Agent skill

Field Lab

by KyleAMathews in KyleAMathews/field-lab

An always-available field lab for thinking with AI, guided by Kit.

No licenceAuto-check passedKnowledge Management

Install Field Lab

skills CLI
$ npx skills add KyleAMathews/field-lab --skill field-lab -a claude-code

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

GitHub CLI
$ gh skill install KyleAMathews/field-lab field-lab --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
field-lab
GitHub stars
576
Token cost
~15k tokens
SKILL.md length
7,159 words
Files
318 (incl. scripts, assets)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

An always-available field lab for thinking with AI, guided by Kit.

  • Works in 4 steps: Restate the relevant experience in the… → Name an emotion or need only when the… → Say why the response makes sense in the… → …
  • From a factual query
  • SKILL.md covers Kit, the field caddy, Keep three axes separate, Instrument-only authority gate and Continue an existing interview, plus 11 more sections
  • Calls node

What it does

Field Lab is an agent skill from KyleAMathews/field-lab. An always-available field lab for thinking with AI, guided by Kit. Use it for any question, from a factual query or practical problem to a genuine tension, hostile thesis test, high-stakes decision, or full recursive dialectic. Give direct answers when enough. Treat open-ended requests to understand, explain, or make sense of conceptual or interpretive material as caddying prompts, not permission for a long explanation: recommend a concrete way to examine the material and run only what the user selects. For other…

Its SKILL.md is about 15k tokens, which your agent loads only when the skill is triggered. The skill folder holds 324 other files, including scripts and assets (for example `.agents/behaviors/bounded-instrument-return/BEHAVIOR.md`, `.agents/behaviors/exact-authority/BEHAVIOR.md` and `.agents/behaviors/human-branch-control/BEHAVIOR.md`).

It sits in Knowledge Management, covering Essays and academic help and Source-grounded notebooks. The repository describes itself as: A field lab for thinking with AI.

When your agent uses it

  • From a factual query
  • Practical problem to a genuine tension
  • Hostile thesis test
  • High-stakes decision

Example prompts

  • “/field-lab”

Workflow steps

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

  1. Restate the relevant experience in the user's terms without adding a theory.
  2. Name an emotion or need only when the user's words support it, and state it tentatively.
  3. Say why the response makes sense in the stated context without treating the user's interpretation as proven fact or approving harmful…
  4. When the user is expressing rather than requesting analysis or change, ask permission before making that shift.

What it can do on your machine

Read from SKILL.md and the folder at commit fc2f3e2. 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:

    • 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

Field Lab loads about 15k tokens when it runs. Until then it costs about 249 tokens; SKILL.md has 7,159 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~249
When it runs · the whole SKILL.md, loaded when a task matches
~15k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 7,159 words (~14,519 tokens).

“Help first; explain the lab only as needed. Start with the smallest useful feedback loop, keep the whole instrument bench available, and start a Field Log only when the work needs one.”

— opening of SKILL.md by KyleAMathews
name
field-lab

Read the full SKILL.md on GitHub

Files

SKILL.md and 317 other files (scripts, assets) in the repository root of KyleAMathews/field-lab.

  • SKILL.md
  • .agents/behaviors/bounded-instrument-return/BEHAVIOR.md
  • .agents/behaviors/exact-authority/BEHAVIOR.md
  • .agents/behaviors/human-branch-control/BEHAVIOR.md
  • .agents/behaviors/selected-route-integrity/BEHAVIOR.md
  • .gitignore
  • README.md
  • artifact-browser/.cursorrules
  • artifact-browser/.gitignore
  • artifact-browser/AGENTS.md
  • artifact-browser/CLAUDE.md
  • artifact-browser/COPILOT.md
  • artifact-browser/LICENSE
  • artifact-browser/README.md
  • … and 304 more

Open the folder on GitHubat commit fc2f3e2

Compare with similar skills

Field Lab 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 Lab compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Field Lab this skillKyleAMathews/field-lab576—~15kAutomated safety check: PassNone
NotebookLM Research Workflowclaude-world/notebooklm-skill467—~1.8kAutomated safety check: PassMIT
SurveySNL-UCSB/literature-survey-skill106—~5kAutomated safety check: PassMIT
Nlm Skilliusztinpaul/ai-research-os-workshop1791 repos~6.9kAutomated safety check: PassMIT
NotebookLM CLI Guidejacob-bd/notebooklm-cli256—~3.4kAutomated safety check: WarnMIT
Notebooklmalirezarezvani/claude-skills28k—~4kAutomated safety check: PassMIT

Similar skills

  • NotebookLM Research Workflow

    claude-world/notebooklm-skill

    Creates NotebookLM notebooks from URLs, text and files, asks cited questions, runs web research and generates audio, slides, quizzes and other artifacts.

    467 GitHub stars~1.8k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • Survey

    SNL-UCSB/literature-survey-skill

    Literature survey assistant with four modes: /survey intent (capture student goals, expertise, and success criteria), /survey triage (landscape mapping via NotebookLM), /survey deepen (structured…

    106 GitHub stars~5k tokensUpdated 6 mo ago
    Knowledge ManagementAuto-check passed
  • Nlm Skill

    iusztinpaul/ai-research-os-workshop

    Expert guide for the NotebookLM CLI (nlm) and MCP server - interfaces for Google NotebookLM.

    179 GitHub starsUsed in 1 repo~6.9k tokens
    Knowledge ManagementAuto-check passed
  • NotebookLM CLI Guide

    jacob-bd/notebooklm-cli

    Guides use of the nlm command-line tool to automate Google NotebookLM: notebooks, sources, research, one-shot questions and generated podcasts, reports, quizzes and slides.

    256 GitHub stars~3.4k tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check: warnings
  • Notebooklm

    alirezarezvani/claude-skills

    Browser automation skill for controlling Google's NotebookLM.

    28k GitHub stars~4k tokensUpdated 1 mo ago
    Knowledge ManagementAuto-check passed
  • Notebooklm CLI

    ItamarZand88/CLI-Anything-WEB

    Drives Google NotebookLM via the cli-web-notebooklm command-line tool — create and manage notebooks, add URL/text sources, ask questions grounded in the sources, and generate/download artifacts…

    231 GitHub stars~997 tokensUpdated 8 days ago
    Knowledge ManagementAuto-check passed

Questions about Field Lab

What does Field Lab do?

An always-available field lab for thinking with AI, guided by Kit. Field Lab is an agent skill from KyleAMathews/field-lab. An always-available field lab for thinking with AI, guided by Kit.

When should I use Field Lab?

Field Lab fits situations like: from a factual query; practical problem to a genuine tension; hostile thesis test; high-stakes decision.

How do I install Field Lab in Claude Code?

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

How do I install Field Lab in Codex?

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

Can I use Field Lab 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 KyleAMathews/field-lab --skill field-lab -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-lab, .gemini/skills/field-lab, .github/skills/field-lab and .opencode/skills/field-lab in your project.

What does Field Lab need to run?

Going by SKILL.md and its folder, Field Lab needs the command-line tools its instructions call (node).

Does Field Lab 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 Lab 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 Field Lab use?

No licence was found for Field Lab or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Field Lab use?

About 15k tokens (SKILL.md is roughly 58k 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 Lab?

Skills that share tags, products or a category with Field Lab: NotebookLM Research Workflow (claude-world/notebooklm-skill, 467 stars), Survey (SNL-UCSB/literature-survey-skill, 106 stars), Nlm Skill (iusztinpaul/ai-research-os-workshop, 179 stars) and NotebookLM CLI Guide (jacob-bd/notebooklm-cli, 256 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Field Lab?

KyleAMathews (a GitHub user) maintains it in KyleAMathews/field-lab, which has 576 GitHub stars. The repository was last updated on September 24, 2026.

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