agentleFS
charleslucascharleslucas/poe_mcp_suite/.claude/skills/freshness-check/SKILL.md

freshness-check

Skill9 starsChanged 3 months agoMITView on GitHub

Model-aware staleness check before asserting how a PoE mechanic/item/system works, plus a scope filter so league/event mechanics don't bleed into the wrong character. Routes to freshness_index.md + mechanics_index.md.

3 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

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    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. Very specific:

    Read reference_data/freshness_index.md and follow its "How to use it" procedure:

    line 10
  2. Distinctive:

    Look up that model's training cutoff in the index's model table.

    line 13
  3. Very specific:

    Treat anything in the index newer than the running model's cutoff as must-verify — use the entry's "Where / verify via" pointer (a cached …

    line 14
  4. Distinctive:

    If the mechanic/item isn't in the index but is plausibly recent (current or last few leagues), verify it anyway and add a row to the index …

    line 16
  5. Distinctive:

    Do not duplicate the index content here — the index is the single source of truth and is maintained per league.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 3 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

Your PoE training knowledge has a model-specific cutoff and the game changes every league, so the biggest risk is an unknown unknown: confidently asserting a mechanic that changed or didn't exist yet.

  1. Read reference_data/freshness_index.md and follow its "How to use it" procedure:
    • Identify the running model (mcp__pob__get_context_usage reports the model ID).
    • Look up that model's training cutoff in the index's model table.
    • Treat anything in the index newer than the running model's cutoff as must-verify — use the entry's "Where / verify via" pointer (a cached file, a memory, or a fresh fetch_wiki_page / live PoB call).
  2. If the mechanic/item isn't in the index but is plausibly recent (current or last few leagues), verify it anyway and add a row to the index so the next session is covered.
  3. Scope filter (compartmentalization). Also consult the mechanic-keyed companion reference_data/mechanics_index.md for each mechanic's current scope (core / challenge-league / event-only / removed / disabled-this-league / nerfed). When the task concerns a specific character, first establish its context (league/realm, and whether it's an event character — see playbooks/README.md §2c), then only apply mechanics whose scope includes that context. A Mirage-only or event-only mechanic must not be recommended for a Standard / next-league / non-event character; a removed or disabled-this-league one isn't present at all. This stops league/event data bleeding into the wrong build.
  4. This is most load-bearing when asserting how a mechanic works or evaluating a unique/node/item's current stats — not every step of a task. Per CLAUDE.md, defer to live tool data over memory when they conflict.

Do not duplicate the index content here — the index is the single source of truth and is maintained per league.

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.