Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills / Engineering / engineering-misc

Custom Distance Metrics

Category: Engineering  ·  Sub-category: engineering-misc  ·  Last updated:
lang:python
Builds two-argument sklearn metric callables and scipy cdist/pdist precomputes (weighted Euclidean/cosine, Numba Manhattan factories) for DBSCAN, HDBSCAN, AgglomerativeClustering, and NearestNeighbors. Needed when Euclidean, cosine, or Jaccard discard sequence, graph, or mixed-type structure. Do not use Lloyd K-Means with a custom metric; do not run a slow Python pairwise on large n without JIT, vectorize, or a precomputed matrix.
Security AStatic scan found no risk patternsHow grading works ›

About this skill (catalog notes)

Custom Distance Metrics includes explicit scope boundaries (an explicit 'when not to use' or 'out of scope' section); a dedicated installation section; pricing or quota commentary. At roughly 3,276 words the SKILL.md is on the longer end of the catalog distribution.

Source
github.com/kazimrmerchant/skill-slice/blob/main/docs/WORKS_V…
License
MIT
Original author
kazimrmerchant
Indexed lastmod
Catalog position
Engineering · engineering-misc
Indexed related skills
10

How Custom Distance Metrics fits the catalog

Custom Distance Metrics sits in the Engineering category under the engineering-misc sub-topic in the ClaudSkills catalog. There are 10 related skills indexed alongside it; comparing a few before installing usually reveals which fits your workflow best.

These notes are auto-generated from features detected in the SKILL.md file and from this catalog's structure — they aren't part of the source repository.

From the source SKILL.md

A custom distance metric lets you define what "similar" and "different" mean for your data instead of accepting the assumptions baked into a generic metric. Distance is the single lever almost every unsupervised and neighbour-based algorithm pulls: clustering, manifold learning, and k-NN all make their decisions only through the distance function. Change the metric and you change the result, without touching the algorithm itself.

What this skill does

Custom Distance Metrics is a community-contributed Claude Code skill in the engineering-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/custom-distance-metrics/ and loads when your prompt matches the skill's trigger.

Who uses this skill

The Custom Distance Metrics Claude Code skill is built for software engineers, backend developers, full-stack teams, and technical leads building and maintaining production systems. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 186,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).

How to install

Free

Manual install (2 steps)

mkdir -p ~/.claude/skills/custom-distance-metrics
curl -L https://claudskills.com/skills/custom-distance-metrics/SKILL.md \
  -o ~/.claude/skills/custom-distance-metrics/SKILL.md

Or just download SKILL.md directly and drop it into ~/.claude/skills/custom-distance-metrics/. Claude Code auto-discovers it on next session.

Skills live at ~/.claude/skills/custom-distance-metrics/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\custom-distance-metrics\SKILL.md on Windows. See the full install guide for step-by-step instructions.

Telegram

📱 Install from your phone or desktop Telegram

Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →

Pro

One-click install via the desktop app

The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.

Pro

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Frequently asked questions

How do I install the Custom Distance Metrics Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy SKILL.md from the source repository to ~/.claude/skills/custom-distance-metrics/SKILL.md and restart Claude Code. Both flows are detailed at claudskills.com/install/.
What does the Custom Distance Metrics skill do?
Builds two-argument sklearn metric callables and scipy cdist/pdist precomputes (weighted Euclidean/cosine, Numba Manhattan factories) for DBSCAN, HDBSCAN, AgglomerativeClustering, and NearestNeighbors. Needed when Euclidean, cosine, or Jaccard discard sequence, graph, or mixed-type structure. Do not use Lloyd K-Means with a custom metric; do not run a slow Python pairwise on large n without JIT, vectorize, or a precomputed matrix.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Custom Distance Metrics skill?
Use Custom Distance Metrics when your Claude Code task falls under the Engineering category — specifically in the engineering misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Custom Distance Metrics" or describe the task and let Claude pick). Browse related skills at /category/engineering/.
What is a Claude Code skill and how does the Custom Distance Metrics skill fit in?
A Claude Code skill is a SKILL.md file that lives under ~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Custom Distance Metrics is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Engineering category. Learn more at /learn/what-is-a-claude-skill/.

Attribution & license

Cite this skill

If you reference this skill in a blog post, paper, or documentation, you can cite it as:

APA
kazimrmerchant. (2026). Custom Distance Metrics [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/custom-distance-metrics/
BibTeX
@misc{custom-distance-metrics-2026,
  author    = {kazimrmerchant},
  title     = {Custom Distance Metrics [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/custom-distance-metrics/}
}

Embed this skill

Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →

Badge
[![ClaudSkills](https://claudskills.com/badge/custom-distance-metrics.svg)](https://claudskills.com/skills/custom-distance-metrics/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/custom-distance-metrics.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/custom-distance-metrics.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Custom Distance Metrics"></iframe>

Security scan

Grade A · scanned 2026-08-15 — free static scan against the OWASP Agentic Skills Top 10.

No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›

Show this grade on your repo (click to copy):

[![Security: A](https://img.shields.io/badge/Security-A-2e7d32)](https://claudskills.com/skills/custom-distance-metrics/#security)

Free. No spam. Unsubscribe in one click.

More Engineering skills

Browse all Engineering skills in the ClaudSkills registry, or explore these other picks from the same category:

Browse all Engineering skills → Top 100 skills
Part of ClaudSkills — the open registry for Claude Skills & Claude Code Skills.  ·  What's New  ·  Install guide  ·  About  ·  llms.txt

Part of Acreator Store — Adam Lankamer's AI tools: PerfectStudio · Ucaption · UTagger · AutoXPoster · TestYourSkills · AutomationFlows · Au Naturel · Telegram @acreatorstore