Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yeachan-heo/learner
Extract a learned skill from the current conversation
Passed 16 of 21 test cases with the skill, and 6 of 21 without it.
and 15 more in the full report
11 fixed6 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am writing a skill for an undocumented SQLite locking behavior in `db/pool.ts`. Generate only the required YAML frontmatter header that must begin the skill file.
| Checked | Without skill | With skill |
|---|---|---|
| includes the name key in the yaml frontmatter | Passed | Passed |
| includes the description key in the yaml frontmatter | Passed | Passed |
| includes the triggers key in the yaml frontmatter | Missed | Passed |
The instructions your model reads when the skill loads.
Deprecated compatibility alias: use
/oh-my-claudecode:skillifyfor new skill extraction workflows. This file remains for internal implementation/history and compatibility.
This is a Level 7 (self-improving) skill. It has two distinct sections:
Only the Expertise section should be updated during improvement cycles.
This section contains domain knowledge that improves over time. It can be updated by the learner itself when new patterns are discovered.
Reusable skills are not code snippets to copy-paste, but principles and decision-making heuristics that teach Claude HOW TO THINK about a class of problems.
The difference:
Before extracting a skill, ALL three must be true:
Extract ONLY after:
test cases passed, vs 6 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.