Skip to content

feat: improve tdd skill score from 83% to 93% #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
yogesh-tessl wants to merge 1 commit into
base: main
Choose a base branch
from
+5 −4
Open

feat: improve tdd skill score from 83% to 93% #11

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions plugins/praxis/skills/tdd/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,21 +1,22 @@
---
name: tdd
description: Boundary-focused TDD workflow enforcing L3/L4 altitude testing, property-based tests, and red-green-refactor phase separation. Use when starting a new module or feature with test-first discipline.
description: "Interactive test-driven development workflow that guides writing one test at a time through red-green-refactor cycles with ZOMBIES test discovery, enforces boundary-level and integration testing with property-based tests, and tracks session progress in a structured log. Use when starting a new module or feature with test-first discipline, writing unit tests, doing TDD, or when the user says 'write tests first', 'start with tests', or 'red green refactor'. Do NOT use for automated multi-phase plan execution (use implement instead)."
triggers:
- "TDD workflow"
- "test driven development"
- "red green refactor"
- "write tests first"
- "test-first implementation"
- "unit tests for this module"
- "start with tests"
- "TDD this feature"
allowed-tools: Read Glob Write Bash
---

# Test-Driven Development Process

> **For automated multi-phase execution** of a pre-planned feature, use `/implement` instead. This skill is for interactive, human-in-the-loop TDD on individual modules where you want to stay in the RED → GREEN → REFACTOR loop yourself. Implement's `agent-test` and `agent-impl` agents follow the same RED → GREEN discipline and Core Rules defined here.

TDD is a design technique that uses tests as a tool. Design emerges from usage, not speculation. Short feedback loops let you course-correct immediately. The resulting architecture is testable by design, not retrofitted. We are not trying to rush towards a feature completion, it's important that the code is correct and well-designed, it's crucial to be thorough and only add what tests demand.

When starting, announce: "Using TDD skill in mode: [auto|human]"

MODE (user specifies, default: auto)
Expand All @@ -39,7 +40,7 @@ MODE (user specifies, default: auto)

## Boundary Testing (Layered Architectures)

For layered architectures, see [boundary-testing.md](references/boundary-testing.md) for L3/L4 altitude testing, property-based tests with fast-check, behavioral assertions, HTTP contract tests, and architecture-specific anti-patterns.
For layered architectures, see [boundary-testing.md](references/boundary-testing.md) for boundary and integration-level testing (L3/L4 altitude), property-based tests with fast-check, behavioral assertions, HTTP contract tests, and architecture-specific anti-patterns.

## Session Log

Expand Down