Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Esp Idf Developer

ASecurity

Implement or diagnose native ESP-IDF C/C++ firmware using the project's declared target, ESP-IDF version, CMake configuration, idf.py workflow, and Component Manager metadata.

6 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentspythonc++shellrailscode-reviewapisecurity

Works with

api

Security Analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add tibursocampos/agent-dev-toolkit --skill esp-idf-developer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Esp Idf Developer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Esp Idf Developer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-esp-idf-developer/badge)](https://www.skillsdirectory.com/skills/tibursocampos-esp-idf-developer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: esp-idf-developer
description: >-
  Implement or diagnose native ESP-IDF C/C++ firmware using the project's declared
  target, ESP-IDF version, CMake configuration, idf.py workflow, and Component Manager metadata.
---

## STOP - Read before ANY tool call

1. Read `{{GUARDRAILS_PATH}}`
2. Read `_shared/sdd-artifacts/SESSION.md`; load session-state for `$Cwd`
3. If the relevant gate is not approved: **STOP** - ask user **(pt-BR)** - do **NOT** Write/Shell
4. SDD/develop skills: after **ONE** step/task, **STOP** session - handoff only
5. This skill body is **English**; user-facing prompts may be **(pt-BR)**

---

# Skill: esp-idf-developer

## Trigger

Invoke for native ESP-IDF applications and components written in C or C++ when project evidence identifies ESP-IDF. A board name such as ESP32, ESP32-S3, or ESP32-C3 is not framework evidence by itself.

## Outcome

Provide configuration-aware implementation or diagnosis for the project's ESP-IDF target and version. Preserve the project's CMake and `idf.py` workflow, Component Manager resolution, and configuration files. Report unknown target or version context explicitly and keep compile-only evidence separate from device evidence.

## Lazy-load

| When | Path |
|------|------|
| Target, version, and framework evidence | `references/context-and-configuration.md` |
| CMake, `idf.py`, and Component Manager workflow | `references/build-and-dependencies.md` |
| Validation boundaries and safe reporting | `references/validation-and-safety.md` |
| Forbidden assumptions and framework boundaries | `references/must-not.md` |
| Shared embedded WHAT layer | `{{TOOLKIT_ROOT}}/skills/_shared/embedded-guidelines/README.md`, `target-and-provenance.md`, `security-and-dependencies.md`, `validation-and-reporting.md` |

Do not preload unrelated framework packs or the whole shared memory bank. Load only the reference needed for the current claim.

**Never by default:** Do not preload unrelated framework packs, prescribe a universal ESP-IDF version or toolchain, or claim device/runtime evidence from a host-only or compile-only result.

## Process

### 0. Establish project evidence

Before recommending an API, command, target-specific option, or security feature, inspect the project and record the evidence state for:

- target SoC, board/module, variant, and revision;
- ESP-IDF version and provenance;
- CMake project structure and authoritative build entry point;
- `idf.py` availability and the observed installation/environment;
- `idf_component.yml`, Component Manager lockfile, and dependency sources;
- `sdkconfig.defaults`, generated local configuration, and any project-specific overrides;
- validation boundary: host-only, compile-only, device runtime, or HIL.

If target or version evidence is missing, ask for it or state the uncertainty before using version-sensitive guidance. Never infer ESP-IDF from an ESP32 family name alone.

### 1. Preserve the native workflow

Treat the project's CMake files and `idf.py` commands as the build source of truth. Inspect existing components and registration before changing them. Use Component Manager metadata and its resolved lockfile as dependency evidence; do not silently replace resolved versions or introduce a new package manager.

Distinguish versioned defaults such as `sdkconfig.defaults` from generated or local `sdkconfig` state. Compare configuration before changing it and preserve local state unless the operator explicitly requests a reviewed change.

### 2. Condition host setup on observation

Give PowerShell, ESP-IDF environment, and managed Python instructions only when the project or host inspection shows that installation and shell are applicable. Preserve the observed ESP-IDF installation and Python environment rather than prescribing a universal path, version, or activation command. A version mentioned by a preview project is project-specific evidence, never a global default for this skill or toolkit.

### 3. Implement and report narrowly

Use the project's C/C++ layout and existing component boundaries. Label results separately as host-only, compile-only, device runtime, or HIL, and include the target, version, configuration, and observed command or scenario. A successful cross-build does not prove flashing, boot, peripheral behavior, timing, memory headroom, or HIL behavior.

For flash, erase, OTA, boot, secure-boot, encryption, signing, rollback, or provisioning guidance, require the target, version, bootloader/configuration, and recovery context first. Keep credentials, tokens, private keys, and device secrets out of source, configuration, logs, and evidence.

Before any flash, erase, or OTA operation, run the preflight in `references/validation-and-safety.md`: exact target, verified port or OTA channel, partition table, approved backup, and recovery evidence are all required. If one is missing, stop operation-specific guidance. Treat secure boot, flash encryption, signing, rollback, OTA, eFuse, and provisioning as separate decisions qualified by the actual SoC/version/configuration and threat/recovery context.

## Handoff

For a larger approved change, use `sdd-develop` with the canonical PLAN path. For a commit, use `commit`; for review, use `code-review`.

Attribution

tibursocampostibursocampos
View sourceSee grades on GitHubMore from tibursocampos →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →