delivery
Delivers production-grade code changes while maintaining test coverage and repository standards.
Install
mkdir -p .claude/skills/delivery && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13618" && unzip -o skill.zip -d .claude/skills/delivery && rm skill.zipInstalls to .claude/skills/delivery
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Deliver features, fixes, and refactors in this repository while following the local stack, testing strategy, and repository conventions.Key capabilities
- →State the behavior being changed
- →Add or update a failing test first
- →Implement minimum change for test pass
- →Run repository's main validation path
- →Update or add E2E coverage for frontend changes
How it works
The skill delivers features, fixes, and refactors by following a TDD-first workflow: stating behavior, adding failing tests, implementing minimum changes, running validation, and updating E2E coverage. It reuses existing stack and conventions.
Inputs & outputs
When to use delivery
- →Implementing new features
- →Refactoring code
- →Fixing bugs
- →Ensuring test coverage
About this skill
Delivery
Use the repository’s existing stack and conventions unless the user explicitly asks to replace them.
Follow this workflow:
- State the behavior being changed.
- Add or update a failing test first.
- Implement the minimum change to make the test pass.
- Run the repository’s main validation path.
- If the change affects frontend behavior, update or add E2E coverage.
Rules:
- Reuse before creation.
- Extend shared abstractions safely.
- Do not broaden scope without explicit instruction.
- Use current official or primary documentation for non-trivial work.
- Document key files, changed behavior, and validation when reporting completion.
When not to use it
- →When the user explicitly asks to replace existing stack or conventions
- →When broadening scope without explicit instruction
Limitations
- →Requires adherence to the repository’s existing stack and conventions
- →Does not broaden scope without explicit instruction
- →Requires TDD-first workflow (failing test first)
How it compares
This skill enforces a structured, test-driven development workflow with validation and E2E coverage, ensuring adherence to repository conventions, unlike an unstructured or manual development process.
Compared to similar skills
delivery side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| delivery (this skill) | 0 | 2mo | No flags | Intermediate |
| code-assist | 1 | 5mo | No flags | Advanced |
| moonbit-agent-guide | 1 | 7mo | Review | Intermediate |
| ruby-pro | 1 | 4mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
code-assist
mikeyobrien
Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.
moonbit-agent-guide
loro-dev
Guide for writing, refactoring, and testing MoonBit projects. Use when working in MoonBit modules or packages, organizing MoonBit files, using moon tooling (build/check/test/doc/ide), or following MoonBit-specific layout, documentation, and testing conventions.
ruby-pro
sickn33
Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use PROACTIVELY for Ruby refactoring, optimization, or complex Ruby features.
agent-implementer-sparc-coder
ruvnet
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
intellij-mcp
navikt
Uses the IntelliJ MCP tools for various programming tasks. Use when the IntelliJ MCP is available and you are building, running tests, searching or refactoring.
apex
zuzu59
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.