A script-based processor for audio recordings and images stored in Gastrohem’s daily WhatsApp folders. It transcribes audio into JSON files and uses OCR to turn image text into Markdown summaries.

Use it to process a day’s audio and image files, create transcripts, extract text from images, and save the results for later use.

It removes repetitive manual work when handling media from dated folders across multiple departments.

skill-075 — Skill for Claude Code and Codex by legendtkl

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/legendtkl/agentic-skill-router

agentmods

npx agentmods add skills/legendtkl/agentic-skill-router/skill-075

Made for: Claude Code, Codex.

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/legendtkl/agentic-skill-router/skill-075/github.svg)](https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-075)

Your own site

<a href="https://agentmods.dev/skills/legendtkl/agentic-skill-router/skill-075"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-075/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/legendtkl/agentic-skill-router/skill-075"><img src="https://agentmods.dev/badge/skills/legendtkl/agentic-skill-router/skill-075.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,172 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	$0.00108	$0.02172
Opus 5	$0.00054	$0.01086
Sonnet 5	$0.00022	$0.00434
Haiku 4.5	$0.00011	$0.00217

Measured 7d ago against content hash 1304288666d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

skill-075 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 7d 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.

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.

experiments/dci-compare/skillrouter-skills/skill-075/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gastrohem Media Processor

Overview

Automatski procesira WhatsApp media fajlove (audio i slike) u Gastrohem dnevnim folderima.

Što radi:

Transkribuje audio fajlove paralelno (3x brže) → kreira .json fajlove
Identifikuje slike koje trebaju OCR → kreira .md fajlove sa prirodnim sažetkom
Default: Koristi današnji datum automatski
Skenira SVE odjele odjednom za dati datum

Performance:

Audio: Do 3 fajla istovremeno (paralelno)
Slike: Batch OCR (sve odjednom sa Claude vision)
Scan: Nalazi sve foldere za datum u <1 sekundi

Note: Skill kreira .json za audio i .md za slike - dodavanje u chat.md je odvojen korak.

When to Use This Skill

User says:

"Process media"
"Process today's media"
"Transcribe audio files"
"Process media for 24.10"
"OCR images in today's folders"

Default behavior: Uses today's date, scans all departments automatically.

Workflow

Simple Usage

Process all media for today (DEFAULT):

python .claude/skills/gastrohem-media-processor/scripts/process_media.py

Uses today's date automatically (26.10 danas)
Scans ALL departments for folders matching today's date
Transcribes audio in parallel
Lists images needing OCR

Process specific date:

python .claude/skills/gastrohem-media-processor/scripts/process_media.py --scan-date 24.10

Process specific folder:

python .claude/skills/gastrohem-media-processor/scripts/process_media.py --folder "gastrohem whatsapp/administracija/20.10 - 27.10/24.10"

What Happens

Audio Processing:

Finds all audio files (.mp3, .ogg, .m4a, .wav, .opus)
Skips files that already have .json transcriptions
Transcribes in parallel (3 concurrent processes)

Creates JSON: {audio_filename}.json

{
  "speakers": [],
  "chunks": [...],
  "text": "Full transcribed text here"
}

Image Processing:

Finds all images (.png, .jpg, .jpeg, .webp, .bmp)
Checks which images DON'T have .md files
Returns list of images needing OCR
Claude reads images in parallel and creates natural summaries with Gastrohem-relevant info

Creates markdown: {image_filename}.md

# image.png

**Poslao:** Mahir Kadic
**Datum:** 26.10.2025 13:58

---

[Natural language summary focusing on Gastrohem-relevant information:
 contacts, names, emails, phone numbers, business details, etc.]

Read the full file on GitHub · 251 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.

7d ago First seen · 251 lines · 108 tokens per session scan A 1304288666d0

Subscribe to this mod's changes

skill-075 is a skill published in the GitHub repository legendtkl/agentic-skill-router (5 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 2,172 once invoked, about $0.0005 per session on Opus 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 2026-09-03.

Documents Research

baoyu-youtube-transcript

A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.

JimLiu/baoyu-skills · 107 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

overleaf-sync

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

wanshuiyin/Auto-claude-code-research-in-sleep · 97 tokens