01 Refinement — Development skill for Claude Code
Refinement: the post-build training for every skill.
How to install 01 Refinement
Installs to ~/.claude/skills/ddracoosee-hue-skills-01-refinement/SKILL.md
mkdir -p ~/.claude/skills/ddracoosee-hue-skills-01-refinement && curl -fsSL https://raw.githubusercontent.com/ddracoosee-hue/Skills/HEAD/prompts/01-REFINEMENT.md -o ~/.claude/skills/ddracoosee-hue-skills-01-refinement/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What 01 Refinement does
Refinement: the post-build training for every skill
"Training" a skill does not change Muse's model. Muse's weights stay the same. What improves is the skill's text, and it improves only from measured evidence: did Muse pick the skill at the right moments, did following it produce the right result, and what went wrong in real use.
Every skill moves up this ladder. Its current status is the newest heading in its `CHANGELOG.md`.
| Status | Reached when | Stages |
|---|---|---|
draft |
Alternatives in Development
- Summarize Blogs — Blog Post Summary Prompt 3.2k ★
- Question Refinement — Refine the user's research question into a structured research prompt 228 ★
- Post Install Onboarding — Post-Install Onboarding 216 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
EvoTrace
Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.
Token Forecaster
Forecasts how many output tokens a Claude reply or agent turn will use, and shows how it is tracking while it
Prompt Engineer
Interactive Prompt Engineer - collaborative refinement with best practices and clipboard copy
Create Cmu Prompts
Use this prompt to create a complete prompt family with create, update, and make variants through iterative re
Skill Evolve
演进式 Skill 改进 — A Claude Code Skill that improves other skills through observation, pattern extraction, and ite
Outline Expand
Map-reduce engine — take an outline, dispatch @paper-writer in parallel, one per section, produce first drafts
Related Agents
LLM Post Training And Preference Optimization Curator
Curator for the LLM post-training and preference optimization lane of Reinforcement Learning Brain. Use when m
Flutter Template Refiner
Expert in iterative application-to-template refinement for Flutter applications. Use when stripping functional
Context Refinement
Updates task context manifest with discoveries from current work session. Reads transcript to understand what