agentleFS
WingedGuardianWingedGuardian/skyrimvr-claude-toolkit/.agents/skills/logging-registry/SKILL.md

logging-registry

Skill22 starsChanged 3 days agoMITView on GitHub

Inventory, search and refresh logging switches across a Skyrim install, with configured values, source evidence and explicit coverage gaps. Use to locate debug/log controls or assess observability before troubleshooting. Does not enable logging or analyze log contents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Use tools/logging-registry.py for repeatable read-only discovery.

    line 9
  2. Distinctive:

    Keep generated inventories and local review files out of a public repository.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
<!-- GENERATED by scripts/gen_agent_trees.py from agent/skills/logging-registry/SKILL.md. Toolkit contributors: edit the source. Your own notes belong in KNOWLEDGEBASE.local.md, which updates never replace. -->

Logging registry

Use tools/logging-registry.py for repeatable read-only discovery. Read the tool guide for formats, review annotations and limits.

Choose the actual game/Data and user-config roots. Do not silently select a different Skyrim edition or interpret an MO2 mods directory as the winning virtual Data view. For MO2, obtain an externally resolved view or describe the missing coverage; individual mod folders are not authoritative winners.

python tools/logging-registry.py scan --game-root <game> --config-dir <user-config> --plugins-txt <authority-plugins.txt> --output-dir <local-report-dir>
python tools/logging-registry.py show <local-report-dir>/registry.json --filter <mod-or-setting>
python tools/logging-registry.py diff <previous-registry.json> <new-registry.json>

Keep generated inventories and local review files out of a public repository. Reports redact arbitrary string values and omit log contents, but still reveal installed component/file names. Use synthetic fixtures for public tests and examples.

Report both discoveries and the denominator: scanned scopes, file outcomes, limits, unresolved components, missing parsers and uninspected archives/compiled code. Distinguish logging candidates from general debug candidates, configured values from defaults/commented examples, and source declarations from deployed PEX behavior. A failed or empty search does not prove that a mod lacks logging.

Before describing how a switch works, inspect its installed documentation/source or verified runtime behavior. Record reviewed semantics with --reviews; reviews are bound to source hashes and become stale when the file changes. No review annotation establishes runtime verification automatically. Use existing log-triage tools to analyze contents separately when requested.

The scanner never toggles settings, launches the game, decompiles scripts or installs dependencies. A request to inventory logging does not authorize enabling debug modes. Some debug switches change gameplay or render overlays rather than merely write logs.

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.