Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Detailed development workflow with modular patterns for git, review, testing, and deployment.
.claude/skills/athola-development-workflow/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 38% | 0% |
This modular skill provides a detailed framework for software development workflows. It's designed as a hub that coordinates specialized modules for different aspects of development.
Get started quickly with this development workflow framework:
Quick Start: Set up repository structure and basic workflow in minutes
Progressive Learning: Start simple, add complexity as needed
Use Case-Based: Jump directly to what you need
This workflow illustrates a hub coordinating these specialized modules. Each link below resolves to a working example file in this skill's modules/ directory; copy the directory and adapt the contents when using this template for a real skill:
To use this development workflow:
Use git-workflow module for repository initialization and branching setup Verification: Run the command with --help flag to verify availability.
**Verification:** Run the command with --help flag to verify availability. git-workflow → code-review → testing-strategies → documentation-guidelines Verification: Run pytest -v to verify tests pass.
**Verification:** Run the command with --help flag to verify availability. deployment-procedures module handles CI/CD and production monitoring Verification: Run the command with --help flag to verify availability.
Start with the git-workflow module to establish repository structure, then progress through modules as your project develops.
Use individual modules to improve specific areas:
Guide new team members through the modules in order to establish consistent practices.
This modular approach provides several advantages over monolithic workflows:
Each module includes validation tools to validate best practices:
Use the quality-metrics tool to assess your workflow implementation:
bashquality-metrics --workflow development-workflow --modules all
Verification: Run the command with --help flag to verify availability.
This workflow is designed to be adaptable:
See the modules directory for detailed documentation on:
Command not found Ensure all dependencies are installed and in PATH
Permission errors Check file permissions and run with appropriate privileges
Unexpected behavior Enable verbose logging with --verbose flag
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 18,434 | 17,167 | -7% | 1 | 1 | 0% | 3,013 | 4,101 | +36% | 0 | 0 | — |
case-01 | fail→pass | 19,019 | 17,441 | -8% | 1 | 1 | 0% | 3,114 | 4,064 | +31% | 0 | 0 | — |
case-02 | fail→fail | 32,724 | 15,897 | -51% | 1 | 1 | 0% | 3,258 | 3,649 | +12% | 0 | 0 | — |
case-04 | fail→pass | 16,986 | 1,969 | -88% | 1 | 1 | 0% | 2,759 | 1,433 | -48% | 0 | 0 | — |
case-05 | pass→pass | 5,896 | 2,001 | -66% | 1 | 1 | 0% | 887 | 1,356 | +53% | 0 | 0 | — |
case-06 | pass→pass | 10,416 | 2,542 | -76% | 1 | 1 | 0% | 1,781 | 1,506 | -15% | 0 | 0 | — |
case-07 | fail→pass | 10,259 | 1,977 | -81% | 1 | 1 | 0% | 1,534 | 1,445 | -6% | 0 | 0 | — |
case-08 | fail→pass | 16,811 | 3,154 | -81% | 1 | 1 | 0% | 3,044 | 1,641 | -46% | 0 | 0 | — |
case-09 | fail→pass | 7,486 | 2,430 | -68% | 1 | 1 | 0% | 1,116 | 1,538 | +38% | 0 | 0 | — |
case-10 | fail→pass | 9,689 | 2,798 | -71% | 1 | 1 | 0% | 1,449 | 1,568 | +8% | 0 | 0 | — |
case-11 | fail→pass | 8,883 | 2,726 | -69% | 1 | 1 | 0% | 1,344 | 1,573 | +17% | 0 | 0 | — |
case-12 | fail→pass | 9,608 | 3,236 | -66% | 1 | 1 | 0% | 1,357 | 1,679 | +24% | 0 | 0 | — |
case-13 | fail→pass | 11,913 | 2,828 | -76% | 1 | 1 | 0% | 1,887 | 1,514 | -20% | 0 | 0 | — |
case-14 | fail→pass | 11,130 | 3,521 | -68% | 1 | 1 | 0% | 1,674 | 1,634 | -2% | 0 | 0 | — |
case-15 | fail→pass | 8,932 | 2,388 | -73% | 1 | 1 | 0% | 1,433 | 1,345 | -6% | 0 | 0 | — |
case-16 | pass→pass | 13,834 | 8,979 | -35% | 1 | 1 | 0% | 2,264 | 2,542 | +12% | 0 | 0 | — |
case-17 | pass→pass | 7,509 | 2,141 | -71% | 1 | 1 | 0% | 1,110 | 1,391 | +25% | 0 | 0 | — |
case-18 | fail→pass | 9,771 | 2,691 | -72% | 1 | 1 | 0% | 1,443 | 1,527 | +6% | 0 | 0 | — |
case-19 | fail→pass | 9,145 | 4,760 | -48% | 1 | 1 | 0% | 1,311 | 1,480 | +13% | 0 | 0 | — |
case-20 | pass→pass | 6,313 | 6,074 | -4% | 1 | 1 | 0% | 1,186 | 2,120 | +79% | 0 | 0 | — |
case-21 | pass→pass | 13,714 | 12,306 | -10% | 1 | 1 | 0% | 2,538 | 3,377 | +33% | 0 | 0 | — |
case-22 | pass→pass | 4,979 | 5,648 | +13% | 1 | 1 | 0% | 900 | 2,093 | +133% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.