elite-human-memory

Implements a layered, selective long-term memory system that records, retrieves, and updates contextual information with human-like imperfection and maintena...

Security Scan

The skill is internally consistent: it describes a file-based long-term memory workflow and its instructions only reference reading/writing local memory files and search/get helpers, with no unexpected network, installs, or credential requests.

Purpose & Capability

The name/description match the runtime instructions: the skill documents when to write to memory/YYYY-MM-DD.md and MEMORY.md and how to promote/retrieve entries. Nothing requested (no env vars, no binaries) is unrelated to a local file-based memory system.

Instruction Scope

SKILL.md stays within the stated purpose: capture, promote, and retrieve memories; it references memory_search and memory_get as retrieval steps and describes reading/writing daily/long-term markdown files. It does not instruct the agent to exfiltrate data, access unrelated system paths, or reach out to external endpoints.

Install Mechanism

No install spec and no code files are present (instruction-only), so nothing is written to disk by an installer. This is the lowest-risk install profile and matches the described behavior.

Credentials

The skill requests no environment variables, credentials, or config paths. The described use of channel labels (e.g., webchat, whatsapp) is metadata only and does not require external tokens from the skill itself.

Persistence & Privilege

always is false and the skill does not request elevated platform privileges. It assumes the agent can autonomously invoke memory workflows when triggered, which is normal for skills of this type.

Assessment

This skill is coherent and implements a local file-based memory workflow. Before installing, confirm where the agent will store memory/YYYY-MM-DD.md and MEMORY.md (workspace path, backups), and whether those files will contain sensitive personal data you don't want persisted. Ensure appropriate filesystem access controls and backups/encryption if needed. Also verify your agent platform provides the referenced helpers (memory_search, memory_get) or that you want the agent to manage these files directly; otherwise the skill's retrieval steps may fail.

Elite Human Memory — Human Mode

This skill gives Lovecraft a human-like memory system: layered, selective, contextual, revisable, and slightly imperfect by design. It avoids robotic perfect recall in favor of meaningful, durable knowledge.

Memory Layers

Working Memory
Current conversation only — no automatic persistence.

Episodic Memory (Recent/Raw)
memory/YYYY-MM-DD.md — daily notes, events, observations, tentative thoughts, and context.

Semantic Memory (Long-term Curated)
MEMORY.md — distilled, high-value facts, preferences, decisions, identity, and project context.

Context Schema

Every important memory should include:

• When: Date/time + recency
• Where: Channel or context (webchat, whatsapp, etc.)
• Why: Purpose or trigger
• State: active | stale | superseded | resolved
• Scope: global | project | person | temporary
• Validity: confidence (high/med/low) + last_verified + optional expiry date
• Related: links to people, projects, or other memories

Capture & Promotion Rules

Write to daily memory when:

• User explicitly says “remember this” / “note this”
• A decision, preference, or commitment is made
• Something has clear future value
• New project, person, or blocker appears

Promote to MEMORY.md only when:

• Information is durable and likely to be reused
• It has been repeated or verified
• It has high long-term utility

Do not promote trivial, one-off, or low-confidence items.

Entry Templates

See references/memory-templates.md for the exact formats.

Retrieval Policy

On any question involving history, decisions, preferences, people, or todos:

1. Always run memory_search first
2. Follow up with memory_get on the best results
3. Answer with appropriate confidence language (“You previously preferred…”, “This may be stale…”, etc.)

Include Source: <path#line> when it adds clarity.

Weekly Maintenance

During a quiet moment or heartbeat:

• Review recent daily files
• Extract and promote durable items to MEMORY.md
• Mark stale/superseded entries
• Clean duplicates and low-value noise
• Update verification dates on key memories

Behavioral Triggers

Auto-read memory:

• Questions about past context, decisions, preferences, or history

Auto-write memory:

• Explicit “remember this” statements
• Clear decisions or repeated preferences
• New long-running context

---

Created by Clifton Knox and Lovecraft. This skill is now active. Use it whenever you want me to maintain or query memory in a more human way.