Agent skill
context-loader
Load project context from .claude/ directory at the start of every task. This ensures Gemini CLI has the same coding rules, design decisions, and library constraints as Claude Code.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/context-loader
SKILL.md
Context Loader Skill for Gemini
Purpose
Load shared project context from .claude/ directory to ensure Gemini CLI operates with the same knowledge as Claude Code and Codex CLI.
When to Activate
ALWAYS - This skill should run at the beginning of research or analysis tasks.
Workflow
Step 1: Load Coding Rules
Read relevant files from .claude/rules/:
.claude/rules/
├── coding-principles.md # Simplicity, single responsibility, early return
├── dev-environment.md # uv, ruff, ty, pytest requirements
├── language.md # Think in English, respond in Japanese
├── security.md # Secrets, validation, SQLi/XSS prevention
└── testing.md # TDD, AAA pattern, 80% coverage
Step 2: Load Design Documentation
Read .claude/docs/DESIGN.md for:
- Architecture decisions
- Implementation patterns
- Library choices and constraints
Step 3: Check Library Documentation
If the task involves specific libraries, read relevant files from:
.claude/docs/libraries/
Step 4: Execute Research Task
With the loaded context, execute the requested research/analysis following:
- Project coding principles
- Existing design decisions
- Library constraints
Key Rules to Remember
- Simplicity first - Recommend readable solutions over complex
- Type hints required - Suggest typed code
- Use uv - Reference uv for package management
- Security - Highlight security considerations
Language Protocol
- Thinking/Reasoning: English
- Code examples: English (variables, functions, comments)
- Output: Structured markdown, suitable for documentation
Output Guidelines
When providing research results:
- Structure with clear headings
- Include code examples when relevant
- Cite sources from web search
- Note constraints relevant to this project
- Save comprehensive findings to
.claude/docs/research/
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?