0xlayerghost/solidity-agent-kit/claude-code-usage
Claude Code and agent skill by 0xlayerghost/solidity-agent-kit
- community
Checking that the SKILL.md file is still in the repository.
[AUTO-INVOKE] MUST be invoked at the START of each new coding session. Covers context management, task strategies, and Foundry-specific workflows. Trigger: beginning of any new conversation or coding session in a Solidity/Foundry project.
Install
npx vskill@latest install 0xlayerghost/solidity-agent-kit/claude-code-usageSKILL.md
The same SKILL.md was published earlier as 0xlayerghost/solidity-agent-kit/claude-code-usage.
Claude Code Best Practices
Language Rule
- Always respond in the same language the user is using. If the user asks in Chinese, respond in Chinese. If in English, respond in English.
Context Management Rules
| Rule | Why | |
|---|---|---|
| One window = one task | Mixing tasks pollutes context and degrades output quality | |
Use /clear over /compact | Clean start is more reliable than compressed context | |
/clear after complex tasks | Prevents old context from interfering with new work | |
| Copy key info to new windows | Don't rely on context persistence — paste critical details |
Task Execution Strategy
| Task Type | Recommended Approach | |
|---|---|---|
| Small bug fix (few lines) | Describe directly, let Claude modify in-place | |
| Large feature / refactor | /plan → review approach → /clear → paste plan → execute step by step | |
| Multi-file changes | Must use /plan workflow — never modify multiple files without a plan | |
| Code analysis / learning | Ask Claude to analyze directly — no plan needed | |
| Debugging | Provide error message + file path + relevant code — ask for root cause |
Prompt Techniques
Do This
- Give specific paths: "Modify the `_transfer` function in `src/MyToken.sol`"
- Give examples: "Input: 100 tokens, Expected: 95 tokens after 5% fee"
- Set boundaries: "Only modify this function, don't touch other code"
- Reference tests: "The fix should make `test_transfer_feeDeduction` pass"
Avoid This
- Vague references: "Modify that transfer function" — which one? Where?
- Open-ended requests without constraints: "Make it better"
- Multiple unrelated tasks in one message
Ambiguity Resolution — When Instructions Are Unclear
When a user instruction is vague, open-ended, or could be interpreted in multiple ways, do NOT guess and proceed. Proactively analyze the instruction and present all possible interpretations for the user to confirm before taking action.
Trigger Conditions
Activate ambiguity resolution when the instruction matches ANY of these patterns:
| Pattern | Example | |
|---|---|---|
| No target specified | "优化一下" — optimize what? | |
| Multiple possible scopes | "加个检查" — which function? what kind of check? | |
| Unclear boundary | "改一下权限" — add? remove? which role? | |
| Implicit context | "跟上次一样处理" — what was "last time"? | |
| Conflicting possibilities | "处理一下安全问题" — which vulnerability? what level? |
Analysis Dimensions
When ambiguity is detected, analyze across these dimensions:
- Scope — Which files / contracts / functions could be affected?
- Action — What operation is intended? (add / modify / delete / refactor / fix)
- Skill match — Which skills are relevant? Map each interpretation to applicable /skill
- Impact — What side effects could each interpretation have?
- Constraints — Are there implicit boundaries the user might assume?
Output Format
Present findings as a numbered list:
Example
Key Rules
| Rule | Why | |
|---|---|---|
| Never guess | Wrong guesses waste more time than one clarification round | |
| Show skill connections | Map each interpretation to relevant /skill so user knows what workflow triggers | |
| Respect confirmation | User says "就按第2个来" → proceed immediately, no further questions | |
| Context-aware skip | If conversation history already disambiguates, skip this process and act directly |
Meta-Prompting — When Things Go Wrong
When Claude's response misses the mark, don't just rephrase and retry. Use Meta-Prompting (reverse prompting) to let Claude diagnose the gap, then re-ask with complete context.
Four Prompt Types
| Type | When to Use | Template | |
|---|---|---|---|
| Diagnose | Answer was wrong or incomplete | "我刚才的提问中缺少了哪些关键信息,导致你没能一次性给出正确答案?请逐条列出。" | |
| Rewrite | You don't know how to improve the question | "请帮我重写刚才的问题,补全你认为缺失的上下文,使你能一次性给出正确答案。" | |
| Template | Prevent same mistake next time | "对于这类问题,我应该提供哪些信息你才能一次性解决?请给我一个提问模板。" | |
| Pre-check | Before Claude starts working | "在你开始写代码之前,列出你还需要我提供的所有信息。" |
Recommended Flow
Practical Example
Key Principle
Don't guess what you missed — let Claude tell you. One round of meta-prompting saves multiple rounds of trial and error.
Post-Correction Rule
- Every time after correcting a mistake, always end with: "Update your `CLAUDE.md` so you won't make the same mistake again." This ensures lessons learned are persisted into the project memory, preventing the same error from recurring in future sessions.
Git Operation Rules
- Always run
git diffbefore committing to review changes - Only commit — do not push unless explicitly requested
- Never push directly to main/master branch
- Stage specific files — never use
git add .in Solidity projects (risk of committing.env)
Foundry-Specific Workflow
| Action | Command | |
|---|---|---|
| Before committing | forge fmt && forge test | |
| After modifying contracts | forge build to check compilation | |
| Before PR | forge test --gas-report to check gas impact | |
| Debugging failed test | forge test --match-test <name> -vvvv for full trace |
Quick Command Reference
| Command | Purpose | |
|---|---|---|
/clear | Clear context, start fresh | |
/plan | Enter planning mode — analyze before modifying | |
/help | View all available commands | |
/compact | Compress context (prefer /clear instead) |
Project-level Configuration
Create .claude/instructions.md in the project root with project-specific rules. Claude automatically reads it at the start of every conversation — no manual loading needed.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/claude-code-usage/SKILL.md
Popularity
- Repository stars
- 4
- Repository forks
- 1
- 7-day trend score
- 3
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 16 Mar 2026, 8 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/0xlayerghost/solidity-agent-kit/claude-code-usage)