Agent skill
mcp-servers-seanchatmangpt-ggen-2
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/mcp-servers-seanchatmangpt-ggen-2
SKILL.md
MCP Server Integration (80/20 Edition)
Auto-trigger: MCP, GitHub operations, filesystem access, external integrations
Overview
Model Context Protocol connects LLMs to external tools:
- GitHub: Issues, PRs, repositories
- Filesystem: Enhanced file operations
- Custom: SPARQL, validation, domain-specific
Configuration
{
"mcpServers": {
"github": {
"command": "mcp-server-github",
"env": {"GITHUB_TOKEN": "${GITHUB_TOKEN}"}
},
"filesystem": {
"command": "mcp-server-filesystem",
"args": ["/home/user/ggen"]
}
}
}
GitHub Operations
Create Issue
{"tool": "github_create_issue", "arguments": {
"title": "feat: Add feature X",
"body": "## Summary\n- Requirement 1\n- Requirement 2",
"labels": ["enhancement"]
}}
Create PR
{"tool": "github_create_pull_request", "arguments": {
"title": "feat: Implement X",
"body": "## Summary\n- Added X\n\n## Receipts\n[Receipt] cargo make test: ✓",
"head": "claude/feature-branch",
"base": "main"
}}
Core Principles
1. Receipt Collection
✅ [Receipt] PR #123 created: https://github.com/org/repo/pull/123
✅ [Receipt] File written: path.rs (sha256:abc...)
❌ "I created a PR" # No evidence
2. Path Validation
// Always validate before MCP filesystem calls
if !path.starts_with(allowed_base) { return Err(PathNotAllowed); }
3. Timeout & Rate Limiting
timeout(Duration::from_secs(5), mcp_call(tool, args)).await?
Integration with EPIC 9
Spec closure → Fan-out 10 agents → Each uses MCP for validation
→ Collision detection → Convergence → PR via GitHub MCP
Security
- Never hardcode tokens - use
${ENV_VAR} - Validate all paths - prevent traversal
- Rate limit - prevent API abuse
- Timeout all calls - default 5s
Common Workflows
Create Feature with MCP
/speckit-verify specs/042-feature
/bb80-parallel "[spec]"
mcp_call github_create_pull_request --title "feat: X" --body "$(cat receipts.md)"
Audit Repository
mcp_call github_search_code --query "unwrap language:rust path:src"
# Receipt: ✅ 0 violations in production
Best Practices
- Validate inputs before MCP calls
- Collect receipts for all operations
- Use spec-first (RDF → ggen sync → MCP)
- Apply timeouts (5s default)
- Never hardcode secrets
Constitutional: MCP = Validated inputs + Receipts + Timeouts + Spec-first
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?