agentleFS
Sign inStart free
tikocitikoci/rosetta/.github/skills/re-extract/SKILL.md

re-extract

Skill54 starsChanged 4 months agoMITView on GitHub

Re-extract the legacy Confluence RouterOS documentation export into SQLite. Use only for rebuilding historical pre-migration DBs; the default pipeline (make extract-full) fetches the live manual.mikrotik.com Docusaurus docs instead.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use this skill as the migration path for <https://manual.mikrotik.com>.

    line 14
  2. Very specific:

    Do not run this against a DB built by extract-docusaurus — pick one prose source per build.

    line 46
  3. Very specific:

    If HTML directory changed, update HTML_DIR in the root Makefile

    line 63
  4. Very specific:

    If using offline/local data, pass explicit source paths to extract-commands.ts or extract-all-versions.ts

    line 64

≈ “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

Re-extract Legacy Documentation Pipeline

When to Use

  • A legacy Confluence HTML export is available
  • Database needs rebuilding from scratch
  • Schema changes require fresh extraction
  • New RouterOS versions available in restraml GitHub Pages

Do not use this skill as the migration path for https://manual.mikrotik.com. MikroTik's new Docusaurus manual and CLI Reference require extractor and MCP/TUI result-shape redesign; read DESIGN.md and briefings/B-0012-docusaurus-manual-migration.md first.

Procedure

  1. Verify prerequisites
    • Bun is installed: bun --version
    • Dependencies installed: bun install
    • Legacy HTML export exists in box/documents-export-*/ROS/
    • For commands: internet access to https://tikoci.github.io/restraml/ (or provide a local docs path explicitly)
  2. Clean existing database
    make clean

  3. Run the legacy pipeline

    make extract / make extract-full are the Docusaurus pipeline and never read box/ — the legacy path is its own sequence:

    make extract-legacy-confluence   # extract-html + extract-properties from box/latest/ROS
make extract-commands            # single version (fast), or:
make extract-all-versions        # all tracked RouterOS versions (slower)
make link

    Pipeline order:

    • extract-html — HTML → pages + callouts tables
    • extract-properties — Property tables from HTML → properties table
    • extract-commands or extract-all-versions — inspect.json → commands + ros_versions + command_versions
    • link — command ↔ page mapping

    Do not run this against a DB built by extract-docusaurus — pick one prose source per build.

  4. Verify results
    make search query="firewall filter"
    Expected counts (March 2026 export, all versions):
    • ~317 pages, ~4860 properties, ~1034 callouts
    • ~40K commands (primary version), ~1.67M command_versions
    • 46 ros_versions, ~92% dir link coverage
  5. Validate with type check and lint
    bun run typecheck && make lint

Troubleshooting

  • If HTML directory changed, update HTML_DIR in the root Makefile
  • If using offline/local data, pass explicit source paths to extract-commands.ts or extract-all-versions.ts
  • Each extractor is idempotent — safe to re-run individually
  • FK deletion order matters: callouts → properties → pages

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.

Check your setup, free