Tooluck logoTooluck
SKILL.md

claude-code-guide

Agent skill fromdavila7/claude-code-templates

Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.

How to install claude-code-guide

install claude-code-guide
# install the claude-code-templates pack with the skills CLI
npx skills add davila7/claude-code-templates

# or add only this skill to Claude Code: copy the folder

cli-tool/components/skills/ai-research/claude-code-guide/

# into

~/.claude/skills/claude-code-guide/ (all projects)

.claude/skills/claude-code-guide/ (one project)

cli-tool/components/skills/ai-research/claude-code-guide/SKILL.md

MITFull file
1# Claude Code Guide
2
3## Purpose
4
5To provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.
6
7## Configuration (`CLAUDE.md`)
8
9When starting a new project, create a `CLAUDE.md` file in the root directory to guide the agent.
10
11### Template (General)
12
13```markdown
14# Project Guidelines
15
16## Commands
17
18- Run app: `npm run dev`
19- Test: `npm test`
20- Build: `npm run build`
21
22## Code Style
23
24- Use TypeScript for all new code.
25- Functional components with Hooks for React.
26- Tailwind CSS for styling.
27- Early returns for error handling.
28
29## Workflow
30
31- Read `README.md` first to understand project context.
32- Before editing, read the file content.
33- After editing, run tests to verify.
34```
35
36## Advanced Features
37
38### Thinking Keywords
39
40Use these keywords in your prompts to trigger deeper reasoning from the agent:
41
42- "Think step-by-step"
43- "Analyze the root cause"
44- "Plan before executing"
45- "Verify your assumptions"
46
47### Debugging
48
49If the agent is stuck or behaving unexpectedly:
50
511. **Clear Context**: Start a new session or ask the agent to "forget previous instructions" if confused.
522. **Explicit Instructions**: Be extremely specific about paths, filenames, and desired outcomes.
533. **Logs**: Ask the agent to "check the logs" or "run the command with verbose output".
54
55## Best Practices
56…

Excerpt shown under the repository's MIT license.

More skills in claude-code-templates

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates