Implements a feature from its specification. Reads the spec, designs architecture, writes code, tests, and documentation. Use after a feature spec has been approved.
Scanned 5/28/2026
Install via CLI
openskills install ArtemioPadilla/agent-triforce---
name: implement-feature
description: >
Implements a feature from its specification. Reads the spec, designs architecture,
writes code, tests, and documentation. Use after a feature spec has been approved.
context: fork
agent: forja-dev
---
Implement the feature: $ARGUMENTS
Follow these steps:
**SIGN IN:**
- Run the SIGN IN checklist from your agent file
- Run the Receiving-from-Prometeo checklist to verify the spec handoff
- If significant architecture decisions are needed, create an ADR in `docs/adr/`
**DESIGN:**
1. Define interfaces/contracts first — program to interfaces, not implementations
2. Plan the layer structure: entities → use cases → adapters → frameworks (Clean Architecture)
3. Identify which business logic needs TDD (test-first) vs infrastructure glue (test-after acceptable)
**BUILD (TDD Cycle):**
4. For each piece of business logic:
a. **Red**: Write a failing test that describes the expected behavior (Arrange-Act-Assert)
b. **Green**: Write minimal code to make the test pass
c. **Refactor**: Clean up — extract methods, improve names, remove duplication
d. Verify each acceptance criterion from the spec has at least one test — if not, write one before proceeding
5. Implement infrastructure/adapters and write integration tests for critical paths
6. Scan for and remove any dead code you introduced or found
**⏸️ TIME OUT — Run Implementation Complete Checklist (DO-CONFIRM):**
7. Run through every item in the Implementation Complete checklist from your agent file
8. Fix any failures BEFORE proceeding
**REFACTORING PASS:**
9. Review all new code for code smells: long methods, feature envy, data clumps, primitive obsession
10. Apply Extract Method, Rename, Move as needed — leave code better than you found it
**⏸️ TIME OUT — Run Pre-Delivery Checklist (DO-CONFIRM):**
11. Run through every item in the Pre-Delivery checklist from your agent file
12. Fix any failures BEFORE proceeding
**SIGN OUT:**
13. Write the Handoff-to-Centinela using the communication checklist
14. Run the SIGN OUT checklist from your agent file
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.