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

Design Lab

by fl-sean03 in fl-sean03/OpenSDL

Scope the physical and interface design of a laboratory before configuring it.

Apache-2.0Auto-check passedBackend & APIs

Install Design Lab

skills CLI
$ npx skills add fl-sean03/OpenSDL --skill design-lab -a claude-code

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

GitHub CLI
$ gh skill install fl-sean03/OpenSDL design-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).

Manual copy
$ git clone --depth 1 https://github.com/fl-sean03/OpenSDL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/design-lab .claude/skills/design-lab && 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
design-lab
GitHub stars
107
Token cost
~1.2k tokens
SKILL.md length
632 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

Scope the physical and interface design of a laboratory before configuring it.

  • Works in 12 steps: Read the nearest AGENTS.md and inspect… → State the loop before the equipment: the… → Define the minimum viable loop. Prefer… → …
  • A user asks how to approach a lab buildout
  • SKILL.md covers Boundary with start-here, Inputs, Procedure and Completion, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Lab is an agent skill from fl-sean03/OpenSDL. Scope the physical and interface design of a laboratory before configuring it. Use when a user asks how to approach a lab buildout, how to break a cell into components, which mechanism or instrument to choose, how to tailor a reference design to their material system or hazards, whether a design is over-engineered, or how to keep a lab extensible.

Its SKILL.md is about 1.2k 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 Backend & APIs, covering API design. The repository describes itself as: A modular Python foundation for reproducible computational and autonomous laboratories. Alpha; the reference profile is simulator-only. The licence is Apache-2.0.

When your agent uses it

  • A user asks how to approach a lab buildout
  • How to break a cell into components
  • Which mechanism
  • Instrument to choose

Example prompts

  • “/design-lab”

Workflow steps

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

  1. Read the nearest AGENTS.md and inspect Git state before changing files. In a laboratory
  2. State the loop before the equipment: the decision, the measurement, the shortest operation
  3. Define the minimum viable loop. Prefer one closed loop with simulated or manual steps over a
  4. Separate plant, interface, capability, and campaign decisions. Keep a physical constraint out of
  5. For each component under discussion, name the functions it serves before naming a mechanism. When
  6. Identify the binding constraint by estimating margin per requirement. Record it. Warn explicitly
  7. Check every borrowed pattern against the material-system table in the guide. Report any row that
  8. Classify each decision as reversible or irreversible. Recommend deliberate design time and outside
  9. Where the laboratory must grow, propose a versioned interface specification and record it in the
  10. For unattended operation, identify each state the machine must observe rather than infer, and
  11. Keep safety functions in an independent rated system that OpenSDL cannot outvote. Do not design
  12. Write results into docs/lab/decisions.md and setup-plan.md: the choice, the rejected

What it can do on your machine

Read from SKILL.md and the folder at commit 43f4988. 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

Design Lab loads about 1.2k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 632 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 fl-sean03/OpenSDL at commit 43f4988, republished under its Apache-2.0 licence (© fl-sean03). 632 words, ~1,229 tokens.

Download SKILL.mdSave it as .claude/skills/design-lab/SKILL.md (or your agent's skills folder).
name
design-lab
description
Scope the physical and interface design of a laboratory before configuring it. Use when a user asks how to approach a lab buildout, how to break a cell into components, which mechanism or instrument to choose, how to tailor a reference design to their material system or hazards, whether a design is over-engineered, or how to keep a lab extensible.

Design a laboratory for its application

Apply the method in docs/guides/design-a-lab.md. This procedure records its output as durable decisions in a laboratory repository.

Boundary with start-here

Use design-lab for plant and interface questions: what to build, which requirement drives it, which choices cannot be revised later, and how a pattern from another field transfers to this material system. Use start-here for OpenSDL configuration: repository context, inventory, capability mapping, and the first workflow. A design session usually precedes a start-here session, or interrupts one when a configuration question turns out to be a physical one.

Inputs

  • the decision the loop must make, and the measurement that informs it;
  • the material system and its relevant properties or hazard classes;
  • throughput, cycle time, and expected campaign length;
  • existing equipment, facility constraints, and budget envelope; and
  • the intended growth path beyond the first workflow.

Begin with partial input. Ask only for what changes the recommendation.

Procedure

  1. Read the nearest AGENTS.md and inspect Git state before changing files. In a laboratory repository, read docs/lab/context.md, inventory.md, setup-plan.md, and decisions.md.
  2. State the loop before the equipment: the decision, the measurement, the shortest operation sequence, and the cycle count needed for convergence. Flag when cycle time and required cycles make the loop impractical, because no downstream choice fixes that.
  3. Define the minimum viable loop. Prefer one closed loop with simulated or manual steps over a broader set of automated but open steps.
  4. Separate plant, interface, capability, and campaign decisions. Keep a physical constraint out of workflow logic.
  5. For each component under discussion, name the functions it serves before naming a mechanism. When requirements conflict inside one part, propose an architectural split rather than a more complex part.
  6. Identify the binding constraint by estimating margin per requirement. Record it. Warn explicitly when a candidate design is borrowed from a field whose binding constraint differs.
  7. Check every borrowed pattern against the material-system table in the guide. Report any row that applies, and treat a recognized hazard class as a prompt for qualified review rather than a resolved question.
  8. Classify each decision as reversible or irreversible. Recommend deliberate design time and outside review for the irreversible ones, and recommend over-provisioning payload, envelope, utilities, bandwidth, and slot count.
  9. Where the laboratory must grow, propose a versioned interface specification and record it in the laboratory repository beside the manifest.
  10. For unattended operation, identify each state the machine must observe rather than infer, and name the failure modes that warrant verification by two different physical principles.
  11. Keep safety functions in an independent rated system that OpenSDL cannot outvote. Do not design an interlock that depends on the orchestration layer.
  12. Write results into docs/lab/decisions.md and setup-plan.md: the choice, the rejected alternatives, the driving constraint, and the condition that would justify revisiting it.
  13. Hand the next task to start-here, create-lab, add-capability, add-adapter, or develop-workflow.
Show full SKILL.md (151 more words)Show less

Completion

The laboratory repository records the loop, the minimum viable path to close it, the binding constraint for each open design question, the irreversible decisions and their headroom, and any interface specification the growth path requires. Each recorded decision names its driving constraint and its expiry condition. Unresolved questions are listed as unknowns rather than assumed.

Stop conditions

Stop before mutation when repository ownership or destination is unclear. Stop when the user asks for a determination that requires a qualified engineer: hazard analysis, material compatibility, quantity limits, containment adequacy, structural or pressure rating, regulatory classification, or a safety case. Describe the relevant considerations and the governing standards, then name the review the decision needs.

Do not approve a design for physical construction or operation. Do not record an assumed material property, hazard rating, or equipment specification as a confirmed fact. Do not commission equipment or perform physical work through this skill.

© fl-sean03, 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/design-lab of fl-sean03/OpenSDL.

Open the folder on GitHubat commit 43f4988

Compare with similar skills

Design 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.

Design Lab compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Lab this skillfl-sean03/OpenSDL107—~1.2kAutomated safety check: PassApache-2.0
Nodejs Backend Patternsever-works/ever-works16218 repos~4kAutomated safety check: PassAGPL-3.0
API DesignerJeffallan/claude-skills12k1 repos~2kAutomated safety check: PassMIT
Pangolin CRUD Endpointsfosrl/pangolin23k—~461Automated safety check: PassCustom licence
Backend PatternshellangleZ/burn-in-cceverywhere-ralph11217 repos~3.3kAutomated safety check: PassNone
API Design Principlesjh941213/my-cc-harness12518 repos~3.4kAutomated safety check: PassNone

Similar skills

  • Nodejs Backend Patterns

    ever-works/ever-works

    Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices.

    162 GitHub starsUsed in 18 repos~4k tokens
    Backend & APIsAuto-check passed

  • API Designer

    Jeffallan/claude-skills

    Designs REST and GraphQL APIs from resource modeling to an OpenAPI 3.1 contract, with versioning, pagination and RFC 7807 error handling.

    12k GitHub starsUsed in 1 repo~2k tokens
    Backend & APIsAuto-check passed

  • Pangolin CRUD Endpoints

    fosrl/pangolin

    Use whenever asked to add, create, or scaffold a CRUD endpoint, router, or entity in this repo's server (create/list/get/update/delete handlers, new…

    23k GitHub stars~461 tokensUpdated today
    Backend & APIsAuto-check passed

  • Backend Patterns

    hellangleZ/burn-in-cceverywhere-ralph

    Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

    112 GitHub starsUsed in 17 repos~3.3k tokens
    Backend & APIsAuto-check passed

  • API Design Principles

    jh941213/my-cc-harness

    REST 및 GraphQL API 설계 원칙 가이드. An agent skill from jh941213/my-cc-harness.

    125 GitHub starsUsed in 18 repos~3.4k tokens
    Backend & APIsAuto-check passed

  • API And Interface Design

    dzhalaevd/Donatello

    Guides stable API and interface design. An agent skill from dzhalaevd/Donatello.

    135 GitHub starsUsed in 8 repos~2.6k tokens
    Backend & APIsAuto-check passed

More from fl-sean03/OpenSDL

All 11 skills in this repo

  • Author Skill

    fl-sean03/OpenSDL

    Create, revise, split, or remove an OpenSDL repository skill.

    107 GitHub stars~440 tokensUpdated 5 days ago
    Auto-check passed

  • Create Lab

    fl-sean03/OpenSDL

    Create a simulator-first organization laboratory scaffold with policy and validation.

    107 GitHub stars~441 tokensUpdated 5 days ago
    Auto-check passed

  • Debug Run

    fl-sean03/OpenSDL

    Diagnose a failed OpenSDL run, reproduce it in simulation, and validate the smallest correct fix.

    107 GitHub stars~438 tokensUpdated 5 days ago
    Auto-check passed

  • Develop Workflow

    fl-sean03/OpenSDL

    Design, change, validate, and test an OpenSDL workflow through a simulation manifest.

    107 GitHub stars~462 tokensUpdated 5 days ago
    Auto-check passed

  • Orient Lab

    fl-sean03/OpenSDL

    Inspect the current OpenSDL repository and declared laboratory state.

    107 GitHub stars~534 tokensUpdated 5 days ago
    Auto-check passed

  • Release

    fl-sean03/OpenSDL

    Build and validate OpenSDL release candidates by synchronizing versions and producing every workspace distribution locally.

    107 GitHub stars~580 tokensUpdated 5 days ago
    Auto-check passed

Categories

Questions about Design Lab

What does Design Lab do?

Scope the physical and interface design of a laboratory before configuring it. Design Lab is an agent skill from fl-sean03/OpenSDL. Scope the physical and interface design of a laboratory before configuring it.

When should I use Design Lab?

Design Lab fits situations like: A user asks how to approach a lab buildout; how to break a cell into components; which mechanism; instrument to choose.

How do I install Design Lab in Claude Code?

Run `npx skills add fl-sean03/OpenSDL --skill design-lab -a claude-code`. Or copy the skill folder (.agents/skills/design-lab in fl-sean03/OpenSDL) into .claude/skills/design-lab in your project. Claude Code loads it when a task matches its description.

How do I install Design Lab in Codex?

Run `npx skills add fl-sean03/OpenSDL --skill design-lab -a codex`. Or copy the skill folder (.agents/skills/design-lab in fl-sean03/OpenSDL) into .agents/skills/design-lab in your project. Codex loads it when a task matches its description.

Can I use Design 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 fl-sean03/OpenSDL --skill design-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/design-lab, .gemini/skills/design-lab, .github/skills/design-lab and .opencode/skills/design-lab in your project.

What does Design Lab need to run?

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

Does Design 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 Design 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. Review the folder before installing.

What licence does Design Lab use?

Design Lab 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 Design Lab use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Design Lab?

Skills that share tags, products or a category with Design Lab: Nodejs Backend Patterns (ever-works/ever-works, 162 stars), API Designer (Jeffallan/claude-skills, 12k stars), Pangolin CRUD Endpoints (fosrl/pangolin, 23k stars) and Backend Patterns (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Lab?

fl-sean03 (a GitHub user) maintains it in fl-sean03/OpenSDL, which has 107 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 4, 2026.

Source: fl-sean03/OpenSDL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.