rfc-specification
RFC (Request for Comments) specification writing with objective technical analysis. Use when creating technical specifications, design documents, or architecture proposals that require structured evaluation of options and trade-offs.
Best use case
rfc-specification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
RFC (Request for Comments) specification writing with objective technical analysis. Use when creating technical specifications, design documents, or architecture proposals that require structured evaluation of options and trade-offs.
Teams using rfc-specification should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/rfc-specification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How rfc-specification Compares
| Feature / Agent | rfc-specification | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
RFC (Request for Comments) specification writing with objective technical analysis. Use when creating technical specifications, design documents, or architecture proposals that require structured evaluation of options and trade-offs.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# RFC Specification Writing Skill
This skill automatically activates when writing technical specifications, design documents, or architecture proposals that require structured evaluation and stakeholder review.
## When This Skill Activates
- Creating a new technical RFC or design document
- Proposing architectural changes or new systems
- Evaluating technical options objectively
- Documenting technical decisions with rationale
- Writing system design specifications
## Core Principles
### Objective Technical Analysis
RFCs must maintain strict neutrality when evaluating options:
1. **Evidence-Based Evaluation**
- Support claims with data, benchmarks, or documented experience
- Avoid subjective language ("better", "best", "obvious choice")
- Present measurable criteria for comparison
2. **Balanced Trade-off Analysis**
- Every option has advantages AND disadvantages
- Document both explicitly for each alternative
- Avoid dismissing options without clear justification
3. **Separation of Facts and Opinions**
- Clearly label assumptions vs verified facts
- Cite sources for technical claims
- Distinguish between team preferences and technical constraints
4. **Stakeholder Neutrality**
- Present options without advocating for a predetermined choice
- Let evaluation criteria drive the recommendation
- Document dissenting opinions fairly
## RFC Document Structure
### Required Sections
1. **Header Metadata**
```yaml
---
rfc_id: RFC-XXXX
title: [Descriptive Title]
status: DRAFT | REVIEW | APPROVED | IN_PROGRESS | COMPLETED | SUPERSEDED
author: [Name]
reviewers: [List of reviewers with status]
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
decision_date: YYYY-MM-DD (when approved)
---
```
2. **Overview** (1-2 paragraphs)
- What this RFC proposes
- Why it matters now
- Expected outcome
3. **Background & Context**
- Current state of the system
- Historical context if relevant
- Glossary of terms
- Links to related RFCs or documentation
4. **Problem Statement**
- Specific problem being addressed
- Evidence of the problem (metrics, incidents, user feedback)
- Impact of not solving (cost, risk, opportunity loss)
5. **Goals & Non-Goals**
- Explicit scope boundaries
- What success looks like
- What this RFC deliberately does NOT address
6. **Evaluation Criteria**
- Measurable criteria for comparing options
- Weight or priority of each criterion
- Minimum thresholds where applicable
7. **Options Analysis**
For each option (minimum 2):
```markdown
### Option N: [Name]
**Description**: [What this option entails]
**Advantages**:
- [Pro 1]
- [Pro 2]
**Disadvantages**:
- [Con 1]
- [Con 2]
**Evaluation Against Criteria**:
| Criterion | Score/Rating | Notes |
|-----------|--------------|-------|
| ... | ... | ... |
**Effort Estimate**: [Complexity and resources required]
**Risk Assessment**: [Potential risks and mitigations]
```
8. **Recommendation**
- Recommended option with justification
- How it scores against criteria
- Acknowledged trade-offs being accepted
9. **Technical Design** (for approved RFCs)
- Architecture diagrams
- API specifications
- Data models
- Security considerations
10. **Implementation Plan**
- Phases and milestones
- Dependencies
- Rollback strategy
11. **Open Questions**
- Unresolved technical questions
- Areas needing further investigation
- Pending stakeholder input
12. **Decision Record**
- Final decision made
- Date and approvers
- Key discussion points
- Conditions or constraints on approval
## RFC Lifecycle
```
DRAFT → REVIEW → APPROVED → IN_PROGRESS → COMPLETED
↓
SUPERSEDED (if replaced by newer RFC)
```
### Status Definitions
| Status | Description |
|--------|-------------|
| DRAFT | Initial writing, not ready for review |
| REVIEW | Open for stakeholder feedback |
| APPROVED | Decision made, ready for implementation |
| IN_PROGRESS | Implementation underway |
| COMPLETED | Implementation finished |
| SUPERSEDED | Replaced by newer RFC (link to new RFC) |
## Evaluation Criteria Framework
Use these standard criteria categories (adapt as needed):
### Technical Criteria
- **Performance**: Latency, throughput, resource usage
- **Scalability**: Horizontal/vertical scaling, bottlenecks
- **Reliability**: Fault tolerance, recovery, availability
- **Security**: Attack surface, data protection, compliance
- **Maintainability**: Code complexity, debugging, updates
### Operational Criteria
- **Operability**: Monitoring, alerting, incident response
- **Deployment**: CI/CD integration, rollback capability
- **Documentation**: Learning curve, knowledge transfer
### Business Criteria
- **Time to Implement**: Development effort, dependencies
- **Cost**: Infrastructure, licensing, maintenance
- **Risk**: Technical risk, organizational risk
## Neutral Language Guidelines
### Avoid
- "Obviously the best choice"
- "Everyone agrees that..."
- "This is clearly superior"
- "The only sensible option"
- Dismissing alternatives as "not worth considering"
### Use Instead
- "Based on criteria X, Option A scores higher because..."
- "Option B requires consideration of trade-off Y"
- "The data suggests that..."
- "Stakeholder input indicates a preference for..."
- "Given constraints A and B, Option C is recommended"
## Quality Checklist
Before marking RFC as REVIEW:
- [ ] All required sections are complete
- [ ] At least 2 alternatives are analyzed
- [ ] Evaluation criteria are explicit and measurable
- [ ] Trade-offs are documented for each option
- [ ] Language is objective and evidence-based
- [ ] Technical diagrams are included where helpful
- [ ] Open questions are clearly listed
- [ ] Implementation plan is realistic
## Integration with CTO Architect Workflow
When the CTO Architect agent creates technical specifications:
1. **Use this skill** for any significant technical decision
2. **Follow the template** in `references/rfc-template.md`
3. **Ensure neutral evaluation** of all options
4. **Link to related PRDs** when applicable
5. **Request review** from appropriate technical stakeholders
## File Naming Convention
- RFC documents: `RFC-XXXX-<short-description>.md`
- Example: `RFC-0042-api-gateway-selection.md`
## Directory Structure
```
rfcs/
├── draft/ # Work in progress
├── review/ # Under stakeholder review
├── approved/ # Approved, awaiting or in implementation
├── completed/ # Implementation finished
└── archive/ # Superseded or abandoned
└── YYYY/
```
## References
- Template: `./references/rfc-template.md`
- Evaluation Matrix: `./references/evaluation-matrix.md`Related Skills
technical-specification
Technical specification writing for implementation details. Use when documenting how to build a solution (post-decision), API contracts, schemas, and system design. Complements RFC skill which handles decision-making.
zod
Zod schema validation patterns and type inference. Auto-loads when validating schemas, parsing data, validating forms, checking types at runtime, or using z.object/z.string/z.infer in TypeScript.
typescript-import-style
Merge-friendly import formatting (one-per-line, alphabetical). Auto-loads when writing TypeScript/JavaScript imports to minimize merge conflicts in parallel development. Enforces consistent grouping and sorting.
setup-mcp-auth
Configure authentication for an existing FastMCP server
fastmcp
FastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/prompts, implementing authentication, configuring transports, or working with FastMCP in TypeScript.
add-mcp-tool
Add a new tool to an existing FastMCP server with guided configuration
add-mcp-resource
Add a new resource or resource template to an existing FastMCP server
plan-with-team
Validate plan file ownership
privacy-compliance
GDPR, CCPA, and privacy compliance guidance for data protection. Use when handling personal data, implementing consent management, or ensuring regulatory compliance across jurisdictions.
oauth
OAuth 2.0 and OpenID Connect implementation patterns. Use when implementing authentication, authorization flows, or integrating with OAuth providers like Google, GitHub, or custom identity providers.
mcp-security
Use when securing MCP servers, preventing prompt injection, implementing authorization, validating user input, or building secure multi-agent pipelines. Provides 5-layer defense architecture patterns.
rag-cag-security
Security patterns for RAG and CAG systems with multi-tenant isolation. Use when building retrieval-augmented or cache-augmented generation systems that require tenant isolation, access control, and secure data handling.