Files
Skills/pseudo/SKILL.md
T
Brummel ec69e34d1b feat(pseudo): show data-structure layout, not just control flow
Add rule 7: alongside the control flow, sketch the layout of the
data structures the code in focus reads or builds — record
fields, collection nesting, variant cases relevant to the
question — placed beside the code that touches them and reduced
in the same spirit (only the fields on the topic path). When the
data layout is the question, it leads and the flow becomes the
stub. Iron Law, worked example, frontmatter, and README updated
to match.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-04 12:35:57 +02:00

119 lines
5.3 KiB
Markdown

---
name: pseudo
description: Use when the user wants code explained in human-readable, commented pseudocode rather than prose — invoked as `/pseudo` or when the user asks to "explain this in pseudocode". Every reply is pseudocode only; no prose paragraphs, opens with a source-file-and-approximate-line anchor, tags notable steps with reference markers ([1], [A]) the user can point back at, and sketches the layout of the data structures the code touches alongside the control flow. Strips detail irrelevant to the question and omits low-level mechanics (memory management, error plumbing) unless the question is about them. Defaults to the project's main entry point.
---
# pseudo — explain code as commented pseudocode
> **Violating the letter of these rules is violating the spirit.**
## Overview
The user wants to understand how code works without reading the
code. The medium of explanation is **commented pseudocode**
not prose, not the real source. The pseudocode is a teaching
artefact: it shows the shape of the logic at the altitude the
question demands, and nothing more.
This is a conversational behaviour skill. It dispatches no
agents and runs no pipeline. While it is active, every answer
obeys the rules below.
## The Iron Law
```
EVERY ANSWER IS PSEUDOCODE. NO PROSE PARAGRAPHS.
EVERY ANSWER OPENS WITH ITS SOURCE FILE AND APPROXIMATE LINE.
MARK THE NOTABLE POINTS SO THE USER CAN POINT BACK AT THEM.
SHOW ONLY WHAT THE QUESTION IS ABOUT — REDUCE THE REST TO A STUB.
SKETCH THE DATA SHAPES THE CODE TOUCHES, NOT JUST THE CONTROL FLOW.
OMIT LOW-LEVEL MECHANICS UNLESS THE QUESTION IS ABOUT THEM.
NEVER LONGER THAN ONE SCREEN.
```
## Rules
1. **Pseudocode is the whole answer.** No introductory sentence,
no closing summary. If something must be said in words, it is
said as a `# comment` inside the pseudocode block.
2. **Anchor line first.** The block opens with a `# comment`
naming the source file and the approximate line the
explanation starts at — e.g. `# src/server.rs ~line 42`. The
line is a navigation hint, not a promise of exactness; "~"
signals that. If the answer spans several files, each new
file's section opens with its own anchor.
3. **Mark the notable points.** Tag the steps worth discussing
with a reference marker — `[1]`, `[2]` or `[A]`, `[B]` — at
the end of the line, so the user can reply "expand [2]" or
"why [B]?" without quoting code. Mark only meaningful points,
not every line; numbering noise defeats the purpose.
4. **Human-readable, not language-specific.** Use plain
constructs (`if`, `for each`, `call`, `return`) and real
names from the code where they aid recognition. Do not
reproduce the actual source syntax.
5. **Reduce the irrelevant.** Anything not on the path the user
asked about collapses to a one-line stub:
`validate(input) # details elsewhere`. Detail is spent only
on the topic.
6. **Omit mechanics by default.** Memory management, allocation,
error-propagation plumbing, logging, and similar are left
out — *unless* the question is precisely about them, in which
case they become the topic and rule 5 reduces everything else.
7. **Show the data shapes, not just the flow.** The control
flow is only half the picture; sketch the layout of the data
structures the code in focus reads or builds — the record
fields, the collection nesting, the variant cases that matter
to the question. Put the shape near the code that touches it,
in the same reduced spirit: only the fields on the topic path,
the rest stubbed (`… # other fields elsewhere`). When the
data layout *is* the question, it leads the answer and the
control flow becomes the stub.
8. **Default entry point.** When the user names no starting
point, begin at the project's main entry (the `main` function
/ primary CLI or server bootstrap). Otherwise start where
they point.
9. **One screen, hard limit.** No answer exceeds roughly one
screen page. If the explanation does not fit, show the top
level as stubs and offer to expand one stub next — let the
user steer the zoom rather than dumping everything.
## Shape of a good answer
```
# src/server.rs ~line 30 — how a request reaches a handler
Router: # [1] the structure match() reads
routes: list of { path_pattern, handler }
… # fallback handler, middleware chain elsewhere
main():
config = load_config() # details elsewhere
router = build_routes() # fills Router.routes
serve(router):
for each incoming request:
handler = router.match(request.path) # [2] scans routes
response = handler(request) # [3]
send(response)
```
That is a whole answer. It opens with the file-and-line anchor,
sketches the `Router` shape `[1]` right beside the code that
reads it (only the field on the topic path; the rest stubbed),
keeps the request path in focus, stubs the config load, omits
the socket and memory mechanics, marks the discussable steps,
and fits one screen. The user can now say "expand [2]" and the
next answer zooms into route matching — with its own anchor line.
## When to stop
The skill stays active for the conversation. The user leaves it
by asking for normal prose, invoking another skill, or saying so.