skills.rest
krzemienski
krzemienskiCOMMUNITY
Explore all skills by this author →
Website𝕏@nkrzemienskiGitHub

forge-team

Coordinate parallel platform validators with dependency-based blocking and wave execution.

2|Updated Apr 8, 2026
Search Tags:#validation#multi-agent#orchestration#evidence#end-to-end#dependency-graph#wave-execution
One-click install
npx skills add https://github.com/krzemienski/validationforge --skill forge-team
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: forge-team
Source: https://github.com/krzemienski/validationforge/tree/main/skill-audit-workspace/forge-team/skill-snapshot
Command: npx skills add https://github.com/krzemienski/validationforge --skill forge-team

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinates multi-platform validators to prevent wasted work and ensure reliable, evidence-backed validation by enforcing upstream-first execution and blocking dependent platforms when necessary. It eliminates ad-hoc parallel runs that produce incomplete or conflicting evidence and centralizes verdict synthesis so teams can act on a single source of truth.

Core Features & Use Cases

  • Wave-based dependency execution: Build and execute wave plans so DB and design validators run before API, and API before Web/iOS as required.
  • Exclusive evidence ownership: Each validator writes only to its e2e-evidence/{platform}/ directory to avoid contamination and ensure traceable artifacts.
  • Blocking and reporting: Automatically BLOCK dependent platforms when upstream validators FAIL and write BLOCKED reports with root-cause pointers.
  • Parallel spawn with orchestration: Spawn platform agents in parallel within waves, wait for completion, track states in .vf/state/wave-plan.json, and synthesize a final e2e-evidence/report.md.
  • Use Case: Run pre-release fullstack validation across DB, API, Web, and iOS, capture all evidence, and produce a single actionable report for the release owner.

Quick Start

Run the forge-team skill to detect platforms, execute validators in dependency-aware waves, collect per-platform evidence into e2e-evidence/, and produce the unified report.

Frequently Asked Questions about forge-team

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run fullstack validation across multiple platforms like DB, API, Web, and iOS?▼

Fullstack validation across DB, API, Web, and iOS is coordinated by detecting platforms and spawning parallel validators in dependency-aware waves, collecting per-platform evidence into e2e-evidence/ directories and synthesizing a unified report.

How does wave-based execution manage dependencies for end-to-end validation?▼

Wave-based execution manages end-to-end validation by building dependency graphs so upstream validators run first, blocking dependent platforms on failures and tracking states in .vf/state/wave-plan.json before spawning the next wave.

What happens when an upstream validator fails during multi-agent orchestration?▼

When an upstream validator fails during multi-agent orchestration, the system automatically BLOCKs dependent downstream platforms and write BLOCKED reports with root-cause pointers to prevent wasted work and incomplete evidence.

Do I need multiple platforms to use wave-based dependency execution?▼

Wave-based dependency execution applies to projects with two or more detected platforms, coordinating parallel platform validators to manage dependency-based blocking and capture exclusive per-platform evidence.

How is validation evidence organized to avoid contamination between platform agents?▼

Validation evidence is organized using exclusive evidence ownership, where each platform validator writes only to its designated e2e-evidence/{platform}/ directory to ensure traceable artifacts and avoid contamination.

What is the best way to synthesize a single actionable report from parallel platform validators?▼

The best way to synthesize a single actionable report from parallel platform validators is to wait for wave completion and aggregate all exclusive per-platform evidence into a unified e2e-evidence/report.md verdict.

Related Skills

Explore More Software Engineering Skills→
krzemienskikrzemienski
2

wave-orchestration

Transforms sequential multi-agent execution into parallel waves with dependency analysis and synthesis checkpoints.

Community
Advanced
krzemienskikrzemienski
2

consensus-synthesis

Synthesize per-validator PASS/FAIL reports into consensus verdicts with confidence scoring.

Community
Advanced
ev3rlitev3rlit

gsd-execute-phase

Execute phase plans via dependency-aware wave-based parallel subagent orchestration.

Community
Advanced
tmalcolm-0607tmalcolm-0607

mad-parallel

Orchestrate wave-based parallel feature implementation across isolated git worktrees.

Community
Advanced