Skip to content
Skills Library
Programming · Analysis

map

/map

Use when the user wants to know which parts of this repository nobody understands well enough to explain, debug or safely change, where comprehension debt from AI-written code is worst, or wants the Understanding Map summary and HTML report.

Licence
MIT
Last repository change
12.11.2026

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
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 12.11.2026, 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 wants to know which parts of this repository nobody understands well enough to explain, debug or safely change, where comprehension debt from AI-written code is worst, or wants the Understanding Map summary and HTML report.

Original author description

Use when the user wants to know which parts of this repository nobody understands well enough to explain, debug or safely change, where comprehension debt from AI-written code is worst, or wants the Understanding Map summary and HTML report.

How it works

  1. Running the engine
  2. Steps
  3. Rules
Original SKILL.md headings · 28 lines, 326 words
SKILL.md preview
---
name: map
description: Use when the user wants to know which parts of this repository nobody understands well enough to explain, debug or safely change, where comprehension debt from AI-written code is worst, or wants the Understanding Map summary and HTML report.
---

# Show the Understanding Map

The map is computed by a deterministic scanner from git history, the plugin's own records and the code structure. It makes no LLM calls, so do not add analysis of your own on top of it.

## Running the engine

Claude Code shows `Base directory for this skill: <path>` when this skill loads. Call that path `<base>` and run every engine command as `node "<base>/../../dist/umap.js" <cmd>` from the user's repository. If no base directory was shown, use `node "${CLAUDE_PLUGIN_ROOT}/dist/umap.js" <cmd>` instead.

## Steps

1. **Check setup.** Run `node "<base>/../../dist/umap.js" status --json`. If `setUp` is `false`, follow the setup skill (`/understanding-map:setup`) first: ask solo or team, optionally critical paths, run setup. Then come back here.

2. **Build the map.** Run `node "<base>/../../dist/umap.js" map`. A first run on a large repository can take a couple of minutes, so give the command a generous timeout (5 minutes).

3. **Show the summary verbatim.** Put the command's output in a code block exactly as printed. Do not reorder, trim or reword it, and do not add scores of your own.

4. **Point to the report.** The output ends with `Report: <path>`. Tell the user they can open that file in a browser for the treemap, the ranked table and the evidence behind each zone. It loads nothing over the network.

5. **Suggest the next step.** `/understanding-map:learn` takes about 5 minutes and starts with the top danger zone. Or `/understanding-map:learn <zone>` for a specific one, and `/understanding-map:who <path>` to see who understands a zone and why.

## Rules

- Every level and state is an **estimate**. Say "estimate", never "score" as a fact.
- Do not comment on individual people, and never mention or guess how much of any person's code agents wrote. Agent-written share is only ever a zone total.
- Unknown zones mean "not enough evidence", not "bad". Do not describe them as dark.
- If the command fails, show its one-line error and stop.

Versions

RepositoryScoreLicence
This page · amit429/understanding-map90MIT
milansolutionsai-ops/claude-code-map-skill100MIT
acaprino/alfio-claude-plugins100MIT
shenxingy/clade100MIT
DaBaoAgent/Auto-Video100MIT
bgmacris/quimera-ai100MIT
fabiozagaria/spring-security-advisor100MIT
htlin222/dotfiles100MIT
roma8ok/getmapstack100MIT

Database snapshot: 13.11.2026 · package version 304609900bc6 (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

  • 10010-context-map
    Studies the parts of the project a change touches and writes down how they work, with the evidence and what is still unclear. It changes no code. Use it first, before planning a change.
  • 100explain-and-check
    Checks the user's explanation of code or a topic against real sources. Use when verifying comprehension after LLM-written code, a merged change, or recent study, or when the user wants to explain something in their own words and find gaps.
  • 100handoff
    Use when the user wants a quick 60-second check that they understand what an AI agent just changed in this repository, after the Understanding Map nudge ("Agents changed ~N lines… run /understanding-map:handoff"), or wants to skip or clear that check.
  • 100learn
    Use when the user wants to understand a part of this repository they did not write or have forgotten (often AI-written code), wants a short guided tour of a zone with a few questions to check their understanding, or wants to move a zone on the Understanding Map from Dark or Fading to understood.
  • 10010-context-map-gated
    GATED 10-context-map — the /00-ship* variant, for use ONLY while a run is active. Invoke the plain /10-context-map when there is no run. Studies the parts of the project a change touches and writes down how they work, with the evidence and what is still unclear. It changes no…
  • 96explain-diff-html
    Use when the user asks for a rich explanation of a code change, diff, branch, or PR. Produces HTML output.

Feedback and reports

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