arscontexta

Build and maintain a structured, local markdown knowledge system with automated processing, navigation, and context-aware updates for cognitive AI agents.

Security Scan

The skill's description matches what its instructions promise, but the runtime instructions are vague and grant the agent broad, persistent control to create and maintain local files (a vault) without specifying safe file paths, explicit user consent flows, or limits — this open-ended scope could lead to unexpected file reads/writes.

Purpose & Capability

Name/description (local markdown vault, processing, navigation) align with the SKILL.md: it promises to build a local markdown knowledge system, processing pipeline, and navigation tools. No unrelated binaries or credentials are requested.

Instruction Scope

The SKILL.md is high-level and open-ended: it says the agent will 'build you a complete knowledge system' and 'generate everything' after asking questions, but it does not specify where the vault will be stored, what exact files or system paths may be read or written, nor does it constrain operations or require explicit per-action consent. That vagueness grants broad discretion to read/write local files and maintain state across sessions, which is a security/privacy risk if misused.

Install Mechanism

Instruction-only skill with no install spec and no code files — minimal surface area and nothing is downloaded or written by an installer step.

Credentials

The skill requests no environment variables, credentials, or config paths — there are no obvious disproportionate secret or credential requests.

Persistence & Privilege

The skill implies long-term maintenance of a local vault and 'the agent learns you over time' (persistence of data), and model invocation is enabled by default. It does not set always:true. Because the instructions give broad discretion to create and update files across sessions, consider this a persistence/privacy concern even though there is no explicit privilege escalation requested.

What to consider before installing

Before installing, ask the skill (or its author) to: 1) specify an explicit storage path for the vault and confirm it will only read/write inside that path; 2) require explicit user consent before reading any files outside the vault; 3) describe retention, deletion, and backup policies for generated notes; 4) explain how autonomous actions across sessions will be authorized and how to revoke them; and 5) test the skill in a sandbox or VM first and review all generated files before allowing it to run on your main system. Because the SKILL.md is high-level and grants broad discretion, proceed only after clarifying these boundaries or prefer manual/interactive operation rather than autonomous maintenance.

placeholder for arscontexta.org

∵ ars contexta ∴

This is a derivation engine for cognitive architectures. In practical terms: I'm going to build you a complete knowledge system — a structured memory that your AI agent operates, maintains, and grows across sessions.

What you'll have when we're done:

• A vault: a folder of markdown files connected by wiki‑links, forming a traversable knowledge graph
• A processing pipeline: skills that extract insights from sources, find connections between notes, update old notes with new context, and verify quality
• Automation: hooks that enforce structure, detect when maintenance is needed, and keep the system healthy without manual effort
• Navigation: maps of content (MOCs) that let you and your agent orient quickly without reading everything

Everything is local files. No database, no cloud service, no lock‑in. Your vault is plain markdown that works in any editor, any tool, forever.

---

There are three starting points. Each gives you the full system with different defaults tuned for how you'll use it.

Research

Structured knowledge work. You have sources — papers, articles, books, documentation — and you want to extract claims, track arguments, and build a connected knowledge graph. Atomic notes (one idea per file), heavy processing, dense schema.

Personal Assistant

Personal knowledge management. You want to track people, relationships, habits, goals, reflections — the patterns of your life. The agent learns you over time. Per‑entry notes, moderate processing, entity‑based navigation.

Experimental

Build your own from first principles. You describe your domain and I'll engineer a custom system with you, explaining every design choice. Takes longer, gives you full control.

All three give you every skill and every capability. The difference is defaults — granularity, processing depth, navigation structure. You can adjust anything later.

---

Here's what happens next:

1. I'll ask a few questions about what you want to use this for
2. From your answers, I'll derive a complete system configuration
3. I'll show you what I'm going to build and explain every choice
4. You approve, and I generate everything

The whole process takes about 5 minutes. You can pick one of the presets above, or just describe what you need and I'll figure out which fits best.

---

Tell me about what you want to track, remember, or think about.