added llm degradation report

README.md

@@ -71,18 +71,22 @@ claude
 | **Skill** | Creates output independently (skill) | [`weather-svg-creator`](.claude/skills/weather-svg-creator/SKILL.md) |
 
 ## DEVELOPMENT WORKFLOWS
-- [Cross-Model Claude Code + Codex](development-workflows/cross-model-workflow/cross-model-workflow.md) [![Implemented](!/tags/implemented.svg)](development-workflows/cross-model-workflow/cross-model-workflow.md)
+
+### 🔥 Hot
+- [Cross-Model (Claude Code + Codex) Workflow](development-workflows/cross-model-workflow/cross-model-workflow.md) [![Implemented](!/tags/implemented.svg)](development-workflows/cross-model-workflow/cross-model-workflow.md)
 - [RPI](development-workflows/rpi/rpi-workflow.md) [![Implemented](!/tags/implemented.svg)](development-workflows/rpi/rpi-workflow.md)
-- [Boris Feb26 workflow](https://x.com/bcherny/status/2017742741636321619)
-- [Ralph plugin with sandbox](https://www.youtube.com/watch?v=eAtvoGlpeRU) [![Implemented](!/tags/implemented.svg)](https://github.com/shanraisshan/novel-llm-26)
-- [Human Layer RPI - Research Plan Implement](https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/ace-fca.md)
-- [AgentOs - 2026 its overkill (Brian Casel)](https://www.youtube.com/watch?v=0hdFJA-ho3c)
-- [Github Speckit](https://github.com/github/spec-kit)
-- [GSD - Get Shit Done](https://github.com/glittercowboy/get-shit-done)
-- [OpenSpec OPSX](https://github.com/Fission-AI/OpenSpec/blob/main/docs/opsx.md)
-- [Superpower](https://github.com/obra/superpowers)
-- [Andrej Karpathy Workflow](https://github.com/forrestchang/andrej-karpathy-skills)
-- [Creator of Clawd Bot Workflow](https://www.youtube.com/watch?v=8lF7HmQ_RgY)
+- [Ralph Wiggum Loop](https://www.youtube.com/watch?v=eAtvoGlpeRU) [![Implemented](!/tags/implemented.svg)](https://github.com/shanraisshan/novel-llm-26)
+
+### Others
+- [Github Speckit](https://github.com/github/spec-kit) · ★ 74k
+- [obra/superpowers](https://github.com/obra/superpowers) · ★ 72k
+- [OpenSpec OPSX](https://github.com/Fission-AI/OpenSpec/blob/main/docs/opsx.md) · ★ 28k
+- [get-shit-done (GSD)](https://github.com/gsd-build/get-shit-done) · ★ 25k
+- [Andrej Karpathy (Founding Member, OpenAI) Workflow](https://github.com/forrestchang/andrej-karpathy-skills) · ★ 7k
+- [Brian Casel (Creator of Agent OS) - 2026 Workflow](https://github.com/buildermethods/agent-os) · ★ 4k - [it's overkill in 2026](https://www.youtube.com/watch?v=0hdFJA-ho3c)
+- [Human Layer RPI - Research Plan Implement](https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/ace-fca.md) · ★ 1.5k
+- [Boris Cherny (Creator of Claude Code) - Feb 2026 Workflow](https://x.com/bcherny/status/2017742741636321619)
+- [Peter Steinberger (Creator of OpenClaw) Workflow](https://youtu.be/8lF7HmQ_RgY?t=2582)
 
 ## TIPS AND TRICKS
 
@@ -182,3 +186,4 @@ claude
 | [Agent Memory Frontmatter](reports/claude-agent-memory.md) | Persistent memory scopes (`user`, `project`, `local`) for subagents — enabling agents to learn across sessions |
 | [Advanced Tool Use Patterns](reports/claude-advanced-tool-use.md) | Programmatic Tool Calling (PTC), Tool Search, and Tool Use Examples |
 | [Usage, Rate Limits & Extra Usage](reports/claude-usage-and-rate-limits.md) | Usage commands (`/usage`, `/extra-usage`, `/cost`), rate limits, and pay-as-you-go overflow billing |
+| [LLM Day-to-Day Degradation](reports/llm-day-to-day-degradation.md) | Why LLM performance varies day-to-day — infrastructure bugs, MoE routing variance, and psychology |