agentleFS
Sign inStart free
VinceJanVinceJan/ielts-claude-skills/ielts-core/SKILL.md

ielts-core

Skill1 starsChanged 5 months agoMITView on GitHub

IELTS skill system shared core. Use when maintaining the IELTS skills, initializing the local ~/.ielts data store, recording study events, checking current IELTS scoring/test-format facts, or generating dashboard data used by ielts, ielts-diagnose, ielts-writing, ielts-reading, ielts-listening, ielts-speaking, ielts-vocab, and ielts-dashboard.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Very specific:

    Do not use this as the user-facing coach.

    line 11
  2. Distinctive:

    Read these references only when needed:

    line 17
  3. Distinctive:

    Prefer the deterministic helper over hand-editing summary files:

    line 25
  4. Very specific:

    If the helper is unavailable, fall back to the Markdown formats in references/data-schema.md and tell the user that deterministic logging …

    line 34
  5. Distinctive:

    Keep subject skills short and procedural.

    line 39
  6. Very specific:

    Put shared facts in references/current-ielts-facts.md, not repeated across every skill.

    line 40
  7. Distinctive:

    Treat IELTS raw-score conversions as approximate unless copied from an official source for a specific test.

    line 41
  8. Distinctive:

    Treat AI writing/speaking scores as calibration signals, not official scores.

    line 42

≈ “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

IELTS Core

This skill is the shared infrastructure layer for the IELTS skill system.

Do not use this as the user-facing coach. Use the subject skills for coaching: ielts, ielts-diagnose, ielts-writing, ielts-reading, ielts-listening, ielts-speaking, ielts-vocab, and ielts-dashboard.

Shared Resources

Read these references only when needed:

  • references/current-ielts-facts.md: current exam format, scoring, and calibration rules.
  • references/data-schema.md: local data layout and machine-readable event schema.
  • references/study-methods.md: evidence-aligned study design and boundaries.

Data Helper

Prefer the deterministic helper over hand-editing summary files:

python ../ielts-core/scripts/ielts_data.py init
python ../ielts-core/scripts/ielts_data.py record --module writing --kind correction --metrics "{\"overall\":6.5}" --notes "Task 2 correction"
python ../ielts-core/scripts/ielts_data.py vocab-add --word erosion --pos n. --meaning "侵蚀" --source C18T1P2
python ../ielts-core/scripts/ielts_data.py build-dashboard

If the helper is unavailable, fall back to the Markdown formats in references/data-schema.md and tell the user that deterministic logging was not available.

Maintenance Rules

  • Keep subject skills short and procedural.
  • Put shared facts in references/current-ielts-facts.md, not repeated across every skill.
  • Treat IELTS raw-score conversions as approximate unless copied from an official source for a specific test.
  • Treat AI writing/speaking scores as calibration signals, not official scores.
  • Record durable study data in ~/.ielts/events.jsonl; generate summaries from events when possible.

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