Agent SkillsXiaomingX/mimofan › v4-best-practices

v4-best-practices

GitHub

针对DeepSeek V4系列模型思考模式的多步任务最佳实践,通过验证引用、启用子代理校验及精确路径标注,防止幻觉与执行错误。

crates/tui/assets/skills/v4-best-practices/SKILL.md XiaomingX/mimofan

Trigger Scenarios

使用deepseek-v4-pro或v4-flash进行多步骤规划 需要防止计划假设错误或引用失效的场景

Install

npx skills add XiaomingX/mimofan --skill v4-best-practices -g -y
More Options

Non-standard path

npx skills add https://github.com/XiaomingX/mimofan/tree/main/crates/tui/assets/skills/v4-best-practices -g -y

Use without installing

npx skills use XiaomingX/mimofan@v4-best-practices

指定 Agent (Claude Code)

npx skills add XiaomingX/mimofan --skill v4-best-practices -a claude-code -g -y

安装 repo 全部 skill

npx skills add XiaomingX/mimofan --all -g -y

预览 repo 内 skill

npx skills add XiaomingX/mimofan --list

SKILL.md

Frontmatter
{
    "name": "v4-best-practices",
    "description": "Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output."
}

V4 Best Practices

Rules for multi-step V4 thinking-mode workflows. Each rule prevents a specific, observable failure class.

1. Verify references before writing

Before referencing a file path, function, or type in code or plan output, call grep_files or read_file to confirm it exists in the workspace.

# Bad:  edit_file path="src/config/loader.rs" (assumed from memory)
# Good: grep_files pattern="pub fn load_config" → confirms src/config/mod.rs:42
#        then reference src/config/mod.rs:42

Failure avoided: edit_file errors on non-existent paths; LSP diagnostics on hallucinated symbols.

2. Spawn a verifier sub-agent before multi-file execution

Before executing a plan that touches 3+ files, spawn a deepseek-v4-flash sub-agent (thinking off) to read the target files and confirm path/symbol assumptions still hold.

agent type="verifier" model="deepseek-v4-flash"
  prompt: "Read these files and confirm: [list assumptions]. Report mismatches."

Failure avoided: multi-step edits fail partway because file structure changed since the plan was drafted.

3. Plan output must use confirmed path:line references

In plan-mode output, replace vague location pointers with path:line references drawn from a prior grep_files result.

# Bad:  "Update the retry logic in the client module"
# Good: "Update retry loop at crates/tui/src/client.rs:187"

Failure avoided: agent-mode execution cannot locate the intended edit target when plan directions are imprecise.

Version History

  • ccf85b9 Current 2026-08-08 08:00

Same Skill Collection

.workbuddy/skills/parallel-agent-lock-guard/SKILL.md
crates/tui/assets/skills/delegate/SKILL.md
crates/tui/assets/skills/documents/SKILL.md
crates/tui/assets/skills/feishu/SKILL.md
crates/tui/assets/skills/fleet-manager/SKILL.md
crates/tui/assets/skills/mcp-builder/SKILL.md
crates/tui/assets/skills/pdf/SKILL.md
crates/tui/assets/skills/plugin-creator/SKILL.md
crates/tui/assets/skills/presentations/SKILL.md
crates/tui/assets/skills/skill-creator/SKILL.md
crates/tui/assets/skills/skill-installer/SKILL.md
crates/tui/assets/skills/spreadsheets/SKILL.md

Metadata

Files
0
Version
ccf85b9
Hash
cca76c3e
Indexed
2026-08-08 08:00

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-09 08:44
浙ICP备14020137号-1 $Carte des visiteurs$