skill-freshness

Audit enabled skill consumers for stale dependency files against producer freshness thresholds.

6|2|Updated May 21, 2026

Search Tags:#autonomous agents #quality monitoring #dependency tracking #freshness audit #scheduled workflows #alert deduplication

Ready to run

npx skills add https://github.com/anajuliabit/aeon --skill skill-freshness

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Skill freshness prevents autonomous workflows from consuming outdated upstream outputs without errors by auditing on-disk file modification times against expected producer cadences.

Core Features & Use Cases

Silent staleness auditing: Checks that enabled consumer skills are about to read fresh producer artifacts (articles, chain outputs, memory topic/state files) even when everything “succeeds.”
Explicit + implicit dependency detection: Uses aeon.yml chain consume edges as the source of truth, then supplements coverage by extracting real path references from enabled skills’ SKILL.md files.
Severity-based verdicts and actionable reporting: Produces a single decision-ready article that flags OK, WARN, STALE, and MISSING, with suggested next actions for the worst consumers.
Run-to-run deduplication: Fingerprints flagged dependencies to suppress repeated notifications when nothing materially changes (with periodic re-emit for persistent issues).

Quick Start

Run skill-freshness in dry-run mode for a fleet audit of all enabled skills by using var=dry-run in your invocation.

Frequently Asked Questions about skill-freshness

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

FAQPage Schema

How do I detect silent stale data in autonomous agent workflows?▼

Silent stale data is detected by auditing dependency file modification times and existence against expected producer freshness thresholds. This catches downstream skills consuming outdated cached files when upstream producers stop updating without errors.

Why does my scheduled workflow keep using cached files after an upstream producer stops updating?▼

Scheduled workflows use cached files because autonomous agents lack inherent staleness detection. Auditing dependency file modification times against producer cadences is required to flag outdated artifacts and prevent downstream skills from silently consuming stale data.

How do I run a freshness audit for all enabled skills?▼

Run a freshness audit in dry-run mode by setting var=dry-run in your invocation. This locally parses aeon.yml schedules and SKILL.md dependency references to produce a decision-ready report flagging OK, WARN, STALE, and MISSING dependencies.

How does dependency tracking handle alert deduplication for persistent stale data?▼

Dependency tracking handles alert deduplication by fingerprinting flagged dependencies to suppress repeated notifications. This prevents alert fatigue while ensuring persistent stale data issues are periodically re-emitted to maintain visibility.

Can I extract implicit dependency paths from SKILL.md files for freshness monitoring?▼

Implicit dependency paths are extracted by parsing real path references directly from enabled skills' SKILL.md files. This supplements explicit aeon.yml consume edges to ensure full freshness monitoring coverage across autonomous agent workflows.

What are the limitations of using file mtimes for staleness detection in scheduled agents?▼

File mtime staleness detection is limited to local-only parsing of aeon.yml schedules and SKILL.md references. It compares modification times against expected producer thresholds but cannot verify semantic data accuracy within freshly modified files.