Agent skill
writing-tech-plans
Architectural planning and ADR creation. Use when evaluating feasibility, making technology choices, or defining system integration.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/writing-tech-plans
SKILL.md
Technical Planning
Plan architecture and document decisions. Default to creating ADRs for significant decisions.
Architectural Focus
- System impact - What existing systems does this touch?
- Boundaries - Where does this feature start and end?
- Integration - How does it connect to existing components?
- Data flow - How does information move through the system?
- Trade-offs - What are we gaining and giving up?
ADRs
Create an ADR when choosing between technologies, selecting authentication approaches, introducing new patterns, or making trade-offs with long-term implications.
ADR Format
# ADR-{NNN}: {Decision Title}
**Status**: Proposed | Accepted | Rejected | Superseded
**Date**: YYYY-MM-DD
## Context
[Why is this decision needed?]
## Decision
[Clear statement of what was decided]
## Alternatives Considered
### {Alternative 1}
- **Pros**: ...
- **Cons**: ...
- **Why rejected**: ...
## Consequences
### Positive
- [Benefit]
### Negative
- [Trade-off]
- **Mitigation**: [How handled]
Scan docs/adr/ for existing ADRs and increment the highest number.
Technical Overview
Location: specs/YYYY-MM-DD-feature-name/technical-details.md
Structure
# Technical Overview: {Feature Name}
## Summary
[2-3 sentences]
## Architecture
### System Context
[How this fits into the broader system]
### Component Boundaries
[Components involved and responsibilities]
### Data Flow
[How data moves through the system]
## Integration Points
- **{System A}**: [How it integrates]
## Decisions
| Decision | ADR |
|----------|-----|
| [Choice] | [ADR-NNN](../docs/adr/NNNN-title.md) |
## Security Considerations
[Auth, authorization, data protection]
## Risks and Constraints
- **{Risk}**: [Description and mitigation]
## Open Questions
- [Unresolved questions]
Exclusions
Do not include: specific file paths, implementation order, code snippets, line-by-line details, time estimates, or timeline references.
Guidelines
Confirm feasibility before designing. Document decisions as ADRs. Trust implementers with the how. Think in systems and ripple effects. Address security by default.
Templates
templates/technical-details.md- Technical overviewtemplates/adr-template.md- ADR templatereferences/adr-guide.md- ADR guidelines
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
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.
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.
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.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
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?