rlaope/ultraprompt

context-memory-hygiene

Invoke when deciding what to load into context, what to persist across turns or sessions, and what to drop — reads only what the task needs, writes durable handoffs, avoids context pollution, and chooses when to re-derive versus recall.

원문 언어: 영어

delegation-parallelism

Invoke when deciding whether to split work across parallel agents/sessions or do it inline — tests scope independence, weighs coordination cost against the parallelism win, and sets an observation cadence for delegated work.

원문 언어: 영어

exploration-strategy

Build an accurate mental model of an unfamiliar codebase or problem before making any edit — structural scan, entry-point location, one end-to-end trace, and an explicit known-vs-assumed ledger.

원문 언어: 영어

failure-mode-enumeration

Systematically enumerate how code can break — boundaries, concurrency, partial failure, malicious input, time, resource exhaustion — before writing defenses, then convert the list into tests and guards while pruning paranoia that does not pay rent.

원문 언어: 영어

honest-reporting

Invoke when writing any status, completion, or result report — calibrates claims to the evidence actually gathered, marks the unmeasured as open, reports failures plainly, and distinguishes "verified at layer X" from "should work".

원문 언어: 영어

hypothesis-management

Debug by maintaining 2-4 competing hypotheses with explicit evidence and kill criteria, choosing each probe to maximally discriminate between them instead of confirming a favorite.

원문 언어: 영어

incremental-safety

Decompose a large or risky change into a sequence of independently safe intermediate states, so the system stays green at every step and any step can be reverted alone.

원문 언어: 영어

self-correction-loop

Invoke when an implementation attempt produces a failure signal (test failure, compile error, wrong output, crash, perf regression) and you must decide whether to retry, rethink, or back out — instead of hammering the same fix.

원문 언어: 영어

spec-to-code-fidelity

Invoke when implementing from an authoritative written source — an RFC, academic paper, binary format spec, protocol document, or mathematical derivation — where correctness means matching the document, not just passing ad-hoc tests.

원문 언어: 영어

state-probing

Invoke before acting on any assumption about the runtime or environment — versions, running processes, file/disk reality, git state, network reachability. Grounds claims about the world in a cheap probe instead of a guess, and re-probes when state may have…

원문 언어: 영어

tradeoff-articulation

Invoke when a design decision has multiple viable implementations and the choice affects performance, memory, complexity, or blast radius — forces enumerating real alternatives, quantifying the axes that matter, and recording what would reverse the decision.

원문 언어: 영어

verification-discipline

Invoke before claiming any task is done — defines what counts as evidence of completion (execution, not inspection) and how to verify at the layer the requirement actually lives at.

원문 언어: 영어