Skip to content
Skills Library
Programming · Learning & explanation

qstack-how

/qstack-how

Explain how a subsystem works by tracing its real runtime flow, ownership, boundaries, and files. Use for code walkthroughs, onboarding explanations, placement or layering questions, and explicitly requested architecture critique.

Repository
qstack ↗
Licence
MIT
Last repository change
18.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 18.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Explain how a subsystem works by tracing its real runtime flow, ownership, boundaries, and files. Use for code walkthroughs, onboarding explanations, placement or layering questions, and explicitly requested architecture critique.

Original author description

Explain how a subsystem works by tracing its real runtime flow, ownership, boundaries, and files. Use for code walkthroughs, onboarding explanations, placement or layering questions, and explicitly requested architecture critique.

How it works

  1. Choose the mode
  2. Investigate
  3. Present
Original SKILL.md headings · 49 lines, 277 words
SKILL.md preview
---
name: qstack-how
description: >
  Explain how a subsystem works by tracing its real runtime flow, ownership,
  boundaries, and files. Use for code walkthroughs, onboarding explanations,
  placement or layering questions, and explicitly requested architecture critique.
license: MIT
---

# QStack how

Build a working mental model from the code. This skill is read-only. It does
not edit files, fix critique findings, commit, push, publish, deploy, or message
anyone.

## Choose the mode

- **Explain** is the default. Answer how the system works and where behavior
  lives.
- **Critique** runs only when the user asks for architectural problems or
  improvements. Explain the system first, then critique it.

This skill explains mechanism, placement, and ownership. Label inferred
motivation as inference instead of presenting it as historical fact.

## Investigate

1. Resolve the subject and scope. For harmless ambiguity, state a reasonable
   interpretation and proceed. Ask only when different interpretations would
   materially change the answer.
2. Search for the entry point and read the implementation. Trace callers,
   callees, state changes, data transformations, types, and boundaries until
   the path from trigger to effect has no hand-waved step.
3. Check repository instructions, configuration, generated code, tests, and
   external boundaries that change the flow. Do not infer behavior from names.
4. Record exact paths, symbols, and lines. State any path that could not be
   traced.

Handle a narrow question directly. For a cross-cutting subsystem, read
[complex exploration](references/exploration.md). When the answer needs a full
onboarding narrative, read [structured explanation](references/explanation.md).

## Present

Lead with the direct answer. Then include only the concepts, flow, file map, and
gotchas needed to make it understandable. Use a diagram when it materially
clarifies several components or state transitions.

For Critique mode, read [architecture critique](references/critique.md) only
after the explanation is grounded in the code. Report findings and tradeoffs;
do not apply fixes.

Adapted from Lauren Tan's PStack
[`how`](https://github.com/cursor/plugins/blob/60c641e4fad674784b30abcf9f8915dea39df38d/pstack/skills/how/SKILL.md)
at commit `60c641e4fad674784b30abcf9f8915dea39df38d` under the MIT License.
See [third-party notices](../../THIRD_PARTY_NOTICES.md).
Files in this package (5)
  • SKILL.md 2 KB
  • agents/openai.yaml 1 KB
  • references/critique.md 2 KB
  • references/explanation.md 1 KB
  • references/exploration.md 1 KB

Versions

The database has no other skills named qstack-how.

Database snapshot: 13.11.2026 · package version d285e01d0042 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100how
    Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental…
  • 100how
    Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental…
  • 90how
    Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental…
  • 90how
    Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental…
  • 90how
    Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental…
  • 100how
    Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.