Sota Report — Development skill for Claude Code
Write a SOTA-skills field report for this session — where the guidance failed, was absent, was wrong, or was right and did not fire.
How to install Sota Report
Installs to ~/.claude/skills/martinholovsky-sota-skills-sota-report/SKILL.md
mkdir -p ~/.claude/skills/martinholovsky-sota-skills-sota-report && curl -fsSL https://raw.githubusercontent.com/martinholovsky/SOTA-skills/HEAD/commands/sota-report.md -o ~/.claude/skills/martinholovsky-sota-skills-sota-report/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Sota Report does
description: Write a SOTA-skills field report for this session — where the guidance failed, was absent, was wrong, or was right and did not fire. Run it at the END of a working session, while the history is still in context.
Write a SOTA-skills field report for this session.
You have been applying the sota-* skills (or should have been). I maintain that library and have no telemetry: it learns nothing from use unless a session like this one says so. What I need is not a summary of what
Alternatives in Development
- Sglang Sota B200 Codex Goal Prompts — B200 Codex Goal prompts 767 ★
- Projectmem — Open-source coding agent memory 766 ★
- Cavemem — Frozen — cross-agent persistent memory for coding assistants 674 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Sota Close
End-of-session closure pass — retract what proved wrong and correct it everywhere it reached, hand off open it
Forensic
Investigate what went wrong in a failed build.
Gsd Forensics
Post-mortem investigation for failed GSD workflows — diagnoses what went wrong.
Tmux Claude Session Manager
Run many Claude Code sessions across your projects, each in its own tmux session — then list them, see which a
Preflight
24-tool MCP server that catches vague prompts before they cost 2-3x in wrong→fix cycles. 12-category scorecard
Auto Trigger
After any recon/probe step, route observed signals to the right tools and fire the auto-plan (Balanced policy)
Related Agents
Tracer
For a bug still unexplained after a fix attempt failed: "I already tried fixing this and it is still broken".
Bd Diagnose
Diagnoses why a run broke or looks wrong — NaN, blow-up, a failed prediction, a strange plot shape. Needs hypo
Lw Healer
Diagnoses and remediates failed background agents, stalled tasks and broken local tooling. Dispatched by the h