Stats
Actions
Tags
From autocode
Records mistakes with what, why, and how-fixed, then checks memory before similar builds to avoid repeating errors silently.
How this skill is triggered — by the user, by Claude, or both
Slash command
/autocode:learn-mistakeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
::GENE{learn-mistake|conf:confirmed|scope:global}
::GENE{learn-mistake|conf:confirmed|scope:global} -e T:record_what_why_how_fixed T:check_before_similar_feature T:avoid_silently A:say_i_remember_this_mistake⇒just_avoid_it A:repeat_known_mistake⇒check_memory
::ACTIVATE{learn-mistake} ON:auto
Powered by I-Lang v4.0 | ilang.ai
npx claudepluginhub ilang-ai/autocode --plugin autocodeCaptures agent mistakes, corrections, and discovered gotchas so they are not repeated. Use when: (1) a command or operation fails unexpectedly, (2) the user corrects the agent, (3) the agent discovers non-obvious behavior through debugging, (4) an API or tool behaves differently than expected, (5) a better approach is found for a recurring task. Also searches past learnings before starting tasks to avoid known pitfalls. Activate alongside the memory skill — they share sage-memory but serve different purposes (memory = codebase knowledge, self-learning = agent mistakes and gotchas). Also trigger on "sage review" or "review learnings" to curate and improve the learning database.
Captures lessons from bug fixes and corrections in Phoenix/Elixir projects — Ecto, LiveView, Oban, iron law mistakes. Documents rules in CLAUDE.md or MEMORY.md to prevent repeats.
Detects user corrections, reworks, mistakes, or note requests; runs human-confirmation loops, archives to project/global mistakebook/notebook, refreshes memory caches, escalates to Ascended Mode on repeats.