Memory Tiering

Automated multi-tiered memory management (HOT, WARM, COLD). Use this skill to organize, prune, and archive context during memory operations or compactions.

Security Scan

The instructions match a memory-management purpose, but the skill asks the agent to read and prune internal memory files (including daily logs) and gives vague guidance around handling credentials without declaring any config paths or provenance — this could inadvertently delete important data or mishandle secrets.

Purpose & Capability

Name/description align with the SKILL.md: it is a memory tiering/pruning tool that reads HOT/WARM/COLD memory and daily logs. However, the skill declares no config paths or provenance (homepage/source unknown) while instructing access to specific memory files (e.g., memory/hot/HOT_MEMORY.md, memory/warm/WARM_MEMORY.md, MEMORY.md, memory/YYYY-MM-DD.md). That mismatch (no declared config paths but explicit file paths in instructions) is worth noting.

Instruction Scope

Runtime instructions tell the agent to read all three tiers and recent daily logs and to prune/aggregate COLD content. They also instruct dealing with 'credentials in HOT' (pointing them to root files instead of storing raw secrets). These are destructive/modifying operations (prune, move, remove granular details) and they implicitly touch secrets; the guidance is vague about conditions, safeguards, or backups. This grants the agent broad discretion over internal data and could lead to unintended data loss or exposure if misapplied.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. Nothing is written to disk by the skill itself.

Credentials

The skill requires no environment variables or credentials, which is consistent with being instruction-only. However, it explicitly references 'credentials in HOT' and instructs actions around them without declaring how those credentials are provided or protected. That gap (handling secrets without declared config/paths or safeguards) is concerning.

Persistence & Privilege

always is false and there is no install. The skill can be invoked autonomously (disable-model-invocation is false), which is platform-default; combined with the instruction to run after /compact, this could cause automatic pruning unless you restrict triggers.

What to consider before installing

This skill appears to implement what it claims, but exercise caution before installing or enabling it. Specific recommendations: - Confirm where your agent stores the 'memory/' files referenced in the SKILL.md and review their contents for secrets or important data. Back them up before running this skill. - The SKILL.md instructs pruning and deleting granular data; test the workflow on non-sensitive data first and require explicit confirmation before any irreversible pruning. - Because it mentions 'credentials in HOT' but declares no config paths or credential variables, verify how your agent stores credentials and ensure the skill will not transform or delete raw secrets unintentionally. - Prevent or review automatic triggers (it says it runs after /compact) until you trust its behavior. - The skill has no homepage or source and the owner is unknown—lack of provenance increases risk. Prefer skills with clear source code or documentation. If you want to proceed, ask the skill author for: an explicit list of file paths it will read/modify, a dry-run mode that shows proposed changes without applying them, and a documented backup/rollback procedure.

Memory Tiering Skill 🧠⚖️

This skill implements a dynamic, three-tiered memory architecture to optimize context usage and retrieval efficiency.

The Three Tiers

1. 🔥 HOT (memory/hot/HOT_MEMORY.md):
   • Focus: Current session context, active tasks, temporary credentials, immediate goals.
   • Management: Updated frequently. Pruned aggressively once tasks are completed.
2. 🌡️ WARM (memory/warm/WARM_MEMORY.md):
   • Focus: User preferences (Hui's style, timezone), core system inventory, stable configurations, recurring interests.
   • Management: Updated when preferences change or new stable tools are added.
3. ❄️ COLD (MEMORY.md):
   • Focus: Long-term archive, historical decisions, project milestones, distilled lessons.
   • Management: Updated during archival phases. Detail is replaced by summaries.

Workflow: Organize-Memory

Whenever a memory reorganization is triggered (manual or post-compaction), follow these steps:

Step 1: Ingest & Audit

• Read all three tiers and recent daily logs (memory/YYYY-MM-DD.md).
• Identify "Dead Context" (completed tasks, resolved bugs).

Step 2: Tier Redistribution

• Move to HOT: Anything requiring immediate attention in the next 2-3 turns.
• Move to WARM: New facts about the user or system that are permanent.
• Move to COLD: Completed high-level project summaries.

Step 3: Pruning & Summarization

• Remove granular details from COLD.
• Ensure credentials in HOT point to their root files rather than storing raw secrets (if possible).

Step 4: Verification

• Ensure no critical information was lost during the move.
• Verify that HOT is now small enough for efficient context use.

Usage Trigger

• Trigger manually with: "Run memory tiering" or "整理记忆层级".
• Trigger automatically after any /compact command.