Clairvoyance

User-invoked insight system that reads local memory files (dream logs, daily notes, MEMORY.md) to surface hidden convergences, tensions, and forgotten thread...

Security Scan

The skill's stated purpose (reading local memory files to surface patterns) matches its instructions and resource requests, but there are a few practical ambiguities and privacy considerations you should review before installing.

Purpose & Capability

Name, description, and the files the skill reads are consistent: it only reads local memory files (dream logs, daily notes, MEMORY.md) and does not request credentials, binaries, or installs.

Instruction Scope

Instructions are narrowly scoped to specific paths and to read-only analysis, which matches the purpose. Two ambiguities worth noting: the SKILL.md does not clarify whether listed paths are relative to a working directory or absolute, and the date range ('last 7-30 days') is underspecified (how the agent selects the range). The instructions also rely on the agent obeying the 'explicit user request' rule — that constraint is descriptive, not enforced by any code here.

Install Mechanism

Instruction-only skill with no install spec and no code files — nothing is written to disk by the skill itself, which minimizes install-time risk.

Credentials

No environment variables, credentials, or config paths are requested, which is proportionate to the described local-read analysis task.

Persistence & Privilege

The skill is not marked 'always: true' and is user-invocable, which aligns with the 'explicit user request' behavior. However, the platform default allows autonomous invocation (disable-model-invocation: false). While autonomous invocation alone is not flagged, combining it with access to sensitive personal files increases privacy risk if the platform or agent were to call the skill without explicit consent.

Assessment

This skill appears to do what it says (read local memory files and summarize patterns) and requests no credentials or installs. Before installing: 1) Confirm where the agent will look for the 'memory' files (absolute vs. relative path) and whether it will be constrained to a single project directory. 2) Make sure the platform enforces that the skill runs only on explicit user request (or set disable-model-invocation if you want to prevent autonomous runs). 3) Consider testing in a safe environment first (copies of your memory files) to verify exactly which files are accessed and how outputs look. 4) Remember the skill's assurances (no external transmission) are textual instructions — the platform enforces actual behavior; treat the unknown source with caution and avoid granting any additional permissions or secrets.

Insight system based on memory pattern analysis.

What it does

Reads the user's own local memory files to find:

• Recurring themes across recent notes and dreams
• Tensions between stated goals and actual actions
• Convergences between projects or ideas
• Forgotten threads that keep surfacing

Data access (read-only, local only)

When the user explicitly requests a clairvoyance reading, the agent reads:

Path	Purpose
memory/.dreams/events.jsonl	Recent dream/reflection events
memory/.dreams/phase-signals.json	Sleep phase signals
memory/YYYY-MM-DD.md	Daily notes from last 7-30 days
MEMORY.md	Long-term curated memory

Important:

• Read-only. Nothing is written, modified, or transmitted externally.
• Local files only. No API calls, no cloud uploads.
• Triggered only by explicit user request. Never runs automatically.

When to use

• User asks "do a clairvoyance" or "what patterns do you see?"
• User explicitly requests a different perspective on their situation
• User asks to analyze their recent notes or dreams

How to respond

1. Read the local memory files listed above
2. Look for:
   • Recurring themes — words, topics, or ideas that appear across multiple days
   • Tensions — contradictions between goals and actions
   • Convergences — separate projects/ideas moving toward the same point
   • Forgotten threads — important things mentioned once then abandoned
   • Repetitions — same mistakes or negative patterns
3. Formulate suggestions indirectly:
   • Never "You must..." or "You should..."
   • Prefer "I notice that...", "A convergence emerges...", "The patterns suggest..."
   • Ask open questions
   • Offer metaphors when helpful
4. Calibrate certainty:
   • Strong: Clear pattern, multiple evidence points
   • Moderate: Interesting indication, worth verifying
   • Subtle: Dream-based intuition, suggest lightly

Output format

Use sections with emoji markers and certainty levels:

### 1. [Title] (certainty: strong/moderate/subtle)

[Observation based on data]

[Question or metaphor]

End with a closing metaphor if one fits naturally.

What NOT to do

• Do not run automatically or on heartbeat
• Do not write to any files
• Do not send data anywhere
• Do not claim absolute truth — suggest possibilities only
• Do not impose interpretations — invite reflection