Vibe Implement
idiotLeoLYJ/Daliu-Awesome-Skills
Vibe Coding 流水线的实现阶段(流水线终点,顺序 idea → interaction → architecture → design → prototype → implement)。当 interaction.md、architecture.md、design.md、prototypes/ 已就绪,用户说"开始实现""写代码""把设计落地""进入开发""implement /…
Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.
Install DeepSeek V4 Thinking-Mode Rules
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install codewhale-hq/Codewhale v4-best-practices --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .claude/skills/v4-best-practices && rm -rf skills-srcUse ~/.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/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .claude/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practicesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install codewhale-hq/Codewhale v4-best-practices --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .agents/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .agents/skills/v4-best-practices && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .agents/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install codewhale-hq/Codewhale v4-best-practices --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .cursor/skills/v4-best-practices && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .cursor/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/codewhale-hq/Codewhale.git --path crates/tui/assets/skills/v4-best-practices--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install codewhale-hq/Codewhale v4-best-practices --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .gemini/skills/v4-best-practices && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .gemini/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install codewhale-hq/Codewhale v4-best-practicesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .github/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .github/skills/v4-best-practices && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .github/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install codewhale-hq/Codewhale v4-best-practices --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/codewhale-hq/Codewhale.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/crates/tui/assets/skills/v4-best-practices .opencode/skills/v4-best-practices && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "v4-best-practices" agent skill from https://github.com/codewhale-hq/Codewhale/tree/main/crates/tui/assets/skills/v4-best-practices into .opencode/skills/v4-best-practices/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "v4-best-practices", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
v4-best-practices- GitHub stars
- 41k
- Token cost
- ~443 tokens
- SKILL.md length
- 145 words
- Files
- 1
- Skills in repo
- 63
- Repo updated
- First seen
- Licence
- MIT
At a glance
Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line.
- Works in 3 steps: Verify references before writing → Spawn a verifier sub-agent before… → Plan output must use confirmed path:line…
- Writing a multi-file plan with a DeepSeek V4 thinking model
- SKILL.md covers 1. Verify references before…, 2. Spawn a verifier sub-agent… and 3. Plan output must use…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The skill targets deepseek-v4-pro and deepseek-v4-flash on plan-driven tasks, and each rule names the failure it prevents. First, before citing a file path, function or type in code or plan output, confirm it exists with `grep_files` or `read_file`, which avoids edit errors on missing paths and hallucinated symbols.
Second, before executing a plan that touches three or more files, spawn a `deepseek-v4-flash` verifier subagent with thinking off to read the targets and confirm the assumptions still hold, so edits do not fail halfway through. Third, plan output should use confirmed `path:line` references taken from a prior search instead of vague pointers such as the client module, so agent-mode execution can find each edit target.
When your agent uses it
- Writing a multi-file plan with a DeepSeek V4 thinking model
- Checking plan assumptions before a multi-file edit begins
- Replacing vague location pointers in a plan with exact references
Example prompts
- “Plan the retry refactor across the client and config modules, with confirmed path and line references.”
- “Before editing these four files, have a verifier subagent confirm the symbols still exist.”
- “Verify the function names in this plan against the workspace before I approve it.”
Requirements
- A DeepSeek V4 model and file search and read tools in the agent
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 64bb073. 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
No scripts in the folder and no shell commands in SKILL.md.
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
DeepSeek V4 Thinking-Mode Rules loads about 443 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 145 words of instructions outside code blocks.
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 codewhale-hq/Codewhale at commit 64bb073, republished under its MIT licence (© codewhale-hq). 145 words, ~443 tokens.
Download SKILL.mdSave it as
.claude/skills/v4-best-practices/SKILL.md (or your agent's skills folder).- 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:42Failure 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.
© codewhale-hq, 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 crates/tui/assets/skills/v4-best-practices of codewhale-hq/Codewhale.
Open the folder on GitHubat commit 64bb073
Compare with similar skills
DeepSeek V4 Thinking-Mode Rules 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| DeepSeek V4 Thinking-Mode Rules this skillcodewhale-hq/Codewhale | 41k | — | ~443 | Automated safety check: Pass | MIT | |
| Vibe ImplementidiotLeoLYJ/Daliu-Awesome-Skills | 140 | — | ~2.7k | Automated safety check: Pass | None | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Inline Plan ExecutionjnMetaCode/superpowers-zh | 8.3k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Codex Deepseek Subagentoil-oil/codex-deepseek-subagent | 374 | — | ~673 | Automated safety check: Pass | MIT | |
| OMA Multi-Agent Orchestrationfirst-fluke/oh-my-agent | 1.3k | — | ~4.1k | Automated safety check: Pass | MIT |
Similar skills
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Inline Plan Execution
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
Codex Deepseek Subagent
oil-oil/codex-deepseek-subagent
配置和维护 Codex 桌面应用中的 DeepSeek 原生子 Agent，支持模型选择、路由验证、修复、停用和卸载。仅在用户要求配置或管理该集成时使用；普通 API 问题与配置后的日常编码任务不触发。
OMA Multi-Agent Orchestration
first-fluke/oh-my-agent
Decomposes a complex feature into tasks, dispatches parallel specialist agents with durable state, and supervises verification, QA review and retries.
Executing Plans
GanyuanRan/Aegis
A skill your agent uses when executing a written implementation plan across sessions or with review checkpoints.
More from codewhale-hq/Codewhale
All 63 skills in this repoCodewhale Dogfood Install
codewhale-hq/Codewhale
Proves a Codewhale change in the real product: a stamped release build, an atomic local install, fresh-shell verification and manual QA that automated gates cannot cover.
Codewhale Session Handoff
codewhale-hq/Codewhale
Writes a paste-ready handoff for the next agent session, opening with a state-check command block and separating done, suspected and blocked work.
Codewhale Landing Workflow
codewhale-hq/Codewhale
Decides how verified work should reach main, directly, in a worktree or on an integration branch, while keeping contributor credit and respecting merge gates.
Sub-Agent Delegation
codewhale-hq/Codewhale
Guides when and how to split multi-step coding, research or verification work into focused sub-agent runs while the parent keeps integration and final checks.
Codewhale Fleet Manager
codewhale-hq/Codewhale
Triages and manages Codewhale fleet runs and workers with typed commands, classifying failures and choosing a safe restart, resume or escalation.
GitHub Issue Bulk Assigner
codewhale-hq/Codewhale
Moves a list of GitHub issues into a milestone or assigns them to owners with the gh CLI, checking each one before and after the change.
Related
Works with
Categories
Questions about DeepSeek V4 Thinking-Mode Rules
What does DeepSeek V4 Thinking-Mode Rules do?
Three rules for multi-step work with DeepSeek V4 thinking models: verify references, use a verifier subagent before big edits, and write plans with exact path and line. The skill targets deepseek-v4-pro and deepseek-v4-flash on plan-driven tasks, and each rule names the failure it prevents. First, before citing a file path, function or type in code or plan output, confirm it exists with `grep_files` or `read_file`, which avoids edit errors on missing paths and hallucinated symbols.
When should I use DeepSeek V4 Thinking-Mode Rules?
DeepSeek V4 Thinking-Mode Rules fits situations like: writing a multi-file plan with a DeepSeek V4 thinking model; checking plan assumptions before a multi-file edit begins; replacing vague location pointers in a plan with exact references.
How do I install DeepSeek V4 Thinking-Mode Rules in Claude Code?
Run `npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a claude-code`. Or copy the skill folder (crates/tui/assets/skills/v4-best-practices in codewhale-hq/Codewhale) into .claude/skills/v4-best-practices in your project. Claude Code loads it when a task matches its description.
How do I install DeepSeek V4 Thinking-Mode Rules in Codex?
Run `npx skills add codewhale-hq/Codewhale --skill v4-best-practices -a codex`. Or copy the skill folder (crates/tui/assets/skills/v4-best-practices in codewhale-hq/Codewhale) into .agents/skills/v4-best-practices in your project. Codex loads it when a task matches its description.
Can I use DeepSeek V4 Thinking-Mode Rules 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 codewhale-hq/Codewhale --skill v4-best-practices -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/v4-best-practices, .gemini/skills/v4-best-practices, .github/skills/v4-best-practices and .opencode/skills/v4-best-practices in your project.
What does DeepSeek V4 Thinking-Mode Rules need to run?
SKILL.md names no scripts, command-line tools or credentials: DeepSeek V4 Thinking-Mode Rules is instructions for the agent only. Our summary lists: A DeepSeek V4 model and file search and read tools in the agent.
Does DeepSeek V4 Thinking-Mode Rules 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 DeepSeek V4 Thinking-Mode Rules 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 DeepSeek V4 Thinking-Mode Rules use?
DeepSeek V4 Thinking-Mode Rules 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 DeepSeek V4 Thinking-Mode Rules use?
About 443 tokens (SKILL.md is roughly 1.8k 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 DeepSeek V4 Thinking-Mode Rules?
Skills that share tags, products or a category with DeepSeek V4 Thinking-Mode Rules: Vibe Implement (idiotLeoLYJ/Daliu-Awesome-Skills, 140 stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Inline Plan Execution (jnMetaCode/superpowers-zh, 8.3k stars) and Codex Deepseek Subagent (oil-oil/codex-deepseek-subagent, 374 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains DeepSeek V4 Thinking-Mode Rules?
codewhale-hq (a GitHub organization) maintains it in codewhale-hq/Codewhale, which has 41,076 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 10, 2026.
Source: codewhale-hq/Codewhale on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.