What is catalog-intake?

A workflow for turning Google Forms response CSV files into proposed entries for a software catalogue. It normalizes fields, checks URLs and logos, and validates the resulting catalogue data.

Use it to process form submissions, check publicly accessible URLs and logos, prepare a pull-request candidate, and run catalogue validation.

It reduces manual cataloguing work while keeping unverified submissions separate from the final catalogue changes.

How yourtablecloth/TableClothCatalog configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yourtablecloth/TableClothCatalog. 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/yourtablecloth/TableClothCatalog/main/.claude/skills/catalog-intake/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/yourtablecloth/TableClothCatalog

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yourtablecloth/tableclothcatalog/catalog-intake/github.svg)](https://agentmods.dev/skills/yourtablecloth/tableclothcatalog/catalog-intake)

Your own site

<a href="https://agentmods.dev/skills/yourtablecloth/tableclothcatalog/catalog-intake"><img src="https://agentmods.dev/badge/skills/yourtablecloth/tableclothcatalog/catalog-intake/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yourtablecloth/tableclothcatalog/catalog-intake"><img src="https://agentmods.dev/badge/skills/yourtablecloth/tableclothcatalog/catalog-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,144 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00120	$0.03144
Opus 5.5	$0.00048	$0.01258
Sonnet 5.5	$0.00024	$0.00629
Haiku 4.5	$0.00012	$0.00314

Measured 2mo ago against content hash 52bfeb6d4f4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

catalog-intake scanned grade A with 0 findings 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 2mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_urls.py, scripts/detect_switch.py, scripts/fetch_logo.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/catalog-intake/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

카탈로그 제보 인테이크 (catalog-intake)

Google Forms 제보(비-GitHub 사용자용)를 docs/Catalog.xml 변경으로 옮기는 반자동 절차. docs/SITE_HEALTH_WORKFLOW.md와 같은 철학을 따른다: 기계는 정규화·검증·후보 생성까지, 최종 판정과 반영(merge)은 사람.

⚠️ 안전 경계선 (먼저 읽기)

이 카탈로그의 <Package>는 사일런트 스위치로 무인 설치되는 보안 프로그램이다. 제보는 익명은 아니지만(폼 로그인 필수) 미검증 외부 입력이다.
따라서 이 스킬은 PR 후보까지만 만든다. 자동 commit/merge 금지. 사람이 검토 후 반영.
check_urls.py·fetch_logo.py는 URL을 읽기만 한다. 설치 파일을 실행하지 않는다.
데이터 수집 원칙은 docs/DATA_BOUNDARY.md를 따른다. 특히 3절 차단 우회 금지와 4절 인증/유료 게이트 뒤 리소스 제외는 이 스킬의 URL 검증 단계에도 그대로 적용된다. 접근이 막혀 확인이 안 되는 항목은 우회하지 말고 gap으로 남긴다.

입력

필수: Google Forms 응답을 내보낸 CSV 경로 (Sheets → 파일 → 다운로드 → CSV).
참고 문서: references/field-mapping.md — 필드 매핑·Category· gap 정의·설치기/스위치 시드표. 처리 규칙의 근거는 전부 여기에 있다.

사전 준비 (도구)

uv (Python) — scripts/*.py 실행. PEP 723 자체완결이라 uv run 시 의존성 자동 설치.
ussfc — 무인 설치 스위치 탐지(.NET 전역 도구). 최초 1회 설치:
```
dotnet tool install -g ussfc      # 갱신: dotnet tool update -g ussfc
```
설치 없이 쓰려면 .NET 10 SDK의 dnx ussfc도 가능(detect_switch.py가 자동 폴백).
gh (GitHub CLI) — PR/이슈 생성. dotnet 10 SDK — catalogutil.cs 등 검증 도구.

파이프라인

[0] 최신화 (필수)            main pull → 작업 브랜치 생성  ← 스킬 시작 전 반드시
      │
[1] normalize   (오프라인)   CSV → 정규화 JSON + gap 플래그
      │
[2] 게이트 확인               consent/dedup 누락 건은 보류 표시
      │
[3] 항목별 처리              빈칸 4종 채우기(아래 규칙) — URL확인/로고/스위치/분류
      │
[4] 편집                     Catalog.xml + 이미지 배치 (변경 유형별 commit 분리)
      │
[5] 검증                     catalogutil.cs 스키마 검증 + (선택) checksites.cs probe
      │
[6] PR + 미완 이슈           완전반영은 PR diff / 미완은 추적 이슈 생성 후 PR에 링크. merge는 사람.

0. 최신화 — 스킬 실행 전 반드시

제보를 처리하기 전에 로컬 main을 원격 최신으로 맞추고 새 작업 브랜치에서 시작한다. stale한 베이스 위에서 편집하면 이미 반영된 항목을 중복 추가하거나 충돌 검사가 어긋난다.

git switch main
git pull --ff-only origin main          # 최신 카탈로그 확보 (fast-forward만)
git switch -c catalog-intake/<날짜-또는-배치명>   # 예: catalog-intake/2026-07-forms

Read the full file on GitHub · 200 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2mo ago First seen · 200 lines · 120 tokens per session scan A 52bfeb6d4f4b

Subscribe to this mod's changes

catalog-intake is a skill published in the GitHub repository yourtablecloth/TableClothCatalog (21 stars, last pushed 12d ago), licensed Apache-2.0. It adds 120 tokens to every session and 3,144 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

hacktoberfest xml

catalog-intake next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
catalog-intakeyourtablecloth/TableClothCatalog	Skill	21	12d ago	Apache-2.0	A	120	Claude Code
oh-my-poshJanDeDobbeleer/oh-my-posh	Skill	24k	today	MIT	A	47	Claude Code, Codex
conventional-commitJanDeDobbeleer/oh-my-posh	Skill	24k	today	MIT	A	26	Claude Code, Codex
researchArindam200/awesome-ai-apps	Skill	17k	5d ago	MIT	A	78	Claude Code, Codex
date-formatterAzure/azure-sdk-for-net	Skill	6.1k	today	MIT	A	13	Claude Code, Codex
keys-and-harmony-with-pytheorykennethreitz/pytheory	Skill	1.7k	yesterday	MIT	A	132	Claude Code
redux-to-swrcockroachdb/cockroach	Skill	33k	4d ago	none	A	53	Claude Code

TableClothCatalog: Skill for Claude Code