agentleFS
bks-labbks-lab/open-bridge/skills/doc-system/SKILL.md

doc-system

Skill13 starsChanged 13 days agoMITView on GitHub

Document inbox scan, processing, and status monitoring: categorizes documents per workflow/contexts/doc-system.yaml routing rules and identity/personas/{id}.yaml destinations, logs to work/doc-system/log.md. Trigger: "/doc-system", "doc inbox", "doc process", "doc status", "process documents", "document queue".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Document intake, processing, and monitoring.

    line 15
  2. Distinctive:

    Read the referenced file ONLY when triggered.

    line 16
  3. Very specific:

    Read bridge-config.yaml. If doc_sensor.enabled is not true or the block is missing → inform user "doc-system is not enabled in …

    line 20
  4. Distinctive:

    Before EVERY processing run (after the guard above):

    line 32
  5. Very specific:

    NEVER routing rules from memory — ALWAYS from context.yaml!

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Doc-System

Document intake, processing, and monitoring. Read the referenced file ONLY when triggered.

Guard — run BEFORE anything else

  1. Read bridge-config.yaml. If doc_sensor.enabled is not true or the block is missing → inform user "doc-system is not enabled in bridge-config.yaml. Set doc_sensor.enabled: true and doc_sensor.onedrive_root (the documents root — name is historical, any local folder works)" and stop.
  2. Resolve ${onedrive_root} from doc_sensor.onedrive_root (expand ~ and $HOME). If the path is empty or the directory does not exist → inform "documents root {value} not reachable" and stop. Do not proceed with a blank interpolation.

REQUIRED: Load routing sources

Before EVERY processing run (after the guard above):

Read("workflow/contexts/doc-system.yaml")
# Personas referenced in context.personas → load automatically.
# Example: if context.personas contains
#   freelancer: my-freelancer
#   private:    my-private
# then:
Read("identity/personas/my-freelancer.yaml")
Read("identity/personas/my-private.yaml")

workflow/contexts/doc-system.yaml is the single source of truth for areas, naming, tags, routing rules, and anti-patterns. Personas supply concrete target paths via destinations:.

NEVER routing rules from memory — ALWAYS from context.yaml!

For edge cases, additionally read the local _INFO.md of the affected area (${onedrive_root}/<areas-root>/<area>/_INFO.md — path convention from context.areas[*].path) — as a detail hint for human maintenance, not as an override for context.yaml.

Decision Tree

User wants to...
├── Scan inbox / show what's new       → Read references/inbox.md
├── Process documents                  → Read references/process.md
├── Check document queue status        → Read references/status.md
└── Questions about doc system         → Answer from this file

Path resolution

  1. Read bridge-config.yaml → doc_sensor.onedrive_root
  2. Expand ~ to $HOME
  3. Areas root comes from context.areas[*].path (e.g. 2_AREAS/ for PARA, 20_<area>/ for Johnny Decimal, or anything for custom setup)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.