image-matching-webui: Skill for Claude Code

.claude/skills/integrate-matcher/SKILL.md

integrate-matcher is a skill for Claude Code from Vincentqyw/image-matching-webui. It costs 44 tokens per session (5,184 once invoked), scanned C, original, Apache-2.0.

A workflow for adding a feature-matching model to image-matching-webui. Feature matching compares points or patterns between images so they can be aligned or related.

In plain words
What is it for?
Use it when given a GitHub repository for a local image-matching method and asked to make that method available in image-matching-webui.
Why use it?
It removes the need to manually study a model’s repository and adapt it to the web interface’s existing structure.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is Vincentqyw/image-matching-webui's own configuration. It tells Claude Code how to work on image-matching-webui itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything image-matching-webui configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is <matcher>_path = Path(__file__).parent / "../../third_party/<RepoName>/src".

About the project

Image Matching WebUI is a graphical tool for finding corresponding keypoints between two images with different image-matching algorithms. Users can select local or webcam images, choose an algorithm, and inspect the matching result through a Gradio interface.

Vincentqyw/image-matching-webui · 1,301 stars · on GitHub · huggingface.co

Reuse

Borrowing it

Nothing to install: this file belongs to Vincentqyw/image-matching-webui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Vincentqyw/image-matching-webui/main/.claude/skills/integrate-matcher/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Vincentqyw/image-matching-webui

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for integrate-matcher

README.md
[![agentmods](https://agentmods.dev/badge/skills/vincentqyw/image-matching-webui/integrate-matcher/github.svg)](https://agentmods.dev/skills/vincentqyw/image-matching-webui/integrate-matcher)
Your own site
<a href="https://agentmods.dev/skills/vincentqyw/image-matching-webui/integrate-matcher"><img src="https://agentmods.dev/badge/skills/vincentqyw/image-matching-webui/integrate-matcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for integrate-matcher

Your own site · 80×15
<a href="https://agentmods.dev/skills/vincentqyw/image-matching-webui/integrate-matcher"><img src="https://agentmods.dev/badge/skills/vincentqyw/image-matching-webui/integrate-matcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.05184
Opus 5 $0.00022 $0.02592
Sonnet 5 $0.00009 $0.01037
Haiku 4.5 $0.00004 $0.00518

Measured 10d ago against content hash 1035088ea7c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

integrate-matcher scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .git/modules/imcui/third_party/<RepoName>
.claude/skills/integrate-matcher/SKILL.md · 483 lines

How it starts

The opening of the file, as written. The whole thing — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Integrate Matcher into image-matching-webui

This skill automates the integration of a new local feature matching method into the image-matching-webui project. Given a GitHub repository URL, it follows the project's established patterns to add the matcher as a fully functional option in the WebUI.

Prerequisites

  • The target repository must be a local feature matching method (sparse or standalone)
  • You must be working inside the image-matching-webui project root

Step-by-Step Integration Guide

Step 1: Analyze the Target Repository

  1. Clone the repo to /tmp/<repo-name> for analysis (do NOT add as submodule yet)
  2. Identify the matcher type:
    • Dense/Standalone matcher: Takes raw images as input, performs detect+describe+match internally (e.g., LoMa, RoMa, LoFTR). required_inputs = ["image0", "image1"]
    • Sparse matcher: Takes keypoints+descriptors as input, performs matching only (e.g., LightGlue, SuperGlue). required_inputs includes keypoints0, descriptors0, etc.
  3. Find the core model class and its API:
    • How to initialize the model (constructor args, config options)
    • How to run inference (forward method signature)
    • What the model outputs (keypoints, matches, scores, etc.)
    • Model weight download URLs
  4. Check dependencies in pyproject.toml or requirements.txt
  5. Identify model variants (e.g., different sizes: B/L/G/R)
  6. Check for device/amp issues:
    • Does the model use torch.autocast or mixed precision (mp, amp)?
    • Does it manage its own device placement (like LoMa's loma.device)?
    • On MPS/CPU, does it produce dtype mismatches?

Step 2: Add Git Submodule

git submodule add <repo-url> imcui/third_party/<RepoName>
  • Use the original repo name (PascalCase) as the submodule directory name
  • If the repo has a fork in the project's org (e.g., Vincentqyw/xxx or agipro/xxx), prefer the fork
⚠️ CRITICAL: Never modify third_party code directly

imcui/third_party/ contains pinned third-party submodules — you are NOT the owner of this code. If a dependency needs a compatibility fix (e.g., API changes in PyTorch/kornia, import path changes):

Read the full file on GitHub · 483 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 483 lines · 44 tokens per session scan C 1035088ea7c1

Subscribe to this mod's changes

integrate-matcher is a skill published in the GitHub repository Vincentqyw/image-matching-webui (1,301 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 5,184 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

robotgo-flow

Use when building YAML-driven Windows RPA workflows in Go — step-by-step desktop automation with image template matching, interactive recording mode, hotkey triggers. RobotGo-Flow: YAML-based Windows RPA framework built on RobotGo.

znlgis/opengis-skills · 50 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens