance (this agent)

Quick Start

bash

cd <skill_directory>

# Run benchmark with a specific model
uv run benchmark.py --model anthropic/claude-sonnet-4

# Run only automated tasks (faster)
uv run benchmark.py --model anthropic/claude-sonnet-4 --suite automated-only

# Run specific tasks
uv run benchmark.py --model anthropic/claude-sonnet-4 --suite task_calendar,task_stock

# Skip uploading results
uv run benchmark.py --model anthropic/claude-sonnet-4 --no-upload

Available Tasks (23)

Task	Category	Description
`task_sanity`	Basic	Verify agent works
`task_calendar`	Productivity	Calendar event creation
`task_stock`	Research	Stock price lookup
`task_blog`	Writing	Blog post creation
`task_weather`	Coding	Weather script
`task_summary`	Analysis	Document summarization
`task_events`	Research	Conference research
`task_email`	Writing	Email drafting
`task_memory`	Memory	Context retrieval
`task_files`	Files	File structure creation
`task_workflow`	Integration	Multi-step API workflow
`task_clawdhub`	Skills	ClawHub interaction
`task_skill_search`	Skills	Skill discovery
`task_image_gen`	Creative	Image generation
`task_humanizer`	Writing	Text humanization
`task_daily_summary`	Productivity	Daily digest
`task_email_triage`	Email	Inbox triage
`task_email_search`	Email	Email search
`task_market_research`	Research	Market analysis
`task_spreadsheet_summary`	Analysis	Spreadsheet analysis
`task_eli5_pdf_summary`	Analysis	PDF simplification
`task_openclaw_comprehension`	Knowledge	OpenClaw docs comprehension
`task_second_brain`	Memory	Knowledge management

Command Line Options

Option	Description
`--model`	Model identifier (e.g., `anthropic/claude-sonnet-4`)
`--suite`	`all`, `automated-only`, or comma-separated task IDs
`--output-dir`	Results directory (default: `results/`)
`--timeout-multiplier`	Scale task timeouts for slower models
`--runs`	Number of runs per task for averaging
`--no-upload`	Skip uploading to leaderboard
`--register`	Request new API token for submissions
`--upload FILE`	Upload previous results JSON

Token Registration

To submit results to the leaderboard:

bash

# Register for an API token (one-time)
uv run benchmark.py --register

# Run benchmark (auto-uploads with token)
uv run benchmark.py --model anthropic/claude-sonnet-4

Results

Results are saved as JSON in the output directory:

bash

# View task scores
jq '.tasks[] | {task_id, score: .grading.mean}' results/0001_anthropic-claude-sonnet-4.json

# Show failed tasks
jq '.tasks[] | select(.grading.mean < 0.5)' results/*.json

# Calculate overall score
jq '{average: ([.tasks[].grading.mean] | add / length)}' results/*.json

Adding Custom Tasks

Create a markdown file in tasks/ following TASK_TEMPLATE.md. Each task needs:

YAML frontmatter (id, name, category, grading_type, timeout)
Prompt section
Expected behavior
Grading criteria
Automated checks (Python grading function)

Leaderboard

View results at pinchbench.com. The leaderboard shows:

Model rankings by overall score
Per-task breakdowns
Historical performance trends

Files

SKILL.md and 261 other files (scripts, assets) in experiment/pinchbench of dixiyao/FoT.

SKILL.md
.github/benchmark-models.yml
.github/workflows/lint.yml
.github/workflows/release.yml
.github/workflows/update-task-count.yml
.gitignore
.pre-commit-config.yaml
BENCHMARK_VERSION
Dockerfile.benchmark
LICENSE
README.md
assets/GPT4.pdf
assets/OpenClaw Agent Use Cases and Gap Analysis for PinchBench.pdf
assets/ai_blog.txt
assets/broken_ci.yml
assets/broken_k8s_deployment.yml
assets/cncf-tag-runtime-notes.md
assets/company_expenses.xlsx
… and 244 more

Open the folder on GitHubat commit 9761942

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in dixiyao/FoT, which our catalogue first saw on October 7, 2026.

aiskillstore/marketplaceskills/pinchbench/pinchbench

Compare with similar skills

Pinchbench 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.

Pinchbench compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Pinchbench this skilldixiyao/FoT	113	1 repos	~1.1k	Automated safety check: Pass	MIT	10 days ago
Notion To Blogwasp-lang/wasp	19k	—	~922	Automated safety check: Pass	MIT	yesterday
Cuimao TranslatorCuimao777/cuimao-translator	486	—	~3.2k	Automated safety check: Pass	None	5 mo ago
AI Daily Newsgeekjourneyx/ai-daily-skill	235	—	~2.3k	Automated safety check: Pass	None	today
China Travel Kittczyliu/china-travel-kit	194	—	~1.3k	Automated safety check: Pass	MIT	1 mo ago
Story Maintenancedanjdewhurst/story-skills	283	1 repos	~5.4k	Automated safety check: Notes	MIT	yesterday

Similar skills

Notion To Blog
wasp-lang/wasp
Transfer a blog post from Notion to the Wasp blog. An agent skill from wasp-lang/wasp.
19k GitHub stars~922 tokensUpdated yesterday
Writing & ContentAuto-check passed
Cuimao Translator
Cuimao777/cuimao-translator
Translate English PDF books into natural Chinese with three quality modes.
486 GitHub stars~3.2k tokensUpdated 5 mo ago
Writing & ContentAuto-check passed
AI Daily News
geekjourneyx/ai-daily-skill
Fetches AI news from smol.ai RSS and generates structured markdown with intelligent summarization and categorization.
235 GitHub stars~2.3k tokensUpdated today
Writing & ContentAuto-check passed
China Travel Kit
tczyliu/china-travel-kit
Research and plan first-time independent trips in China with bilingual, source-aware city data and official live-check entry points.
194 GitHub stars~1.3k tokensUpdated 1 mo ago
Writing & ContentAuto-check passed
Story Maintenance
danjdewhurst/story-skills
This skill should be used when the user asks to "validate", "reindex", "repair registries", "check links", "run the continuity, pacing, clue, voice, or name checks", "count words", "summarize a…
283 GitHub starsUsed in 1 repo~5.4k tokens
Writing & ContentAuto-check: notes
Whitepaper Bare Section Prose Filler
FlorianBruniaux/claude-code-ultimate-guide
Adds two to four sentences of intro prose before each bare heading in the French and English whitepapers, splitting the work across nine parallel agents.
6.1k GitHub stars~1.5k tokensUpdated 2 days ago
Writing & ContentAuto-check passed

Questions about Pinchbench

What does Pinchbench do?

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Pinchbench is an agent skill from dixiyao/FoT. Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks.

When should I use Pinchbench?

Pinchbench fits situations like: testing model capabilities; comparing models; submitting benchmark results to the leaderboard; checking how well your OpenClaw setup handles calendar.

How do I install Pinchbench in Claude Code?

Run `npx skills add dixiyao/FoT --skill pinchbench -a claude-code`. Or copy the skill folder (experiment/pinchbench in dixiyao/FoT) into .claude/skills/pinchbench in your project. Claude Code loads it when a task matches its description.

How do I install Pinchbench in Codex?

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

Can I use Pinchbench 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 dixiyao/FoT --skill pinchbench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pinchbench, .gemini/skills/pinchbench, .github/skills/pinchbench and .opencode/skills/pinchbench in your project.

What does Pinchbench need to run?

Going by SKILL.md and its folder, Pinchbench needs the command-line tools its instructions call (uv and jq). Our summary lists: Python 3.

Does Pinchbench access the network?

SKILL.md names 2 domains. As links in the text: pinchbench.com and docs.astral.sh. This is read from the text; nothing was executed.

Is Pinchbench 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 Pinchbench use?

Pinchbench is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pinchbench use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Pinchbench?

Skills that share tags, products or a category with Pinchbench: Notion To Blog (wasp-lang/wasp, 19k stars), Cuimao Translator (Cuimao777/cuimao-translator, 486 stars), AI Daily News (geekjourneyx/ai-daily-skill, 235 stars) and China Travel Kit (tczyliu/china-travel-kit, 194 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pinchbench?

dixiyao (a GitHub user) maintains it in dixiyao/FoT, which has 113 GitHub stars. The repository was last updated on September 29, 2026.

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

Install Pinchbench

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

PinchBench Benchmark Skill

Prerequisites

Quick Start

Available Tasks (23)

Command Line Options

Token Registration

Results

Adding Custom Tasks

Leaderboard

Files

Used in 1 other repository

Compare with similar skills

Similar skills

Notion To Blog

Cuimao Translator

AI Daily News

China Travel Kit

Story Maintenance

Whitepaper Bare Section Prose Filler

Related

Questions about Pinchbench