tle-developer-flagos

Name: tle-developer-flagos
Availability: InStock
Author: FlagOS

Coordinate end-to-end TLE kernel development from intake to merge decision.

18|12|Updated Mar 3, 2026

Search Tags:#automation #workflow #validation #kernel #compiler #tle

Ready to run

npx skills add https://github.com/flagos-ai/skills --skill tle-developer-flagos

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tle-developer-flagos
Source: https://github.com/flagos-ai/skills/tree/main/skills/tle-developer-flagos
Command: npx skills add https://github.com/flagos-ai/skills --skill tle-developer-flagos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This self-contained orchestration skill coordinates end-to-end TLE kernel development work, from intake to merge decision, ensuring reproducible validation and auditable artifacts.

Core Features & Use Cases

End-to-end workflow: intake -> implementation -> validation -> artifacts -> merge decision for TLE work.
Guardrails and in-folder guidance: all detailed guidance lives inside the skill folder (references/), reducing external dependency risk.
Use Case: write/optimize TLE kernels, implement API/verifier/lowering/pipeline features, and debug TLE correctness and performance issues.

Quick Start

Trigger the tle-developer-flagos skill with a Goal/Non-goal/Acceptance input to drive end-to-end TLE work.

Frequently Asked Questions about tle-developer-flagos

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

FAQPage Schema

How do I orchestrate end-to-end TLE kernel development from intake to merge?▼

TLE kernel development is coordinated by triggering the workflow with a Goal, Non-goal, and Acceptance input to drive implementation, validation, and merge decisions. It coordinates the entire process from intake to final merge package generation.

What is the best way to debug GPU-based TLE kernel correctness and performance issues?▼

Debugging GPU-based TLE kernel issues requires an orchestration process that enforces input contracts and reproducible validation. It applies to debugging correctness and performance across GPU-based TLE workloads while generating structured Fix Summaries.

Can I use this workflow to implement API, verifier, lowering, and pipeline features for TLE?▼

Yes, you can use this workflow to implement API, verifier, lowering, and pipeline features for TLE. The orchestration applies to kernel optimization and feature work, enforcing guardrails and structured outputs across all tasks.

Do I need external dependencies to validate TLE compiler workloads?▼

No, you do not need external dependencies to validate TLE compiler workloads. All detailed guidance lives inside the skill folder references, reducing external dependency risk while enforcing reproducible validation and auditable artifacts.

What structured outputs are generated when optimizing TLE kernels?▼

Optimizing TLE kernels generates structured outputs including Fix Summaries, Lessons, and Merge Packages. These auditable artifacts ensure reproducible validation and structured outputs across all kernel optimization tasks.