Daily Briefing Agent Skill

Automated daily tech briefing — multi-source collection → knowledge-base deduplication → AI summarization → TTS speech synthesis, generating MP3 audio briefings

837 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

365

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/cosmicstack-labs/mercury-agent-skills --skill daily-briefing

The instruction itself

13 sections, as written by the author

Daily AI Audio Briefing

> Automatically collect, deduplicate, summarize, and synthesize a daily tech briefing as a warm-voiced MP3 every morning.

Workspace

Collection script + summarization/TTS script
Output: briefing/YYYY-MM-DD.mp3 + .txt
Knowledge base: brain/news/YYYY-MM-DD/
Schedule: cron (recommended 8:30 AM)

Workflow

Collect — Scrape GitHub trending/rising, HN top/show/new, arXiv latest AI papers, weather
Deduplicate — Compare against brain/news/ existing entries
New project → mark is_new
Growth >30% → mark is_update
Otherwise → discard
Ingest — Write new entries to brain/news/YYYY-MM-DD/
Summarize — AI composes briefing script from filtered JSON
Synthesize — TTS API → MP3 file
Cleanup — Delete briefings older than 7 days

Rules

Don't use shell-level file deletion (find -delete) — may trigger security scanners; use Python Path.unlink()
Don't assume cron environment has API keys loaded — export them before running scripts
Don't use inline python3 -c or heredocs in agent/cron mode — write to .py files first
Don't trust agent-reported "MP3 generated" — verify mtime with stat after TTS step
Don't let each source exceed 8 items — keeps briefing concise

Validation

[ ] Collection script runs successfully, all sources return data
[ ] After dedup, filtered items ≥ 3
[ ] Generated briefing text contains correct date (no placeholders)
[ ] MP3 mtime matches current time (TTS actually ran)

Pitfalls

Date placeholders not replaced (Fixed: 2026-05-12)

Symptom: Briefing shows "Year X Month X" instead of actual date
Root cause: Prompt didn't inject real date, AI made it up
Fix: Inject datetime.date.today() into summarization prompt

Wrong weather source (Fixed: 2026-05-12)

Symptom: Always reports wrong city/temperature format
Root cause: Source only provided real-time temp, no high/low
Fix: Switch to structured weather API with high/low temp

Cron security scanner false positives

Symptom: Prompt blocked by exfil_curl pattern
Fix: Mark trusted cron job with skip_injection_scan: true

Cron environment missing .env

Symptom: TTS fails with "Missing credentials"
Fix: Export API keys before script execution

Model reasoning field empty content

Symptom: Reasoning model puts output in reasoning field, content is empty
Fix: Set generous max_tokens + retry with assistant message on empty content

TTS text length limit

Symptom: Long text causes unstable TTS output
Fix: Auto-truncate at safe threshold (~3000 chars)

References

references/weather-api.md — Weather data source and format
references/dedup-rules.md — Deduplication strategy and thresholds
references/tts-config.md — TTS model and parameters
references/cron-prompt-template.md — Cron job prompt template

Other skills for the same job

different authors, same section of the catalogue

Canvas Design

by anthropics

vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take cosmicstack-labs/daily-briefing from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.