skill-freshness

Audit upstream file dependencies for staleness across enabled skills in aeon.yml.

Updated Jun 3, 2026

Search Tags:#automation #monitoring #dependencies #freshness #aeon #mtimes

Ready to run

npx skills add https://github.com/swarm-ai-research/aeon --skill skill-freshness-swarm-ai-research

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-freshness
Source: https://github.com/swarm-ai-research/aeon/tree/main/skills/skill-freshness
Command: npx skills add https://github.com/swarm-ai-research/aeon --skill skill-freshness-swarm-ai-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires os, re, json, datetime.

What problem does it solve?

Audit enabled skills' upstream file dependencies to detect staleness that could cause downstream consumers to read outdated data. It flags potential issues before they manifest in production runs.

Core Features & Use Cases

Universal freshness audit: scans all enabled skills in aeon.yml to identify stale or missing upstream references across articles, outputs, memory topics, and memory state files.
Threshold-based severity: evaluates file age against per-class thresholds derived from each producer's cadence, classifying as OK, WARN, STALE, or MISSING.
Automated reporting & state: generates a daily skill-freshness article and persists a fingerprinted state to prevent duplicate notifications, with optional operator alerts when issues arise.

Quick Start

Run the freshness audit to generate the daily report and update state across all enabled skills in aeon.yml.

Frequently Asked Questions about skill-freshness

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I audit dependency freshness across automated workflows?▼

Audit dependency freshness by scanning all enabled skills to evaluate file age against per-class thresholds, classifying upstream references as OK, WARN, STALE, or MISSING to prevent downstream reads of stale data.

What causes stale data reads in automated pipeline dependencies?▼

Stale data reads occur when upstream file dependencies like articles, outputs, and memory state files become outdated. Auditing mtimes against cadence-derived thresholds detects these issues before production runs manifest them.

How do I monitor upstream file dependencies for staleness across all skills?▼

Monitor upstream dependencies by evaluating explicit chains and implicit references across articles, outputs, topics, and state files. The audit computes age against per-class thresholds and writes a daily report with severity classifications.

Can I generate daily freshness reports and persist state for deduplication?▼

Yes, the freshness audit generates a daily article and persists a fingerprinted state to prevent duplicate notifications. Optional operator alerts are triggered when issues or missing dependencies arise.

Does the freshness audit work with skills defined in aeon.yml?▼

Yes, the audit applies to every skill defined in aeon.yml. It evaluates explicit dependency chains and implicit references across all enabled skills to compute age and assign severity.

What are the limitations of monitoring dependency mtimes for freshness?▼

Freshness monitoring relies on file mtimes and per-class thresholds derived from producer cadence. It cannot detect logically incorrect data, only age-based staleness, and classifies dependencies strictly as OK, WARN, STALE, or MISSING.