mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-22 14:12:31 +01:00
Drop the explain-back exit and the opening-belief question. Once code passes the examples (or kuhy says done), the coach writes the post-mortem from the transcript, builds the cards, and appends missing toolbox entries itself; toolbox_cards add gains --define for new vocabulary properties. Adds the contribution technique entry from sum-of-all-odd-length-subarrays. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WzxdWWTVKrxg1PGVP4wc6W
1005 B
1005 B
The commands and the method, as the status app's Coach tab shows them
Quoted verbatim from how_to.py; tests/test_how_to.py fails if they differ.
SKILL.md section 3 is the full method; this is its one-line-per-step form.
Commands:
leetcode --cluster <name>- Serve the next problem of a concept cluster (a due re-test comes first).leetcode <url>- Coach one problem, from its LeetCode URL or slug.leetcode due- List the cold re-tests that are due.leetcode report- One row per session: requirements before code, hint rung, reveal.
The command skips problems LeetCode already shows as Accepted, so it may serve a later one than listed here.
The method:
- Constraint - Turn the hard constraint into a rule for the design.
- Requirements - List what the operation must do, as properties, never by name.
- Toolbox - Search the toolbox for an operation with those properties.
- Post-mortem - Claude says which hint gave which requirement and makes the cards.