Skip to content
Skills Library
Programming · Learning & explanation

dataflow

/dataflow

Use when the user is exploring an unfamiliar codebase and asks about its types (what a type allows, what a signature promises, where outside data becomes a typed value) or its data flow (where a value comes from, where it goes, which code owns it). Also use to go deeper after a how or why answer. Explore together with the user, one step at a time.

Author
caasi ↗
Repository
dong3 ↗
Licence
MIT
Last repository change
19.10.2026

Assessment and security

86/ 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.
Content21 / 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
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 19.10.2026, 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

Use when the user is exploring an unfamiliar codebase and asks about its types (what a type allows, what a signature promises, where outside data becomes a typed value) or its data flow (where a value comes from, where it goes, which code owns it). Also use to go deeper after a how or why answer. Explore together with the user, one step at a time.

Original author description

Use when the user is exploring an unfamiliar codebase and asks about its types (what a type allows, what a signature promises, where outside data becomes a typed value) or its data flow (where a value comes from, where it goes, which code owns it). Also use to go deeper after a how or why answer. Explore together with the user, one step at a time.

How it works

SKILL.md has no level-two headings · 17 lines, 210 words

SKILL.md preview
---
name: dataflow
description: Use when the user is exploring an unfamiliar codebase and asks about its types (what a type allows, what a signature promises, where outside data becomes a typed value) or its data flow (where a value comes from, where it goes, which code owns it). Also use to go deeper after a how or why answer. Explore together with the user, one step at a time.
when_to_use: Questions such as "how does this type stop me from passing X", "what does this type allow", "what does this signature promise", "where does this value come from", "where does this value go", "how does X become Y on the screen". Also when the user writes /types or /dataflow anywhere in a message.
---

# Types and dataflow

Explore with the user. They read the code in their editor; you answer the one question they just asked, then stop so that they choose the next step. If the conversation already has a how or why answer, start from what it found.

Follow one value: where it is created, changed, read, and which code owns it.

If the code has a type system, read the types along that path too: what each type allows and forbids, what each signature promises, and where outside data becomes a typed value. When the question is about types, start there.

Then:

- Give one short answer, not a report: at most five findings.
- Mark each finding [read] (`file:line`) or [spike] (command and output). Before you answer, run at least one spike on the most important finding about behavior. If no finding can be tested without an install or a build, say so. A spike calls the code from outside, on a copy. Ask once before you install or build in the copy.
- End with:
  - **Read next:** two or three `vim +<line> <path>` lines, each with one reason. Give paths relative to the repository root.
  - **Spike next:** one or two facts that you will check next.
Files in this package (2)
  • README.md 4 KB
  • SKILL.md 2 KB

Versions

The database has no other skills named dataflow.

Database snapshot: 13.11.2026 · package version 1d829eee4602 (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

  • 100grok-repo
    Explain an unfamiliar codebase through a repository briefing, dataflow trace, or reconstruction of why and how a change was made. Use when asked for a repo tour, design tradeoffs, how something works, where a value comes from, or why a feature changed. Not for repo health (use repo-eval).
  • 100explain-code-slice
    Use this skill when the user wants a code path, flow, pipeline, request lifecycle, trace, walkthrough, or part of a system explained step by step from start to finish. Explain where data comes from, what shape it has, who sends it, why it enters the flow, what calls what next,…
  • 100show-me
    Explain code structure, dataflow, or proposed changes with a compact tree, pseudocode, type signature, diff, or diagram. Use when a visual clarifies those relationships; whole-repo briefings belong to grok-repo.
  • 100warpp-workflow-authoring
    Author WARPP workflows for Manifold as typed-port dataflow JSON. Use when a user asks to build, create, design, generate, or edit a Flow / workflow / automation / pipeline / DAG in Manifold, or mentions WARPP, workflow nodes, or the /flow builder. Covers the document format,…
  • 90First 10 Moves
    Read and explore unfamiliar code before asking questions. Use when new to a repo, orienting in an unfamiliar codebase, or finding where to start.
  • 95intent-layer-onboarding
    Get oriented in an unfamiliar codebase using its Intent Layer. Use when joining a new project, exploring a codebase for the first time, or helping someone understand "where do I start?" questions.

Feedback and reports

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