improve-urselflisted

# improve-urself This skill extracts durable learnings from the current conversation and creates or updates skills so the pattern persists beyond this session. The core idea: you just ran an experiment. The conversation is the execution trace. Mine it. --- ## Step 1: Mine the conversation for signal Scan the conversation for: - **Mistakes made** — Claude produced wrong output, used the wrong tool, misread intent - **Corrections given** — user said "no, do it like this", "you should have", "next time" - **Patterns that worked** — a technique that solved something cleanly, a format the user liked - **Repeated friction** — anything the user had to clarify more than once - **Domain-specific knowledge** — facts, conventions, or constraints specific to this project/codebase If called with topic args (e.g., `/improve-urself bash errors`), focus extraction on those topics. Otherwise extract the 1–3 most impactful learnings from the whole session. For each learning, note: - What happened (the failure or insight) - What the correct behavior is - How generalizable it is (just this project? all projects? this type of task?) --- ## Step 2: Check for existing skills to update Look in the `skills/` directory of this plugin for existing skills with overlapping scope. Also check any loaded skills in the current session. If a skill already covers the topic: - Propose an edit to that skill rather than creating a new one - Merging is better than fragmentation — don't create a separat