orchimada
UserA daily training rig for product judgment, built as two Claude skills that work as a pair.
Categories
Indexed Skills (6)
judgment-coach
The diagnostic half of judgment training — runs after a judgment-drill session to work out *why* the answers failed, not just that they did. Classifies each miss into a named failure mode, traces it to the reasoning move that produced it, rebuilds the attack angle the user should have run, tracks which errors recur across sessions, and sources real open-source cases where the same error shows up in the wild. Use this automatically at the end of every judgment-drill session, and whenever the user asks to go deeper on a graded answer, wants to know what's structurally wrong with their thinking, asks "why do I keep getting this wrong", "what should I have done instead", "give me the method", "what's my pattern", "coach me on that", or invokes /coach in any form. Also use it when the user pastes a graded answer from a past session and wants a post-mortem, or asks for reading on a reasoning failure mode.
judgment-drill
Runs a daily 25-minute product-judgment training session with five stations — Fermi estimation, stock-or-flow diagnosis, third-order consequences, reverse-the-memo, and a Go problem — all built from real, publicly verifiable cases pulled fresh from the web, graded against sources, with a persistent calibration log. Use this whenever the user asks for their daily drill, training, exercises, practice, "the gym", a Fermi question, a stock-or-flow problem, a case to reason through, a Go problem, or wants to review their calibration or streak. Also use it when the user says something like "give me today's session", "let's train", "quiz me", "I want to practise systems thinking", "run the drill", or invokes /drill in any form. Trigger it even when the user only names one station rather than the whole session.
judgment-coach
The diagnostic half of judgment training — runs after a judgment-drill session to work out *why* the answers failed, not just that they did. Classifies each miss into a named failure mode, traces it to the reasoning move that produced it, rebuilds the attack angle the user should have run, tracks which errors recur across sessions, and sources real open-source cases where the same error shows up in the wild. Use this automatically at the end of every judgment-drill session, and whenever the user asks to go deeper on a graded answer, wants to know what's structurally wrong with their thinking, asks "why do I keep getting this wrong", "what should I have done instead", "give me the method", "what's my pattern", "coach me on that", or invokes /coach in any form. Also use it when the user pastes a graded answer from a past session and wants a post-mortem, or asks for reading on a reasoning failure mode.
judgment-drill
Runs a daily 25-minute product-judgment training session with five stations — Fermi estimation, stock-or-flow diagnosis, third-order consequences, reverse-the-memo, and a Go problem — all built from real, publicly verifiable cases pulled fresh from the web, graded against sources, with a persistent calibration log. Use this whenever the user asks for their daily drill, training, exercises, practice, "the gym", a Fermi question, a stock-or-flow problem, a case to reason through, a Go problem, or wants to review their calibration or streak. Also use it when the user says something like "give me today's session", "let's train", "quiz me", "I want to practise systems thinking", "run the drill", or invokes /drill in any form. Trigger it even when the user only names one station rather than the whole session.
analyst-reps
A 12-minute daily high-rep companion to judgment-drill. Four blocks — ratio flashcards, read-a-real-table, an Analysis of Competing Hypotheses rep, and a brief-compliance check — built to close four specific gaps the drill exposes but cannot fix — missing business primitives, failure to extract derivatives from provided data, single-hypothesis lock-in, and not following the brief. Use this whenever the user asks for reps, ratio practice, the daily reps, "analyst reps", a numbers drill, a table to read, an ACH rep, hypothesis practice, or says something like "let's do reps", "quiz me on ratios", "give me a table", "run the reps", or invokes /reps in any form. Also use it when the user pastes a filing, table, earnings deck or dashboard and wants to practise pulling derivatives out of it, and when they ask what a business ratio means or whether a multiple is cheap.
train
The single entry point for the judgment-gym training system. Reads the drill and reps logs, works out what today's session should be — analyst-reps daily, judgment-drill twice a week with judgment-coach immediately after, weekly reviews on schedule — and dispatches to the right skill with the right cross-feed. Use this whenever the user says "train", "what's today's session", "let's go", "gym", invokes /train in any form, or asks what they should practise today, how the week looks, or for a status dashboard across drill, reps and coach. Also use it when the user seems to want to train but hasn't named a specific skill — routing is this skill's job, not theirs.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.