Implement Feature Agent Skill
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/davepoon/buildwithclaude --skill implement-featureThe instruction itself
8 sections, as written by the authorImplement Feature
Implements a feature from its specification using the Forja (Dev) agent.
When to Use This Skill
- A feature spec has been approved and is ready for implementation
- You need architecture design, code, and tests for a defined feature
- Translating product requirements into working software
What This Skill Does
- Runs the SIGN IN checklist and verifies the spec handoff
- Designs architecture (creates ADR if needed)
- Defines interfaces/contracts, then implements in
src/ - Writes tests in
tests/(unit + integration) - Runs the Implementation Complete checklist (TIME OUT 1)
- Runs the Pre-Delivery checklist (TIME OUT 2)
- Prepares structured handoff to QA agent
- Runs the SIGN OUT checklist
How to Use
Basic Usage
/implement-feature webhook-event-system
With Spec Reference
/implement-feature docs/specs/webhook-event-system.md
Example
User: /implement-feature user-authentication
Output:
- Implementation in
src/with all acceptance criteria met - Tests in
tests/covering critical paths - ADR if significant architecture decisions were made
- Handoff notes for QA: files changed, how to test, known limitations
Tips
- Ensure the feature spec exists before running this skill
- The agent creates an ADR for any significant architecture decisions
- Two TIME OUT checkpoints ensure both correctness and delivery cleanliness
Other skills for the same job
different authors, same section of the catalogue
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
Use when working with error debugging multi agent review
Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.
Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.
Use when working with error debugging multi agent review
Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.
Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
How to use it
Take davepoon/implement-feature from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.