lifecyclereport

SkillDocs & knowledge

Lets your agent scan a project's memory files and report tier counts plus which memories are ready for promotion.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the lifecyclereport skill

About this skill

Scan project memory for v1.7.1 lifecycle frontmatter · report tier distribution + promotion candidates (reinforce_count >= promote_after) · NO LLM.

What this skill tells your AI

The instructions your AI receives, as published by chunxiaoxx/nautilus-compass in skills/codified/lifecycle_report/SKILL.md and read by ahel’s review.

Aggregate the 4-tier lifecycle schema landed in v1.7.1 across a project's memory directory. Identifies memories ripe for tier promotion using the LLM-free deterministic rule: reinforce_count >= promote_after.

When to use

Pre-promotion audit: which working-tier memories should be promoted to episodic? Which episodic to semantic?
Decay sweep: which memories have hit their forget_at ISO8601 timestamp?
Tier health check: ratio of working/episodic/semantic/procedural memories.

Why codified

Frontmatter parsing is stable (won't change · v1.7.1 fixed schema)
Deterministic output · no LLM
Used by the 4-tier paradigm validation per paper3 cite (llm-wiki2 fuse)

Signals

GitHub stars: 818
Forks: 18
Last commit: Sep 2026

Advanced

Item type: skill
Key: lifecycle-report
Source: github.com/chunxiaoxx/nautilus-compass

github.com/chunxiaoxx/nautilus-compass

lifecyclereport

What this skill tells your AI

When to use

Why codified

Signals

Related picks