agentsclimarketplace
Sign in

Personal workspace router

Skill markoblogo/abvx-agent-skills/skills/personal-workspace-router

Design or maintain a local personal AI workspace with a root router, isolated domain folders, user-triggered memory, decision logs, and sparse routing corrections. Use when a user wants one agent workspace spanning multiple projects or life/work domains without mixing context or bloating every session.From its SKILL.md

Install
npx -y skills add markoblogo/abvx-agent-skills --skill personal-workspace-router

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.8 KB, 554 tokens by cl100k_base, as published. Nobody here has run it

Personal Workspace Router

Build a compact local operating layer above project repos. The goal is not one giant memory file; it is routing to the smallest relevant context.

Workspace Shape

WORKSPACE/
├── AGENTS.md
├── MEMORY.md
├── DECISIONS.md
├── ROUTING-LOG.md
└── domains/
    └── <domain>/
        ├── AGENTS.md
        └── MEMORY.md

Core Rules

  1. Root router first: AGENTS.md maps domain signals to domains/<name>/.
  2. On-demand domain context: read only the routed domain's AGENTS.md; read its MEMORY.md only when durable preferences matter or the user asks about remembered context.
  3. User-triggered memory: write memory only when the user explicitly says to remember, log, save, note, or not forget something.
  4. Conflict check: if a requested memory contradicts existing memory, show the conflict and ask how to reconcile it.
  5. Decision log sparingly: append one-line preference signals to DECISIONS.md only after meaningful forks.
  6. Routing log sparingly: append to ROUTING-LOG.md only after user correction, a new durable signal, or repeated ambiguity.

Domain Creation

When adding a domain:

  1. Ask a short interview:
    • domain name;
    • routing signals;
    • repo paths or external surfaces;
    • default stance and forbidden actions;
    • what memory is safe to store.
  2. Create domains/<domain>/AGENTS.md.
  3. Create domains/<domain>/MEMORY.md with a user-triggered policy and empty entries.
  4. Add the domain to the root routing map.

Guardrails

  • Do not ask for confirmation before every routine step; ask only when route, memory, or action risk is real.
  • Do not store secrets, credentials, private contacts, raw transcripts, or bulky logs.
  • Do not turn every successful route into a routing-log entry.
  • Do not let personal workspace rules override repo-local safety, tests, or approval gates.

Pair With

  • project-context-bootstrap when a repo/domain has weak starting context.
  • durable-context-maintenance when repo docs drift after work.
  • doc-grounded-grilling when domain language or durable decisions need sharpening.
  • agent-learning-layer-triage when deciding whether a lesson belongs in memory, docs, a skill, script, or eval.

Final Report

Return the workspace path, created domains, memory policy, decision-log policy, and any unresolved routing ambiguities.

What ships with it: 2 files

2.6 KB alongside SKILL.md

agents/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.