Skip to main content
skill CX Codex

technical-specification · secondsky — Claude Code skill: spec template

This skill walks the agent through a technical spec template: requirements, architecture, API design, rollout plan, tests and risks. Useful before a feature turns into code.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add secondsky/claude-skills --skill technical-specification -a claude-code
Open on GitHub

What technical-specification does

The skill hands the agent a fixed document structure. Inside is a spec template with metadata, an executive summary, goals and explicit non-goals, a functional requirements table with P0 and P1 priorities, non-functional requirements, API design, a database schema and a phased implementation plan.

There is also a testing strategy, a risk table with mitigations and success criteria as a checklist. A longer version lives in references/template.md: security threat analysis, monitoring, rollback plan, dependencies and open questions. The skill tells you to avoid vague requirements like "fast" or "scalable" and not to skip the non-functional section.

Before implementation it asks for stakeholder review. That is the point: the document pins down agreements while the design is still cheap to change.

What it helps with

  • write a spec for a feature before coding starts
  • lock down API contracts and the database schema
  • sort requirements into P0 and P1 priorities
  • plan rollback steps and a risk matrix
  • collect acceptance criteria into one checklist

Example prompts for the agent

  • write a technical specification for the new notification system
  • draft an ADR for moving to the new database schema
  • lay out non-functional requirements and risks for this service

How to install technical-specification

1Skills CLI (Vercel)

npx skills add secondsky/claude-skills --skill technical-specification -a claude-code

2Manually: put the files in place

~/.claude/skills/technical-specification/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/technical-specification/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about technical-specification

How do I install technical-specification in Claude?

Run npx skills add secondsky/claude-skills --skill technical-specification -a claude-code. The skill file then sits at ~/.claude/skills/technical-specification/SKILL.md.

What does technical-specification do?

It creates a technical specification from a template: requirements, architecture, API, implementation plan, testing strategy and risks with mitigations.

How is the full template different from the short one?

The short one gives the base structure, while references/template.md adds security threat analysis, monitoring, a rollback plan, dependencies and open questions.

Source text

SKILL.md · MIT
---
name: technical-specification
description: Creates detailed technical specifications for software projects covering requirements, architecture, APIs, and testing strategies. Use when planning features, documenting system design, or creating architecture decision records.
license: MIT
---

# Technical Specification

Create comprehensive technical specifications for software projects.

## Specification Template

```markdown
# Technical Specification: [Feature Name]

## Metadata
- **Status**: Draft | In Review | Approved
- **Author**: [Name]
- **Reviewers**: [Names]
- **Last Updated**: [Date]

## Executive Summary
[2-3 sentences: What problem does this solve? What's the proposed solution?]

## Background & Context
- Current pain points
- Why now?
- Related work

## Goals
### Primary Goals
1. [Measurable goal]

### Non-Goals
- [What this spec explicitly does NOT cover]

## Functional Requirements
| ID | Requirement | Priority |
|----|-------------|----------|
| FR-1 | [Description] | P0 |
| FR-2 | [Description] | P1 |

## Non-Functional Requirements
- **Performance**: Response time < 200ms
- **Scalability**: Support 10K concurrent users
- **Availability**: 99.9% uptime
- **Security**: [Requirements]

## Technical Design

### Architecture
[Diagram or description]

### API Design
```
POST /api/v1/resource
Request: { "field": "value" }
Response: { "id": "123", "field": "value" }
```

### Database Schema
```sql
CREATE TABLE resources (
  id UUID PRIMARY KEY,
  field VARCHAR(255)
);
```

## Implementation Plan
| Phase | Timeline | Deliverables |
|-------|----------|--------------|
| 1 | Week 1-2 | Core functionality |
| 2 | Week 3 | API endpoints |
| 3 | Week 4 | Testing & docs |

## Testing Strategy
- Unit tests: 80% coverage
- Integration tests: API endpoints
- E2E tests: Critical flows

## Risks & Mitigations
| Risk | Probability | Impact | Mitigation |
|------|-------------|--------|------------|
| [Risk] | Medium | High | [Plan] |

## Success Criteria
- [ ] All P0 requirements implemented
- [ ] Tests passing
- [ ] Performance targets met
- [ ] Documentation complete
```

## Full Template

See [references/template.md](references/template.md) for a comprehensive copy-paste template including:
- Complete metadata section
- Success metrics tables
- Architecture diagrams
- Detailed API design sections
- Security threat analysis
- Monitoring & observability
- Risk assessment matrix
- Rollout and rollback plans
- Dependencies tracking
- Open questions section

## Best Practices

**Do:**
- Include measurable acceptance criteria
- Add architecture diagrams
- Define explicit API contracts
- Quantify performance targets
- Document risks and mitigations
- Get stakeholder review before implementation
- Include security considerations
- Define rollback procedures

**Don't:**
- Use vague requirements ("fast", "scalable")
- Skip non-functional requirements
- Ignore security considerations
- Leave alternatives unexplored
- Omit testing strategy
- Forget dependencies and risks

© secondsky · MIT · secondsky/claude-skills

Similar skills

Everything for Writing and docs →

technical-specification by other authors comes first.

technical-specification aj-geddes Gives your agent a structure for technical specs, PRDs, ADRs and RFCs: requirements, architecture, acceptance criteria. Useful before you start coding a feature. CX Codex +1 804installs create-technical-spike official github Creates time-boxed technical spike documents for researching critical questions about architecture, APIs, or performance before development starts. 9,000installs project-workflow-analysis-blueprint-generator official github A GitHub Copilot skill that maps project architecture and documents end-to-end workflows. Use it when you need implementation blueprints for similar features. 9,366installs system-design official anthropics Walks you through designing services and systems: requirements, components, trade-offs. Useful when you need to decide how to split a service into parts. CX Codex +1 7,500installs sparc-implement ruvnet A skill that runs SPARC design phases: writes algorithm pseudocode, defines module boundaries and API contracts, then generates working code. Use it if you're developing with SPARC methodology and want to automate the architecture stage. CX Codex +1 734installs reviewing-technical-prose riekelt A skill for reviewing someone else's technical writing: it flags banned constructions, unsupported claims and structural defects, then runs a delivery checklist before a document ships. CX Codex +1 18,200installs technical-documentation wondelai A skill that audits and rewrites developer documentation against Google's style guide: READMEs, how-tos, API references, changelogs. Useful when your docs drift in tone and structure. CX Codex +1 1,400installs

From the same set89

bun-sqlite A skill that tells your agent how to write bun:sqlite code: queries, prepared statements, transactions and parameters. CX Codex +1 495installs architecture-patterns A skill that gives your agent backend architecture templates: Clean Architecture layers, ports and adapters, and Domain-Driven Design building blocks. CX Codex +1 493installs api-rate-limiting A skill that walks you through rate limiting an API with token bucket, sliding window and Redis-backed counters. Useful when you open an endpoint to the public or split access by plan. CX Codex +1 491installs design-system-creation A skill that walks the agent through building a design system: tokens, typography, components and their docs. Useful when UI standards need to be settled before code. CX Codex +1 481installs mobile-app-testing A skill for testing mobile apps: unit tests, UI automation, E2E and performance. Useful when you need to set up test infrastructure. CX Codex +1 467installs bun-test-basics A skill that feeds your agent the bun:test syntax: assertions, describe/it, skip/only/each modifiers and how to run the suite. CX Codex +1 458installs threejs A skill with reference files and working examples for Three.js: scenes, materials, lighting, shaders, GLTF loading. Useful when you build 3D in the browser. CX Codex +1 460installs ml-model-training A skill that walks the agent through the full model training cycle: data prep, splitting, training and evaluation. Useful when you need a classifier or regressor without skipping steps. CX Codex +1 457installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor