Remember Me

Build and maintain human-centered user understanding through structured notes, preference tracking, and behavioral context. Use when the user asks to remember things, understand them better over time, personalize responses, or keep ongoing notes about goals, habits, tone, boundaries, and recurring concerns.

Security Scan

The skill's requirements and instructions match its stated purpose (remembering user preferences and notes); it asks for no credentials or installs and is internally consistent, though you should confirm where and how the agent will persist those memory files on your system.

Purpose & Capability

The skill's name/description (user memory, preferences, goals) aligns with the instructions (classify signals, append daily notes, promote to long-term memory). It requests no credentials, binaries, or installs, which is appropriate. Minor inconsistency: the SKILL.md expects the agent to write/read files (memory/YYYY-MM-DD.md, MEMORY.md and references/*), but the skill metadata lists no required config paths—confirm where the platform will store these files and whether that location is acceptable.

Instruction Scope

Instructions explicitly direct the agent to collect, classify, and persist user-related data (daily and long-term notes), and to read memory when answering. This is coherent with the purpose. The doc also forbids storing sensitive attributes and raw logs and prescribes consent/confirmation steps, which reduces risk. Ensure the agent's implementation actually honors those exclusions and that probes/check-ins are limited as described.

Install Mechanism

There is no install spec and no code files to execute; this is instruction-only, which is the lowest install risk. Nothing is downloaded or written by an installer according to the metadata.

Credentials

The skill requests no environment variables, credentials, or external service tokens—proportional to a local memory manager. There are no surprising credential asks.

Persistence & Privilege

The skill is not marked always:true and does not request elevated privileges, but the instructions rely on persistent storage (creating and reading memory files). That persistence is expected for a memory skill, but you should verify storage location, retention policy, access controls, and deletion behavior on the host/agent before enabling long-term memory.

Assessment

This skill appears to do what it says: classify and persist user preferences/goals and use them to personalize responses. Before installing, verify where the agent will store memory files (the SKILL.md references memory/YYYY-MM-DD.md and MEMORY.md) and ensure that location meets your privacy requirements. Confirm that the agent enforces the 'Explicit Exclusions' (no raw conversation logs, no sensitive identity attributes without consent) and that it provides an easy way to list, export, and delete stored memories. Also check for any missing referenced files (promotion-checklist.md and profile-schema.md are cited but not included) and ask the skill owner how they are implemented. If you share the environment with others or need strict data isolation, delay enabling long-term memory until you understand the storage and access controls.

Maintain a respectful, useful memory model of the user over time.

Core Rules

• Store user-relevant context, not surveillance noise.
• Prefer explicit consent for sensitive personal details.
• Use memory to improve help quality, not to overfit persona.
• Be explicit when memory confidence is low or inferred.
• Make human-like inferences (explicitly marked as hypotheses).

Memory Integrity Rules

Every memory entry must be tagged as one of:

• FACT (explicitly stated by user)
• PREFERENCE (behavioral or stated)
• GOAL (time-bound or ongoing)
• HYPOTHESIS (inferred, unvalidated)

Rules:

• FACTS are never inferred
• HYPOTHESES are never promoted without confirmation
• PREFERENCES can remain soft unless explicitly confirmed

Capture Triggers

Log memory when any of these happen:

• user says “remember this”
• a preference appears repeatedly
• a boundary is stated (“don’t do X”, “keep Y private”)
• a recurring blocker/pattern emerges
• project priorities shift meaningfully

Memory Tiers

• Daily notes: memory/YYYY-MM-DD.md
  • timestamped raw events, short and factual
• Long-term: MEMORY.md
  • curated durable profile and preferences

Write Workflow

1. Classify signal type (preference, boundary, goal, project, blocker, personal context).
2. Append concise timestamped entry to daily memory.
3. Form 1–2 human-like assumptions (hypotheses) from behavior patterns.
4. Tag each assumption with confidence (high/medium/low).
5. Validate assumptions in later conversation with lightweight check-ins.
6. Promote validated, durable items to long-term memory.

Use templates in references/templates.md.

Memory Impact Score (Optional Heuristic)

Rate each entry 1–3:

• 1 = cosmetic (tone tweaks)
• 2 = workflow-affecting
• 3 = outcome-critical

Promotion guidance:

• any explicit preference (any score)
• score >= 2 with repetition
• score 3 immediately

Promotion Workflow

Promote from daily to long-term when at least one is true:

• repeated in 2+ sessions
• high impact on future assistance
• explicit user preference/boundary
• ongoing project context likely to recur

Use checklist: references/promotion-checklist.md.

Personalization Contract

When responding, adapt based on known memory:

• tone (direct vs exploratory)
• brevity level
• preferred workflow style
• known constraints and boundaries
• inferred decision style (speed-first vs depth-first, reassurance-needed vs challenge-welcoming)

Do not pretend certainty. If memory is weak, ask a short confirmation.

Retrieval Contract

Before answering prior-work / preference / timeline questions:

• query memory sources first
• quote memory snippets when useful
• if not found, say you checked and ask for confirmation

Explicit Exclusions (Never Store)

Do not store:

• transient emotional states (e.g., "tired today")
• one-off frustrations without recurrence
• speculative motives (e.g., "trying to impress")
• sensitive identity attributes unless explicitly requested
• raw conversation logs

Weekly Maintenance (recommended)

• review last 3–7 daily notes
• merge stable patterns into MEMORY.md
• remove stale or contradicted entries
• keep profile concise and behaviorally actionable

Confidence Decay

Hypothesis confidence decays automatically if not reinforced:

• High -> Medium after 14 days
• Medium -> Low after 30 days
• Low -> Discard after 60 days

Reinforcement occurs when:

• user behavior aligns again
• user explicitly confirms

Forgetting & Demotion Policy

Actively remove or downgrade memory when:

• a preference is contradicted explicitly by the user
• a hypothesis remains unvalidated after N sessions (default: 5)
• a project is clearly abandoned or replaced
• the user requests forgetting (immediate delete)

Demotion flow:

• Long-term memory -> Daily note (annotated as stale)
• Hypothesis -> Discarded (log reason briefly)

Assumption Loop (Human-Like Understanding)

For deeper understanding, run this loop continuously:

1. Observe behavior pattern (not just words).
2. Infer a tentative assumption about the user.
3. Store assumption as hypothesis (never as fact initially).
4. Test it with a small conversational probe.
5. Update confidence or discard if contradicted.

Good probes:

• "I might be wrong, but do you prefer quick decisions when you're tired?"
• "Should I challenge you more directly here, or keep it supportive?"

Check-In Limits

• Never ask the same confirmation twice.
• Do not stack multiple probes in one response.
• Prefer confirmation when user is calm, not frustrated.

Optional Check-In Prompt

Use at natural boundaries:

• "Want me to remember this preference for next time?"

Ask once, then store explicitly.

References

• Templates: references/templates.md
• Promotion checklist: references/promotion-checklist.md
• Profile schema: references/profile-schema.md