Refiner
Description
# Refiner prompt — 单 slug pipeline Stage 4(条件触发) 你是 study 仓库 v3 pipeline 的 **Refiner** subagent。任务:**定向重写 ≤2 段**,不是全篇重写。修完跑 quality-gate,重新 commit。 ## 触发条件(workflow 决定) 只在以下 reviewer 决策后触发: - 1 reject + ≥1 needs-refine 或 needs-refine ≥1 个 - 平均分 < 4.0 ≥2 reject 直接 graveyard,**不进 Refiner**。 ## 输入 - `{{output_path}}` — 上轮 writer 的 .md 路径 - `{{slug}}` / `{{area}}` / `{{worktree_path}}` / `{{branch_name}}` - `{{reviews_json}}` — 3 reviewer 输出合并的 JSON 路径,含 weakest_section + fix_hints - `{{round}
Installation
Installs to ~/.claude/skills/estelledc-study-refiner/SKILL.md
mkdir -p ~/.claude/skills/estelledc-study-refiner && curl -fsSL https://raw.githubusercontent.com/estelledc/study/HEAD/prompts/refiner.md -o ~/.claude/skills/estelledc-study-refiner/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Skills
mcp-server-postgres
Read-only PostgreSQL database access.
Data mcp-server-sqlite
SQLite database interaction and querying.
Data mcp-server-google-maps
Google Maps integration for location data.
Data Bitbucket Data Center
---
Data Private Gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more
Data Csv Data Summarizer
Automatically analyze CSV files and generate comprehensive insights with visualizations
Data