处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

MITAuto-check passedDevelopment

Install Refine Task

skills CLI
$ npx skills add ModelEngine-Group/fit-framework --skill refine-task -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ModelEngine-Group/fit-framework refine-task --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ModelEngine-Group/fit-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/refine-task .claude/skills/refine-task && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
refine-task
GitHub stars
2.1k
Token cost
~134 tokens
SKILL.md length
31 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

  • Works in 7 steps: 验证前置条件 → 读取审查报告,整理问题 → 按优先级逐项修复,修复后运行相关测试验证。 → …
  • Development work in your project
  • Calls mvn

What it does

Refine Task is an agent skill from ModelEngine-Group/fit-framework. 处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

Its SKILL.md is about 130 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: FIT: 企业级AI开发框架,提供多语言函数引擎(FIT)、流式编排引擎(WaterFlow)及Java生态的LangChain替代方案(FEL)。原生/Spring双模运行,支持插件热插拔与智能聚散部署,无缝统一大模型与业务系统。 The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/refine-task”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 验证前置条件
  2. 读取审查报告,整理问题
  3. 按优先级逐项修复,修复后运行相关测试验证。
  4. 运行测试验证
  5. 更新 implementation.md,追加"修复记录"章节。
  6. 更新任务状态。
  7. 提示重新审查(review-task)或直接提交(commit)。

What it can do on your machine

Read from SKILL.md and the folder at commit e2f285d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • mvn

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Refine Task loads about 134 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 31 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~134

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ModelEngine-Group/fit-framework at commit e2f285d, republished under its MIT licence (© ModelEngine-Group). 31 words, ~134 tokens.

Download SKILL.mdSave it as .claude/skills/refine-task/SKILL.md (or your agent's skills folder).
name
refine-task
description
处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。

修复审查问题

执行步骤

  1. 验证前置条件:

    • .ai-workspace/active/<task-id>/task.md 存在
    • .ai-workspace/active/<task-id>/review.md 存在
  2. 读取审查报告,整理问题:

    • 🔴 Blocker 问题(必须修复)
    • 🟡 Major 问题(建议修复)
    • 🟢 Minor 问题(可选修复)
  3. 按优先级逐项修复,修复后运行相关测试验证。

  4. 运行测试验证:

    bash
    mvn test -pl :<module-name>
  5. 更新 implementation.md,追加"修复记录"章节。

  6. 更新任务状态。

  7. 提示重新审查(review-task)或直接提交(commit)。

注意: 严格按照审查报告修复,不要添加额外变更。不要自动 git commit。

© ModelEngine-Group, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/refine-task of ModelEngine-Group/fit-framework.

Open the folder on GitHubat commit e2f285d

Compare with similar skills

Refine Task next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Refine Task compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Refine Task this skillModelEngine-Group/fit-framework2.1k—~134Automated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from ModelEngine-Group/fit-framework

All 21 skills in this repo
  • Commit

    ModelEngine-Group/fit-framework

    提交当前变更到 Git,包含版权头年份检查和任务状态更新。当用户要求提交代码、git commit、保存变更时触发. An agent skill from ModelEngine-Group/fit-framework.

    2.1k GitHub stars~268 tokensUpdated 6 mo ago
    Auto-check passed
  • Create Release Note

    ModelEngine-Group/fit-framework

    从 PR/commit 中自动生成结构化的 Release Notes,并可选创建 GitHub Draft Release。支持 x.y.0 版本合并前一 minor 系列的 release notes。当用户要求生成发布说明、创建 release notes 时触发。参数为版本号和可选的上一版本号。

    2.1k GitHub stars~255 tokensUpdated 6 mo ago
    Auto-check passed
  • Test Integration

    ModelEngine-Group/fit-framework

    执行 FIT Framework 集成测试(服务启动 + 接口验证),需要先完成 Maven 构建。当用户要求运行集成测试、验证服务接口时触发。

    2.1k GitHub stars~218 tokensUpdated 6 mo ago
    Auto-check passed
  • Analyze Codescan

    ModelEngine-Group/fit-framework

    分析 Code Scanning (CodeQL) 告警,评估安全风险并创建修复任务。当用户要求分析 Code Scanning 告警、CodeQL 告警时触发。参数为告警编号。

    2.1k GitHub stars~187 tokensUpdated 6 mo ago
    Auto-check passed
  • Close Codescan

    ModelEngine-Group/fit-framework

    关闭 Code Scanning (CodeQL) 告警,需提供合理理由。当用户要求关闭 Code Scanning 告警、dismiss CodeQL 告警时触发。参数为告警编号。

    2.1k GitHub stars~185 tokensUpdated 6 mo ago
    Auto-check passed
  • Create PR

    ModelEngine-Group/fit-framework

    创建 Pull Request 到指定或自动推断的目标分支。当用户要求创建 PR、提交 PR、发起合并请求时触发。可选参数为目标分支。

    2.1k GitHub stars~179 tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Refine Task

What does Refine Task do?

处理代码审查反馈并修复审查中发现的问题。当用户要求修复审查问题、处理 review 反馈时触发。参数为 task-id。. Refine Task is an agent skill from ModelEngine-Group/fit-framework.

When should I use Refine Task?

Refine Task fits situations like: development work in your project.

How do I install Refine Task in Claude Code?

Run `npx skills add ModelEngine-Group/fit-framework --skill refine-task -a claude-code`. Or copy the skill folder (.agents/skills/refine-task in ModelEngine-Group/fit-framework) into .claude/skills/refine-task in your project. Claude Code loads it when a task matches its description.

How do I install Refine Task in Codex?

Run `npx skills add ModelEngine-Group/fit-framework --skill refine-task -a codex`. Or copy the skill folder (.agents/skills/refine-task in ModelEngine-Group/fit-framework) into .agents/skills/refine-task in your project. Codex loads it when a task matches its description.

Can I use Refine Task in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ModelEngine-Group/fit-framework --skill refine-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/refine-task, .gemini/skills/refine-task, .github/skills/refine-task and .opencode/skills/refine-task in your project.

What does Refine Task need to run?

Going by SKILL.md and its folder, Refine Task needs the command-line tools its instructions call (mvn).

Does Refine Task access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Refine Task safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Refine Task use?

Refine Task is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Refine Task use?

About 134 tokens (SKILL.md is roughly 536 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Refine Task?

Skills that share tags, products or a category with Refine Task: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Refine Task?

ModelEngine-Group (a GitHub organization) maintains it in ModelEngine-Group/fit-framework, which has 2,117 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on March 13, 2026.

Source: ModelEngine-Group/fit-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.