hoavdc/CodexKit / skills/codexkit-mcp-onboarding
codexkit-mcp-onboarding
VerifiedEvaluate and phase MCP adoption with a bias toward the smallest set of integrations that materially improve engineering work.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.0 KB |
| agents/openai.yaml | config | 218 B |
SKILL.md
View on GitHub---
name: codexkit-mcp-onboarding
description: Evaluate and phase MCP adoption with a bias toward the smallest set of integrations that materially improve engineering work.
version: 1.0.0
category: runbook
---
# MCP Onboarding
Use this skill when deciding whether a repo or team should add MCP servers and how to roll them out safely.
## Workflow
1. Start from real engineering tasks, not tool hype.
2. Map each task to the minimum useful MCP capability.
3. Prefer read-only or low-risk integrations first.
4. Define who owns secrets, scopes, and monitoring.
5. Document why each server exists and when to remove it.
## Strong candidates
- docs and API lookup
- issue tracker triage
- repository metadata and pull request context
- observability lookups with strict access control
## Avoid
- installing every available MCP server
- shipping write access without auditability
- embedding team-specific secrets in public examples
## Quality Criteria
- [ ] Steps are executable in sequence without external context
- [ ] Decision points have clear if/then branching
- [ ] Rollback or abort procedures are documented for risky steps
- [ ] Expected duration or time-per-step is estimated
## Verification (4C)
| Check | Question |
|-------|----------|
| **Correctness** | Do the steps execute correctly in the order specified? |
| **Completeness** | Are decision points, error handling, and escalation paths all documented? |
| **Context-fit** | Could someone with the right access but no prior context complete this runbook? |
| **Consequence** | If Step N fails and the operator skips to Step N+1, what breaks? |
## Edge Cases
- **Steps require access the operator doesn't have** — Document exact access requirements upfront. Include escalation contact for emergency access.
- **Environment differs from documented state** — Add a pre-flight check as Step 0 to verify prerequisites before starting.
- **Runbook is triggered during off-hours** — Document who to contact and which steps can be safely deferred to business hours.
## Changelog
- v1.0.0 — Initial release
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |