samwang0723/write-tech-spec
templates/skills/write-tech-spec/SKILL.md
Generate a technical specification document using the DDD template in template.md. Use when the user says 'write tech spec', 'create tech spec', 'technical specification', or needs a structured design document for a new feature or major change covering architecture, domain models, APIs, data design, security, and operations.
$ install --global
skillsauthnpx skillsauth add samwang0723/claudecode-setup write-tech-specInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 17, 2026, 7:46 AM36.4s2 files scanned
SKILL.md
- name:
- write-tech-spec
- description:
- Generate a technical specification document using the DDD template in template.md. Use when the user says 'write tech spec', 'create tech spec', 'technical specification', or needs a structured design document for a new feature or major change covering architecture, domain models, APIs, data design, security, and operations.
Write Tech Spec
Generate a complete technical specification document following the DDD (Domain Driven Design) template at template.md.
Workflow
Step 1: Gather Context
Ask the user for these essentials before generating:
- Feature name and one-line description
- New feature or modification to an existing service?
- Owning team/pillar and key stakeholders/reviewers
- Related links — PRD, Figma, Slack threads, existing docs
Step 2: Technical Discovery
For each relevant template section, ask targeted questions:
| Section | Key Questions | |---------|--------------| | Architecture | What services are involved? Upstream/downstream dependencies? | | Domain | New domain models or entities? State machines needed? | | Data | Database schema changes? PII considerations? Retention policy? | | APIs | New endpoints? Error code patterns? Rate limiting needs? | | Security | External exposure? Auth changes? Threat model required? | | Operations | Feature flags? Rollout strategy? Monitoring metrics? |
Skip sections the user confirms are not applicable — mark them "N/A" in the output.
Step 3: Generate the Spec
- Read
template.mdfrom this skill directory for the full document structure - Fill in each section with gathered information
- Mark gaps with
[TODO: description]placeholders - Mark diagram locations with
[DIAGRAM: description]placeholders - Use mermaid code blocks for architecture and sequence diagrams where possible
Step 4: Output and Review
- Save the completed spec to
.claude/tasks/{slug}/tech-spec.md - Present a summary of completed vs TODO sections for user review
- Optionally upload to Confluence using
mcp__atlassian__confluence_create_page
Template Reference
The full template structure lives in template.md (bundled with this skill). Key sections:
- TL;DR Change Summary — 2-3 sentences: What? Why? Impact?
- Background — Objective, Goals, Non-Goals
- Architecture Overview — Component diagram, service relationships
- Domain Design — Use cases, fund flows, domain models, state machines, configuration
- Data Design — DB schemas, storage, privacy, retention
- APIs Design — Model definitions, endpoints, sequence diagrams, error codes (
{App}-{4-digit-code}) - Logging Design — Log structure with PII masking
- Security Design — Auth, XSS/CSRF/CORS/SQLi prevention, key management
- Compatibility Design — Backward compatibility, platform support
- Operations — Capacity, rollout plan, monitoring, fallback, security assessment, testing, infrastructure
Operations Sections Are Required
Every tech spec must include rollout plan, monitoring metrics/alerts, fallback plan, and security assessment — these are non-negotiable for production readiness.
Focus: $ARGUMENTS
Related Skills
samwang0723/write-prd
testing
VerifiedTrustedCommunity
Write a Product Requirements Document (PRD) using the standard TMAB template with stakeholders, user stories (Given-When-Then), success metrics, and A/B testing plans. Use when the user asks to write a PRD, create product requirements, document a feature spec, or plan a new product feature.
1SKILL.mdUpdated Apr 17, 2026
samwang0723/team-stop
data-ai
VerifiedTrustedCommunity
Clean up an agent team. Removes team resources, optionally cleans worktrees and branches. Use after team work is complete and merged. Use when told to "stop team", "cleanup team", "disband team".
1SKILL.mdUpdated Apr 17, 2026
samwang0723/team-status
testing
VerifiedTrustedCommunity
Check progress of an active agent team. Shows member status, completed tasks, pending work, and any messages. Use when asked "team status", "how's the team", "check team progress", "team update".
1SKILL.mdUpdated Apr 17, 2026
samwang0723/team-start
development
VerifiedTrustedCommunity
Spawn an agent team with multiple parallel Claude instances in tmux panes. Each teammate is a separate session with its own context window. Creates git worktrees and markdown state tracking alongside JSON tasks. Supports: --agents (comma-separated), --members N, --devs N. Use when told to "team up", "parallel team", "spawn a team", or "standby".
1SKILL.mdUpdated Apr 17, 2026