Agent skill

Embedded Firmware From Hardware

by Tansuo2021 in Tansuo2021/ADtoKeil

Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence.

GPL-3.0Auto-check passedDevelopment

Install Embedded Firmware From Hardware

skills CLI
$ npx skills add Tansuo2021/ADtoKeil --skill embedded-firmware-from-hardware -a claude-code

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

GitHub CLI
$ gh skill install Tansuo2021/ADtoKeil embedded-firmware-from-hardware --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/Tansuo2021/ADtoKeil.git skills-src && mkdir -p .claude/skills && cp -r skills-src/embedded-firmware-from-hardware .claude/skills/embedded-firmware-from-hardware && 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
embedded-firmware-from-hardware
GitHub stars
188
Token cost
~1.5k tokens
SKILL.md length
704 words
Files
9 (incl. scripts, references)
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence.

  • Works in 6 steps: Extract hardware evidence → Choose firmware ownership → Bring up in layers → …
  • Codex must convert hardware design knowledge into firmware architecture
  • SKILL.md covers Core Rule, Workflow, Implementation Standards and Debugging Heuristics, plus 1 more section
  • Runs Python scripts from its folder

What it does

Embedded Firmware From Hardware is an agent skill from Tansuo2021/ADtoKeil. Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence. Use when Codex must convert hardware design knowledge into firmware architecture, BSP/HAL code, pin configuration, peripheral drivers, board diagnostics, touch-key/keypad/display/buzzer/WiFi bring-up, or investigate why firmware does not match schematic/PCB behavior.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/architecture.md` and `references/hardware-to-firmware-checklist.md`).

It sits in Development. The licence is GPL-3.0.

When your agent uses it

  • Codex must convert hardware design knowledge into firmware architecture
  • Pin configuration
  • Peripheral drivers
  • Board diagnostics

Example prompts

  • “/embedded-firmware-from-hardware”

Requirements

  • Python 3

Workflow steps

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

  1. Extract hardware evidence
  2. Choose firmware ownership
  3. Bring up in layers
  4. Use board diagnostics
  5. Compare against known-good evidence
  6. Create the buildable project when requested

What it can do on your machine

Read from SKILL.md and the folder at commit 56ab07d. 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/ (Python), which the agent can run.

    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

Embedded Firmware From Hardware loads about 1.5k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 704 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7k

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 Tansuo2021/ADtoKeil at commit 56ab07d, republished under its GPL-3.0 licence (© Tansuo2021). 704 words, ~1,484 tokens.

Download SKILL.mdSave it as .claude/skills/embedded-firmware-from-hardware/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
embedded-firmware-from-hardware
description
Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence. Use when Codex must convert hardware design knowledge into firmware architecture, BSP/HAL code, pin configuration, peripheral drivers, board diagnostics, touch-key/keypad/display/buzzer/WiFi bring-up, or investigate why firmware does not match schematic/PCB behavior.

Embedded Firmware From Hardware

Core Rule

Treat the schematic/PCB as the source of truth for pins and nets, and treat vendor libraries as state machines with required setup, service, restart, and IO-bias contracts. Do not replace a vendor peripheral flow with intuition such as "this should be high impedance" unless the working reference, datasheet, or measured behavior supports it.

Workflow

  1. Extract hardware evidence

    • Build a pin map: MCU pin, alternate function, schematic net, series parts, destination component, PCB pad, and uncertainty.
    • Trace each user-visible function end-to-end: input electrode/switch -> resistor/filter -> MCU pin -> firmware symbol -> behavior.
    • Mark polarity, pull state, power domain, level shifting, reset/default state, and "needs measurement" items.
    • For MCU datasheets, app notes, and vendor PDFs, extract text first; if text is sparse or screenshots contain instructions, render pages as images and read the visual content before deciding the implementation. Prefer scripts/pdf_evidence.py for repeatable extraction/rendering. For Chinese filenames on Windows, enumerate PDFs with Python Path.glob() or use a Python launcher/environment that preserves Unicode paths.
  2. Choose firmware ownership

    • Put product logic in App/.
    • Put board pins and MCU registers in BSP/.
    • Put external chips/protocols in Drivers/.
    • Keep vendor libraries under a clear folder inside the target firmware project, such as Firmware/TKDriver/, and wrap them with a BSP adapter. Do not leave a Keil project depending on a sibling ../TKDriver path when the vendor manual says to copy/export the driver into the target project.
    • Keep Config/board_config.h as the board contract: clocks, pin/channel mappings, timings, display mapping, diagnostic flags.
  3. Bring up in layers

    • First verify clock, power-safe GPIO defaults, and unused-pin handling.
    • Then bring up one visible output path such as display or buzzer.
    • Then bring up one input path with an on-board diagnostic display before integrating product behavior.
    • Only after each layer is observable should App/ depend on it.
  4. Use board diagnostics

    • Prefer diagnostics that work without a debugger: display status codes, beep patterns, LED patterns, or UART logs.
    • Distinguish "interrupt not firing", "scan not completing", "raw event present", and "mapped application event present".
    • Never diagnose "no input response" only from product behavior; add counters/status at the BSP boundary.
  5. Compare against known-good evidence

    • When a known-good firmware exists, diff BSP pin setup, vendor library call order, restart/service calls, thresholds, project options, startup files, and linker output.
    • Favor the smallest transferable differences rather than wholesale copying generated output.
  6. Create the buildable project when requested

    • If the user asks for embedded software development and a Keil/C51 toolchain is present, create or update a real .uvproj/.uvprojx project unless the user explicitly says not to.
    • Put vendor groups such as TKDriver visibly in the project tree, include headers/config files for review, include all required .C and .LIB files for build, then run UV4 build/rebuild to prove the HEX path.
Show full SKILL.md (245 more words)Show less

Implementation Standards

Use references/architecture.md when designing or refactoring firmware structure.

Use references/hardware-to-firmware-checklist.md when converting a schematic/PCB report into code tasks.

Use references/pdf-datasheet-workflow.md when a PDF datasheet or app note must be read with both text extraction and rendered page evidence.

Use references/vendor-touch-libraries.md when working with capacitive touch, spring touch keys, TK libraries, or scan/restart/threshold problems.

Use references/sinone-sc95f861xb.md when working with SinOne/SOC SC95F861xB 8051 MCUs, especially GPIO, TK, UART0, USCI SPI/TWI/UART, clock options, interrupts, and Keil C51 register setup.

Use references/keil-c51-project-review.md when a Keil C51/8051 project builds but hardware behavior is wrong, or when comparing a current project against a known-good Keil project.

Debugging Heuristics

  • If a visible app keeps running but input has no effect, confirm the BSP input event before touching app logic.
  • If a capacitive touch channel never fires, inspect IO mode, pull/bias state, selected channel mask, threshold bytes, interrupt enable, status bit handling, and required restart call.
  • If changing thresholds does nothing, assume the scan flow or IO-bias contract may be wrong.
  • If a diagnostic build still shows old product behavior, suspect the wrong HEX was flashed or the flash operation did not take.
  • If a register comment says "input" but known-good code sets output/pull bits, trust measured/known-good behavior until the datasheet register semantics are confirmed.

Deliverables

When using this skill, finish with:

  • The hardware evidence used.
  • The firmware files changed or proposed.
  • The reason each pin/register/library call is needed.
  • Build result and artifact path.
  • A board-test procedure with observable expected results.

© Tansuo2021, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts, references) in embedded-firmware-from-hardware of Tansuo2021/ADtoKeil.

  • SKILL.md
  • agents/openai.yaml
  • references/architecture.md
  • references/hardware-to-firmware-checklist.md
  • references/keil-c51-project-review.md
  • references/pdf-datasheet-workflow.md
  • references/sinone-sc95f861xb.md
  • references/vendor-touch-libraries.md
  • scripts/pdf_evidence.py

Open the folder on GitHubat commit 56ab07d

Compare with similar skills

Embedded Firmware From Hardware 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.

Embedded Firmware From Hardware compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Embedded Firmware From Hardware this skillTansuo2021/ADtoKeil188—~1.5kAutomated safety check: PassGPL-3.0
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from Tansuo2021/ADtoKeil

  • Altium Circuit Investigator

    Tansuo2021/ADtoKeil

    Evidence-led analysis of Altium schematic and PCB designs using netlist tracing, full symbol-pin coverage, connector and PCB pad inventories, local schematic screenshots/SVG labels, component…

    188 GitHub stars~2.1k tokensUpdated 4 mo ago
    Auto-check passed
  • Altium Schematic Reader

    Tansuo2021/ADtoKeil

    Read and reason about Altium Designer projects and schematics using structured data from .PrjPcb and .SchDoc files.

    188 GitHub stars~1.4k tokensUpdated 4 mo ago
    Auto-check passed
  • Keil

    Tansuo2021/ADtoKeil

    Keil MDK/uVision build skill for embedded projects. An agent skill from Tansuo2021/ADtoKeil.

    188 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Serial

    Tansuo2021/ADtoKeil

    Embedded serial-port debugging skill. An agent skill from Tansuo2021/ADtoKeil.

    188 GitHub stars~754 tokensUpdated 4 mo ago
    Auto-check passed
  • Workflow

    Tansuo2021/ADtoKeil

    Thin orchestration layer for embeddedskills. An agent skill from Tansuo2021/ADtoKeil.

    188 GitHub stars~625 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Embedded Firmware From Hardware

What does Embedded Firmware From Hardware do?

Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence. Embedded Firmware From Hardware is an agent skill from Tansuo2021/ADtoKeil. Build and review maintainable embedded MCU firmware from schematic, PCB, netlist, pin-map, BOM, Keil/C51/MDK projects, vendor demo code, or hardware debug evidence.

When should I use Embedded Firmware From Hardware?

Embedded Firmware From Hardware fits situations like: Codex must convert hardware design knowledge into firmware architecture; pin configuration; peripheral drivers; board diagnostics.

How do I install Embedded Firmware From Hardware in Claude Code?

Run `npx skills add Tansuo2021/ADtoKeil --skill embedded-firmware-from-hardware -a claude-code`. Or copy the skill folder (embedded-firmware-from-hardware in Tansuo2021/ADtoKeil) into .claude/skills/embedded-firmware-from-hardware in your project. Claude Code loads it when a task matches its description.

How do I install Embedded Firmware From Hardware in Codex?

Run `npx skills add Tansuo2021/ADtoKeil --skill embedded-firmware-from-hardware -a codex`. Or copy the skill folder (embedded-firmware-from-hardware in Tansuo2021/ADtoKeil) into .agents/skills/embedded-firmware-from-hardware in your project. Codex loads it when a task matches its description.

Can I use Embedded Firmware From Hardware 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 Tansuo2021/ADtoKeil --skill embedded-firmware-from-hardware -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/embedded-firmware-from-hardware, .gemini/skills/embedded-firmware-from-hardware, .github/skills/embedded-firmware-from-hardware and .opencode/skills/embedded-firmware-from-hardware in your project.

What does Embedded Firmware From Hardware need to run?

Going by SKILL.md and its folder, Embedded Firmware From Hardware needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Embedded Firmware From Hardware 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 Embedded Firmware From Hardware 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 Embedded Firmware From Hardware use?

Embedded Firmware From Hardware is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Embedded Firmware From Hardware use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.6k tokens, read only when the agent opens those files.

What are the alternatives to Embedded Firmware From Hardware?

Skills that share tags, products or a category with Embedded Firmware From Hardware: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Embedded Firmware From Hardware?

Tansuo2021 (a GitHub user) maintains it in Tansuo2021/ADtoKeil, which has 188 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 7, 2026.

Source: Tansuo2021/ADtoKeil on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.