tibursocampos/agent-dev-toolkit / core/skills/implementation-survey
implementation-survey
UnverifiedDescribe what changed and how the implementation appears to work. The report opens with the external observable goal. Descriptive skill, not a code-review mode. Use when invoking /implementation-survey.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.6 KB |
| references/comparison.md | markdown | 1.2 KB |
| references/patterns.md | markdown | 1.2 KB |
| references/report-template.md | markdown | 2.9 KB |
| references/search-map.md | markdown | 4.9 KB |
| references/stack-discovery.md | markdown | 2.4 KB |
references/stack-discovery.md
View on GitHub# Stack discovery
Read the Signal table in `core/skills/_shared/agents/ROUTING.md`. Do not edit that file. Walk the rows in the order already published there.
A primary-stack row selects a stack only when its signal is present. The stack ids, in that published order, are `dotnet`, `react-native`, `react`, `angular`, `vue`, `blazor`, `electron`, `javascript`, `java`, `python`, `micropython`, `esp-idf`, `arduino`, and `blip-plugin`.
Exactly one matching primary-stack row selects that stack. Stop the walk there. Then load only that stack's section from `references/search-map.md`.
Two or more matching primary-stack rows are mixed evidence. Ask one question. Do not select a stack.
No matching primary-stack row is absence of evidence. Ask one question. Do not select a stack.
The rows below never select a stack. They are not an extra stack id. `Mixed / unclear` is one of those rows, not a fifteenth stack.
| Published signal | Result |
|------------------|--------|
| `.cs` / `.csproj` / EF | `dotnet` |
| React Native / Expo | `react-native` |
| React / TSX | `react` |
| Angular | `angular` |
| Vue | `vue` |
| Blazor | `blazor` |
| Electron | `electron` |
| Node / plain JS | `javascript` |
| Java / `pom.xml` / Gradle | `java` |
| CPython host applications, tools, or tests (including host code that communicates with firmware) | `python` |
| Declared MicroPython runtime/firmware workflow with runtime, target, or port evidence | `micropython` |
| Native ESP-IDF evidence (`idf_component.yml`, Component Manager lockfile, `idf_component_register`, ESP-IDF CMake structure, `sdkconfig`/`sdkconfig.defaults`, or project `idf.py` scripts) | `esp-idf` |
| Explicit Arduino Core/framework evidence, Arduino metadata, or configured `framework = arduino` | `arduino` |
| `.ino`, `main.py`, or board-family name without framework/runtime/toolchain evidence | Ask one question. Do not infer a stack from the board name. |
| Python or `.py` without runtime/target evidence when APIs or deployment could differ | Ask one question. Do not infer `micropython` from the extension. |
| Mixed / unclear | Ask one question. This row is not a stack. |
| UI shape / audit first | Not a primary stack. Do not select a stack from this row. |
| Blip plugin scaffold | `blip-plugin` |
An ESP32-family name alone does not select `esp-idf`, `arduino`, or `micropython`. CPython host code stays on `python` when that row is the only match, including host code that talks to firmware.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |