Agent skill

Field Testing

by n1m21n in n1m21n/Infinite

Proving a Field change didn't regress: tests/field/corpus.txt golden harness (RunFieldTest), per-domain conformance, re-baselining, per-step exit criteria.

Custom licenceAuto-check passed

Install Field Testing

skills CLI
$ npx skills add n1m21n/Infinite --skill field-testing -a claude-code

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

GitHub CLI
$ gh skill install n1m21n/Infinite field-testing --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/n1m21n/Infinite.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/field-testing .claude/skills/field-testing && 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
field-testing
GitHub stars
264
Token cost
~3.9k tokens
SKILL.md length
2,050 words
Files
1
Skills in repo
56
Repo updated
First seen
Licence
Custom licence

At a glance

Proving a Field change didn't regress: tests/field/corpus.txt golden harness (RunFieldTest), per-domain conformance, re-baselining, per-step exit criteria.

  • Works in 8 steps: Invariants → How testing works in this repo → The step-1 regression corpus → …
  • SKILL.md covers When to use (full scope), 0. Invariants, 1. How testing works in this… and 2. The step-1 regression corpus, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Field Testing is an agent skill from n1m21n/Infinite. Proving a Field change didn't regress: tests/field/corpus.txt golden harness (RunFieldTest), per-domain conformance, re-baselining, per-step exit criteria. Use before/after any Field compiler or language change, for "did this break saved patches", or when writing a prompt for Field work.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with C++. The repository describes itself as: Infinite is a node-based audiovisual workstation — real-time GPU video compositing, procedural 3D geometry, modular synths, DSP, and VST3/AU plugin hosting.

Example prompts

  • “did this break saved patches”
  • “/field-testing”

Workflow steps

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

  1. Invariants
  2. How testing works in this repo
  3. The step-1 regression corpus
  4. The golden-value harness
  5. Re-baselining across the randomness break
  6. Per-domain conformance cases
  7. Exit criterion per build step
  8. What the harness cannot prove, and what covers it instead

What it can do on your machine

Read from SKILL.md and the folder at commit 2e82b19. 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.

    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

Field Testing loads about 3.9k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 2,050 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,050 words (~3,945 tokens).

“How to prove a Field change did not regress Infinite — extending the regression corpus at tests/field/corpus.txt without baking new behaviour into golden values, the golden-value harness as an INFINITE_* fixture, per-domain conformance cases for frame/element/pixel/sample, how to re-baseline across…”

— opening of SKILL.md by n1m21n, Custom licence
name
field-testing

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/field-testing of n1m21n/Infinite.

Open the folder on GitHubat commit 2e82b19

Compare with similar skills

Field Testing 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.

Field Testing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Field Testing this skilln1m21n/Infinite264—~3.9kAutomated safety check: PassCustom licence
Paddle BuildPaddlePaddle/Paddle24k—~1kAutomated safety check: PassApache-2.0
Fory Releaseapache/fory4.6k—~2.9kAutomated safety check: PassApache-2.0
ONNX Runtime Shape Inference Safety Auditmicrosoft/onnxruntime22k—~3.3kAutomated safety check: PassMIT
Code Audit3stoneBrother/code-audit8931 repos~2.7kAutomated safety check: PassNone
Qt C++ Code Reviewx-tools-author/x-tools1.1k2 repos~4.3kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Paddle Build

    PaddlePaddle/Paddle

    A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.

    24k GitHub stars~1k tokensUpdated 8 days ago
    AI & LLM EngineeringAuto-check passed
  • Fory Release

    apache/fory

    Prepare an Apache Fory release candidate from a clean release branch, including the version bump, RC tag, JVM staging, ASF source artifacts, SVN upload, and vote email.

    4.6k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Official

    Finds and fixes out-of-range output writes in ONNX Runtime operator shape-inference functions where a getNumOutputs guard admits too few outputs.

    22k GitHub stars~3.3k tokensUpdated today
    SecurityAuto-check passed
  • Code Audit

    3stoneBrother/code-audit

    Professional code security audit skill covering 55+ vulnerability types.

    893 GitHub starsUsed in 1 repo~2.7k tokens
    SecurityAuto-check passed
  • Qt C++ Code Review

    x-tools-author/x-tools

    Read-only review of Qt6 C++ code that combines a deterministic lint script with six parallel analysis agents and reports only high-confidence issues.

    1.1k GitHub starsUsed in 2 repos~4.3k tokens
    DevelopmentAuto-check passed
  • Translation

    doxygen/doxygen

    Keeps all Doxygen and Doxywizard translations up to date across three mechanisms: translator C++ classes (src/translatorxx.h), Qt .ts locale files for the Doxywizard GUI (addon/doxywizard/i18n/)…

    6.6k GitHub stars~5.2k tokensUpdated 8 days ago
    Writing & ContentAuto-check passed

More from n1m21n/Infinite

All 56 skills in this repo
  • Audio Node UI

    n1m21n/Infinite

    Layout grammar, widgets and visualizers that make Infinite's audio/note node bodies look like real instruments.

    264 GitHub stars~3.6k tokensUpdated yesterday
    Auto-check passed
  • Cable Logic Sweep

    n1m21n/Infinite

    Check connection rules: what can patch into what, what's refused, whether a node's pins are reachable; cross-checks main.cpp's four wiring chains statically.

    264 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • CI Failure Triage

    n1m21n/Infinite

    Diagnose a failed GitHub Actions run (Windows MSVC crash, Linux clang/sanitizer, link errors) from the logs in one pass, and fix every candidate at once instead of one CI round-trip at a time.

    264 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Data Accuracy Sweep

    n1m21n/Infinite

    Sweep for data corruption along a patch chain: copy/paste and save/load drops, altering pass-throughs, stale caches, TextureRevision lies, fan-out memo breaks, bypass, out-of-unit modulation.

    264 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Field Domains

    n1m21n/Infinite

    Field's domain transfer operators (reduce, map, implicit broadcast, resample, downsample): legality, cost, audio→geometry→pixel examples.

    264 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed
  • Field Integration

    n1m21n/Infinite

    How a Field node joins Infinite: INode + IAudioSource/IGeometrySource, ParamRef, ParamMailbox, GLUtil::CompileProgram, Patch save/load grammar, undo.

    264 GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Field Testing

What does Field Testing do?

Proving a Field change didn't regress: tests/field/corpus.txt golden harness (RunFieldTest), per-domain conformance, re-baselining, per-step exit criteria. Field Testing is an agent skill from n1m21n/Infinite.txt golden harness (RunFieldTest), per-domain conformance, re-baselining, per-step exit criteria.

How do I install Field Testing in Claude Code?

Run `npx skills add n1m21n/Infinite --skill field-testing -a claude-code`. Or copy the skill folder (.claude/skills/field-testing in n1m21n/Infinite) into .claude/skills/field-testing in your project. Claude Code loads it when a task matches its description.

How do I install Field Testing in Codex?

Run `npx skills add n1m21n/Infinite --skill field-testing -a codex`. Or copy the skill folder (.claude/skills/field-testing in n1m21n/Infinite) into .agents/skills/field-testing in your project. Codex loads it when a task matches its description.

Can I use Field Testing 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 n1m21n/Infinite --skill field-testing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/field-testing, .gemini/skills/field-testing, .github/skills/field-testing and .opencode/skills/field-testing in your project.

What does Field Testing need to run?

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

Does Field Testing 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 Field Testing 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 Field Testing use?

Field Testing has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Field Testing use?

About 3.9k tokens (SKILL.md is roughly 16k 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 Field Testing?

Skills that share tags, products or a category with Field Testing: Paddle Build (PaddlePaddle/Paddle, 24k stars), Fory Release (apache/fory, 4.6k stars), ONNX Runtime Shape Inference Safety Audit (microsoft/onnxruntime, 22k stars) and Code Audit (3stoneBrother/code-audit, 893 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Field Testing?

n1m21n (a GitHub user) maintains it in n1m21n/Infinite, which has 264 GitHub stars. The repository holds 56 skills in this directory. The repository was last updated on October 7, 2026.

Source: n1m21n/Infinite on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.