Agent skill

Dev

by atopile in atopile/atopile

LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

MITAuto-check passedFrontend & Design

Install Dev

skills CLI
$ npx skills add atopile/atopile --skill dev -a claude-code

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

GitHub CLI
$ gh skill install atopile/atopile dev --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/atopile/atopile.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dev .claude/skills/dev && 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
dev
GitHub stars
4k
Token cost
~1.6k tokens
SKILL.md length
648 words
Files
1
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

  • Works in 2 steps: Zig Changes: Edit files under… → Profiling: If something is slow, use ato…
  • Tasks that involve HTML artifacts
  • SKILL.md covers Quick Start, Relevant Files, Dependants (Call Sites) and How to Work With / Develop /…, plus 1 more section
  • Calls gh

What it does

Dev is an agent skill from atopile/atopile. LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

Its SKILL.md is about 1.6k 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 HTML artifacts. It works with GitHub Actions. The repository describes itself as: Design circuit boards with code! ✨ Get software-like design reuse 🚀, validation, version control and collaboration in hardware; starting with electronics ⚡️. The licence is MIT.

When your agent uses it

  • Tasks that involve HTML artifacts

Example prompts

  • “/dev”

Requirements

  • Python 3

Workflow steps

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

  1. Zig Changes: Edit files under src/faebryk/core/zig/src/ -> Run ato dev compile.
  2. Profiling: If something is slow, use ato dev profile to generate a flamegraph or stats.

What it can do on your machine

Read from SKILL.md and the folder at commit 619eda7. 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

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Dev loads about 1.6k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 648 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~43
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 atopile/atopile at commit 619eda7, republished under its MIT licence (© atopile). 648 words, ~1,559 tokens.

Download SKILL.mdSave it as .claude/skills/dev/SKILL.md (or your agent's skills folder).
name
dev
description
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

Dev Module

This skill is written for LLMs working inside this repo. It focuses on the fastest, most reliable inner loop:

  • rebuild Zig bindings when needed
  • run the repo’s orchestrated test runner (ato dev test --llm, not raw test output)
  • use the generated test reports (artifacts/test-report.json, artifacts/test-report.html, artifacts/test-report.llm.json)
  • discover and use ConfigFlags correctly (and inventory them repo-wide)

Quick Start

bash
source .venv/bin/activate

ato dev compile
ato dev test --llm -k solver
ato dev test --llm --view HEAD --open
ato dev test --reuse --baseline HEAD~1
ato dev flags

Relevant Files

  • CLI commands: src/atopile/cli/dev.py
    • ato dev compile (triggers Zig build via import faebryk.core.zig)
    • ato dev test --llm (runs test/runner/main.py with args; supports baseline/CI report helpers)
  • Zig build-on-import glue: src/faebryk/core/zig/__init__.py (ZIG_NORECOMPILE, ZIG_RELEASEMODE)
  • Config flags utility: src/faebryk/libs/util.py (ConfigFlag, ConfigFlagInt, …)
  • Test runner + reports: test/runner/main.py (artifacts/test-report.json, artifacts/test-report.html, artifacts/test-report.llm.json)
  • CI artifacts definition: .github/workflows/pytest.yml (test-report.json, test-report.html)

Dependants (Call Sites)

  • CI/CD: The dev commands are the primary interface for GitHub Actions workflows.
  • Local Development: Developers use ato dev compile after modifying Zig code.

How to Work With / Develop / Test

Core Commands
  • ato dev compile: compile native extensions (graph/typegraph/sexp bindings).
  • ato dev test --llm: runs the orchestrated test runner (defaults to -p test -p src); supports:
    • -k filter (-- -k ... also works via passthrough args)
    • --baseline comparisons (commit hash or HEAD~N style)
    • --view / --open to fetch and open the test-report.html artifact from GitHub Actions (requires gh CLI)
    • --ci to apply the CI marker expression (not not_in_ci and not regression and not slow)
    • --direct -k <testname> to run a single test via test/runtest.py (tight single-test loops)
Test Reports (JSON as source of truth)

Local test runs write:

  • artifacts/test-report.json (single source of truth; outcomes/durations/memory/baseline compare status + stdout/stderr/logs/tracebacks; see tests[].output_full)
  • artifacts/test-report.html (human dashboard; derived from JSON; controlled by FBRK_TEST_GENERATE_HTML=1)
  • artifacts/test-report.llm.json (LLM-friendly; derived from JSON; ANSI stripped logs)

CI uploads both artifacts (see .github/workflows/pytest.yml):

  • test-report.json
  • test-report.html

Notes for LLM debugging:

  • Prefer artifacts/test-report.json or artifacts/test-report.llm.json over raw output; they include structured failures, logs, baseline compare, and collection errors.
  • The HTML is best for quickly scanning long-running tests, worker crashes, and per-test output.

Remote/baseline behavior:

  • ato dev test --llm --baseline <commit> uses the CI test-report.json artifact as the baseline (requires gh CLI).
  • ato dev test --llm --view <commit> --open currently fetches/opens only the HTML artifact; for JSON, download the test-report.json artifact via gh run download.
  • ato dev test --reuse --baseline <commit> rebuilds JSON/HTML/LLM against a baseline without rerunning tests.
  • ato dev test --keep-open keeps the live report server running after tests finish.

Useful test-runner environment variables (see test/runner/main.py):

  • FBRK_TEST_REPORT_INTERVAL (seconds; report refresh cadence)
  • FBRK_TEST_LONG_THRESHOLD (seconds; “long test” threshold)
  • FBRK_TEST_WORKERS (0 = cpu count, negative scales workers)
  • FBRK_TEST_GENERATE_HTML (1/0)
  • FBRK_TEST_PERIODIC_HTML (1/0)
  • FBRK_TEST_OUTPUT_MAX_BYTES (truncate preview output used by HTML; tests[].output_full remains complete)
  • FBRK_TEST_OUTPUT_TRUNCATE_MODE (head or tail)
  • FBRK_TEST_BIND_HOST (orchestrator bind host; default 0.0.0.0)
  • FBRK_TEST_REPORT_HOST (host used in printed report URL; default bind host)
  • FBRK_TEST_PERF_THRESHOLD_PERCENT (default 0.30)
  • FBRK_TEST_PERF_MIN_TIME_DIFF_S (default 1.0)
  • FBRK_TEST_PERF_MIN_MEMORY_DIFF_MB (default 50.0)
Show full SKILL.md (205 more words)Show less

LLM quick usage:

  • artifacts/test-report.llm.json is always generated (ANSI stripped, full tests + logs).
  • ato dev test --llm prints a concise summary + schema + jq hints (stdout only).
  • jq recipes are embedded in the report under llm.jq_recipes.
  • Auto-LLM: ato dev test enables the summary automatically when running under claude-code/codex-cli/cursor.
  • Force on/off via FBRK_TEST_LLM=1 or FBRK_TEST_LLM=0.
ConfigFlags (how to use + how to inventory)

ConfigFlag is the repo’s “toggle-by-env-var” mechanism. The environment variable name is the first argument to ConfigFlag(...).

Usage:

bash
export SOME_FLAG=1

Inventory all ConfigFlags in-tree (preferred over trying to maintain a manual list):

bash
ato dev flags

Prefer using ato dev flags when you want the full picture (types/defaults/descriptions + callsite counts) in one place.

High-leverage flags you’ll use often:

  • Zig build: ZIG_NORECOMPILE, ZIG_RELEASEMODE
  • Solver debug: SLOG, SVERBOSE_TABLE, SPRINT_START, SMAX_ITERATIONS, SSHOW_SS_IS
  • Logs: COLOR_LOGS, LOG_TIME, LOG_FILEINFO
Development Workflow
  1. Zig Changes: Edit files under src/faebryk/core/zig/src/ -> Run ato dev compile.
  2. Profiling: If something is slow, use ato dev profile <command> to generate a flamegraph or stats.
Testing
  • Main test entrypoint: ato dev test --llm.
  • If you change CLI behavior, add/adjust tests under test/ that exercise the command surface.

Best Practices

  • Use ConfigFlags: For experimental features or verbose debugging, use a ConfigFlag instead of commenting out code.
  • Compile often: Zig errors won’t be caught by Python tooling.

© atopile, MIT. 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 .claude/skills/dev of atopile/atopile.

Open the folder on GitHubat commit 619eda7

Compare with similar skills

Dev 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.

Dev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dev this skillatopile/atopile4k—~1.6kAutomated safety check: PassMIT
Kb GitHub Workflow StandardsCommunity-Access/accessibility-agents422—~4.5kAutomated safety check: PassMIT
LobeHub Interactive Prototypelobehub/lobehub83k—~1.6kAutomated safety check: PassCustom licence
Paperclip Pagepaperclipai/paperclip99k—~1kAutomated safety check: PassMIT
Openkb Deck NeonVectifyAI/OpenKB4.7k1 repos~4.3kAutomated safety check: PassApache-2.0
Webhome Homepage Builderwebhtv/webhtv1.7k—~3.8kAutomated safety check: PassGPL-3.0

Similar skills

  • Kb GitHub Workflow Standards

    Community-Access/accessibility-agents

    Reference data, not a reviewer. An agent skill from Community-Access/accessibility-agents.

    422 GitHub stars~4.5k tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed
  • Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Paperclip Page

    paperclipai/paperclip

    Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host.

    99k GitHub stars~1k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Openkb Deck Neon

    VectifyAI/OpenKB

    A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…

    4.7k GitHub starsUsed in 1 repo~4.3k tokens
    Frontend & DesignAuto-check passed
  • Build, review, debug, reverse-engineer data sources for, and package FongMi/WebHome custom homepage single-file HTML.

    1.7k GitHub stars~3.8k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Solo Artifacts

    solo-agent/solo

    A skill your agent uses when a Solo task or thread should become an interactive, reviewable, self-contained HTML artifact for progress/status, review/decision, or comparison/leaderboard work inside…

    697 GitHub stars~961 tokensUpdated 25 days ago
    Frontend & DesignAuto-check passed

More from atopile/atopile

All 19 skills in this repo
  • Ato Language

    atopile/atopile

    Reference for the .ato declarative DSL: type system, connection semantics, constraint model, and standard library.

    4k GitHub stars~3.5k tokensUpdated 3 mo ago
    Auto-check passed
  • Compiler

    atopile/atopile

    How the atopile compiler builds and links TypeGraphs from .ato (ANTLR front-end → AST → TypeGraph → Linker → DeferredExecutor), plus the key invariants and test entrypoints.

    4k GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed
  • Domain Layer

    atopile/atopile

    Instructions for electronics-specific logic and build processes: netlists, PCBs, build steps, and exporters.

    4k GitHub stars~791 tokensUpdated 3 mo ago
    Auto-check passed
  • Fabll

    atopile/atopile

    How FabLL (faebryk.core.node) maps Python node/trait declarations into the TypeGraph + instance graph, including field/trait invariants and instantiation patterns.

    4k GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Faebryk

    atopile/atopile

    How Faebryk's TypeGraph works (GraphView + Zig edges), how to traverse/resolve references, and how FabLL types/traits map onto edge types.

    4k GitHub stars~861 tokensUpdated 3 mo ago
    Auto-check passed
  • Graph

    atopile/atopile

    How the Zig-backed instance graph works (GraphView/NodeReference/EdgeReference), the real Python API surface, and the invariants around allocation, attributes, and cleanup.

    4k GitHub stars~952 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Dev

What does Dev do?

LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags. Dev is an agent skill from atopile/atopile.json/html artifacts, and discover/debug ConfigFlags.

When should I use Dev?

Dev fits situations like: tasks that involve HTML artifacts.

How do I install Dev in Claude Code?

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

How do I install Dev in Codex?

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

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

What does Dev need to run?

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

Does Dev access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Dev 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 Dev use?

Dev is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dev use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Dev?

Skills that share tags, products or a category with Dev: Kb GitHub Workflow Standards (Community-Access/accessibility-agents, 422 stars), LobeHub Interactive Prototype (lobehub/lobehub, 83k stars), Paperclip Page (paperclipai/paperclip, 99k stars) and Openkb Deck Neon (VectifyAI/OpenKB, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dev?

atopile (a GitHub organization) maintains it in atopile/atopile, which has 3,976 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on June 13, 2026.

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