Whats going on

Skill ChristopherAlphonse/calphonse-skills/whats-going-on

One-pass codebase intelligence sweep. Use when onboarding to a repo or asking "what's going on here?" Produces a concise map of core use cases, lifecycle, architecture, and where to start reading.From its SKILL.md

Install

npx -y skills add ChristopherAlphonse/calphonse-skills --skill whats-going-on

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, 471 tokens by cl100k_base, as published. Nobody here has run it

What's Going On

Create a concise onboarding map in one pass. Default to reading files yourself; use sub-agents only if the repo is large enough that parallel exploration clearly saves time.

Guardrails

Do not modify source code.
Prefer evidence over guesses. Cite files for important claims or label assumptions.
Focus on core use cases, lifecycle, architecture, and navigation. Skip roadmap, refactor advice, and peripheral features.
Read the smallest set of files that explains the system: README, package/build config, routes/entrypoints, tests, core modules, .planning/* if present.

One-Pass Workflow

Orient: Identify repo type, run/build/test commands, main entrypoints, and existing docs.
Trace core flows: Find 3-5 primary user or system flows from entrypoint to response, job completion, persistence, or external call.
Map architecture: Identify 5-10 major components only. Exclude thin wrappers, utilities, and config-only files.
Synthesize directly: Write one artifact to .planning/system/whats-going-on.md.

Create .planning/system/ if needed.

Output Shape

# What's Going On - <repo name>

## Core Use Cases
- <use case>: <what it does>
  Evidence: <key files>

## Lifecycle
- <flow>: <entry> -> <validation/business logic> -> <persistence/external call> -> <result>

## Architecture
| Component | Responsibility | Key Files |
| --- | --- | --- |

## New Engineer Navigation
- Start here: <file/doc>
- Core logic: <files>
- Data enters/exits: <files/routes/jobs>
- Integrations: <services/protocols>
- Run first: <command>

## Assumptions And Unknowns
- <only if needed>

Optional Sidecar Files

Only write these when the repo is complex enough that separate docs will stay useful:

.planning/system/use_cases.md
.planning/system/lifecycle.md
.planning/system/architecture.md

Install: npx skills add ChristopherAlphonse/calphonse-skills --skill whats-going-on

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most architecture codebase skills give in 471 tokens

Counted across 811 of the 1,134 authors here whose files we hold, read 2026-08-07

Ask the user which candidate to explorein 45 of 811, across 15 files
Apply the deletion test to suspected shallow modulesin 43 of 811, across 15 files
Read any relevant architecture decision records firstin 31 of 811, across 8 files
Use exact glossary terms in every suggestionin 30 of 811, across 10 files
Accept dependencies instead of creating themin 24 of 811, across 5 files
Include before and after visualisations for each candidatein 24 of 811, across 5 files
Read the domain glossary before exploringin 24 of 811, across 6 files
Return results instead of producing side effectsin 23 of 811, across 4 files
Explore the codebase for shallow modules and frictionin 23 of 811, across 3 files
Introduce seams only where things varyin 22 of 811, across 3 files
Reduce the number of methodsin 21 of 811, across 2 files
Design deep modules with small interfacesin 21 of 811, across 3 files

Said here and by no other author read

Do not modify source code
Cite files for important claims or label assumptions
Focus on core use cases, lifecycle, architecture, and navigation
Skip roadmap, refactor advice, and peripheral features
Read the smallest set of files that explains the system
Identify repository type, commands, entrypoints, and docs

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.