craft-tune
craft-tune
Purpose
Diagnose an existing prompt or skill and apply targeted edits that preserve its core intent.
A pass over a working artifact is two jobs in one: figure out what's actually broken, then change only what's blocking the goal. Diagnosis without edits leaves the user holding the bag; edits without diagnosis silently drift the artifact's scope and lose the lessons its phrasing already encodes. craft-tune does both in one pass and lets the user stop after diagnosis when that's what they need.
Use this when
- a prompt or skill is close but needs sharpening
- a prompt "feels off" or behaves inconsistently across runs
- a working artifact needs review before being generalized or shipped
- a large rewrite is tempting and a diagnostic pass should anchor the next edit
- minimal-diff improvement is better than rewriting from scratch
Switch to diagnose-only mode when the user explicitly wants findings without edits — typical signals: "review only," "diagnose only," "what's wrong with this but don't change it yet," "audit before I touch it." See § Diagnose-only mode.
Inputs
More from sungjunlee/craftkit
craft-scaffold
Turn a rough idea into a structured prompt or skill scaffold with explicit objective, inputs, workflow, outputs, and a concrete file plan. Use this whenever the user wants to design a new prompt or skill, scaffold a skill-like workflow, mentions "scaffold," "blueprint," "structure," or "plan" for a prompt, or arrives with a vague request that needs to be shaped before implementation — even if they don't explicitly ask to scaffold.
9craft-survey
One-shot prior-art survey — study comparable prompts, skills, or repo assets, extract recurring patterns worth adopting, flag patterns to avoid, and synthesize actionable improvements for the current artifact. Use this whenever the user wants to ground a prompt or skill in proven patterns, references older assets to learn from, asks "how do others do this," mentions "survey," "prior art," or "research," or is designing something new and wants a literature-review pass before committing — even if they don't say "survey." Distinct from craft-autoresearch (which runs an eval-driven optimization loop, not a prior-art survey).
9craft-prompt
Craft well-structured, copy-paste-ready prompts for any LLM — Claude, GPT, Gemini, Perplexity, or any other. Use this whenever the user wants a prompt built from scratch, asks to "write/make/build a prompt," needs a session handoff prompt to carry work into a new Claude Code or Codex session, shares scattered notes that need to be shaped into a usable prompt, or requests a reusable prompt template — even if they don't explicitly say "prompt." Also triggers on Korean equivalents like "프롬프트 만들어," "프롬프트 작성," "프롬프트 빌드.
9craft-autoresearch
Eval-driven autonomous optimization loop for a prompt or skill. Define eval criteria and a run harness, then iterate — run the artifact on test inputs, score outputs, mutate the prompt or skill, keep improvements, discard regressions, and stop on a written condition. Use this whenever the user wants to automatically improve a prompt or skill, mentions autoresearch, eval-driven optimization, benchmarking a skill, running evals, self-improving a prompt, or any iterative test-and-refine request — including 스킬 개선, 스킬 최적화, 스킬 벤치마크, 스킬 평가 — even if they don't say "autoresearch.
9craft-handoff
>-
8craft-critique
Critique a prompt or skill and surface ambiguity, hidden assumptions, weak structure, portability issues, and likely failure modes before any rewrite happens. Use this whenever the user asks to review, audit, critique, or diagnose a prompt or skill, mentions a prompt that "feels off" or behaves inconsistently, or is about to start a large rewrite and should stop to diagnose first — even if they don't explicitly say "critique" or "review.
7