agentleFS
victordelrosalvictordelrosal/chairman/.claude/skills/knowledge/SKILL.md

knowledge

Skill0 starsChanged 8 months agoMITView on GitHub

Knowledge base update from field data. Scans the week's operational data for new patterns, structures them, and writes to department knowledge bases. Thursday-Friday routine. Octopus colors: Yellow (pattern extraction) + Red-Orange (structure) + Blue (implementation).

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read .chairman/config.json for active departments

    line 14
  2. Distinctive:

    Check for contradictions with existing knowledge base entries

    line 23
  3. Very specific:

    Write new entries to departments/{dept}/knowledge/

    line 26
  4. Distinctive:

    Update existing entries if information has changed

    line 27
  5. Very specific:

    Remove outdated entries (move to _archive/ subfolder)

    line 28
  6. Very specific:

    Never delete knowledge base entries.

    line 53
  7. Very specific:

    Check for contradictions before writing.

    line 54
  8. Distinctive:

    Do not add speculative knowledge.

    line 55
  9. Distinctive:

    If $ARGUMENTS targets a specific department, only update that one.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “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

/knowledge: Knowledge Base Update

Octopus Colors: Yellow (Researcher) + Red-Orange (Designer) + Blue (Maker)

Process

  1. Read .chairman/config.json for active departments
  2. For each department (or specific department if $ARGUMENTS provided):
  3. Scan for new knowledge (Yellow):
    • Recent reports in .chairman/reports/
    • Recent assignments and their outputs
    • Patterns: recurring issues, common objections, process gaps
    • Customer feedback or market signals
  4. Structure the knowledge (Red-Orange):
    • Categorize: process update, FAQ, pattern, correction
    • Check for contradictions with existing knowledge base entries
    • Format consistently with existing entries
  5. Implement updates (Blue):
    • Write new entries to departments/{dept}/knowledge/
    • Update existing entries if information has changed
    • Remove outdated entries (move to _archive/ subfolder)

Output Format

# Knowledge Base Update: [Date]

## Updates Made

### [Department]
- **Added:** [filename] - [what was added and why]
- **Updated:** [filename] - [what changed]
- **Archived:** [filename] - [why it is outdated]

### [Department]
...

## Summary
- Total updates: [count] across [dept count] departments
- New entries: [count]
- Updated: [count]
- Archived: [count]

Rules

  • Never delete knowledge base entries. Archive them to _archive/.
  • Check for contradictions before writing. If found, flag to Chairman.
  • Do not add speculative knowledge. Only patterns supported by data.
  • If $ARGUMENTS targets a specific department, only update that one.
  • Notify Chairman of significant additions (new process, corrected procedure).

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.