flagos-ai/flagtree/tle-developer
Claude Code and agent skill by flagos-ai/flagtree
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Self-contained orchestration skill for writing high-performance TLE kernels and shipping TLE feature changes with reproducible validation.
Install
npx vskill@latest install flagos-ai/flagtree/tle-developerSKILL.md
TLE Developer
Mission
Use this skill to execute TLE work end-to-end: intake -> implementation -> validation -> artifacts -> merge decision.
Scope
Use for:
- Writing or optimizing TLE kernels.
- Implementing TLE API/verifier/lowering/pipeline features.
- Debugging correctness, performance, and regression issues.
Self-Contained Policy
- Do not rely on documentation outside this skill folder.
- Put all detailed guidance in
references/. - Keep this file as orchestration-only (no duplicated deep details).
Required Input
Start every task with:
Mandatory Read Order
references/tle-sources.mdreferences/workflow-templates.md
Operating Contract
- Treat
references/tle-sources.mdas the technical source of truth for:
- quickstart,
- current TLE semantics contract,
- kernel patterns,
- feature-development file map,
- debug/perf procedures.
- Treat
references/workflow-templates.mdas the source of truth for:
- intake,
- validation matrix,
- performance record,
- fix summary,
- lessons entry,
- merge package.
Non-Negotiable Guardrails
- Never assume a specific python environment name.
- Never assume a fixed build script name.
- If native Triton files are modified for TLE-specific behavior, use compile-time guards like
#ifdef __TLE__/#endif. - Do not use comment marker blocks (
// begin flagtree tle/// end flagtree tle) as a policy mechanism. - Do not add
__TLE__guards insidethird_party/tleunless that subtree explicitly requires it.
Required Outputs Per Task
- Validation commands and outcomes.
- Fix Summary (when fixing bugs or regressions).
- Lessons Entry (for fixes and optimization work).
- Merge Decision Package (changed layers, risks, follow-ups).
Completion Checklist
- Acceptance criteria mapped to tests.
- Changes validated with reproducible commands.
- Artifacts filled from templates.
- Residual risks explicitly stated.
References
references/tle-sources.mdreferences/workflow-templates.md
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/tle-developer/SKILL.md
Popularity
- Repository stars
- 306
- Repository forks
- 108
- 7-day trend score
- 29
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/flagos-ai/flagtree/tle-developer)