gh
FreeDiagnose GitHub CLI hiccups caused by Codex sandbox constraints; not a general GitHub workflow.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026
FreePublished on GitHub
forecast-experiment
Records hypotheses, evidence and decisions when proposing, running or evaluating forecast experiments, including backtests and feature or model comparisons. Excludes routine tests and unchanged forecast operation.
The English summary is being prepared. Showing the original description.
See how to installFiles included (1)
- SKILL.md2.0 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
Forecast experiments
Read the evaluation contract and point-in-time contract before designing a comparison.
Before execution
Save a proposal with the MLflow experiment record before launching the run. Record:
- The hypothesis and intended change.
- Motivating experiment IDs and prior results inspected; use none for the first baseline.
- The comparison baseline, fixed evaluation dates and metrics, and what result would support the hypothesis.
Use saved artifacts for the proposal and conclusion, and tags for related experiment/run IDs. Link execution runs for folds, variants and retries to the research record; distinguish these from experiments that motivated the idea. If proposing only, save the proposal without launching work.
During execution
Link the exact run manifests for inputs, code, environment, configuration and seeds; do not copy their contents into prose. Retain failed and interrupted attempts with their status. Preserve the original proposal; start a linked experiment when the hypothesis or evaluation protocol changes.
After execution
Append the results, evidence links, limitations, conclusion and next decision: keep, reject or investigate further. Compare against the baseline on matching evaluation rows. Record losses and failures as well as gains. If reviewing an existing run without a prior proposal, mark the rationale as retrospective; do not invent a pre-run hypothesis.
Identify evaluation periods whose results informed experiment choices as development data, not untouched holdouts. Keep experiment history in MLflow; put durable accepted design decisions in the wiki with experiment IDs. Follow this procedure manually when automation is absent.
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
More skills from this repository
goldfish
FreeReview a design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026
grill
FreeInterrogate the user before implementing a non-trivial or ambiguous ask, converging on shared intent. Use when the user says "grill me", when an ask admits multiple interpretations, or before any sizable piece of work whose intent isn't fully clear.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026
job-supervision
FreeLaunches and supervises long-running commands — solves, workflows, downloads, builds — detached with a log, PID and exit sentinel, then tells stuck from slow and kills verifiably. Use before running anything that may exceed a minute, for nohup or background launches, and when a run hangs, shows no output, or timed out.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026
llm-wiki
FreeBuild and maintain a persistent, LLM-maintained markdown wiki following Andrej Karpathy's LLM Wiki pattern — the agent incrementally compiles raw sources into an interlinked knowledge base instead of re-deriving answers from scratch. Use this whenever the user wants to ingest a source (an article, paper, transcript, chapter, meeting notes), file knowledge or conversation findings into the wiki, query the accumulated knowledge base, lint or health-check the wiki, or mentions "the wiki", "knowledge base", "ingest this", "file this", "what do we know about X", or accumulating notes on a topic over time — even if they don't say "LLM Wiki" explicitly.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026
mermaid
FreeGuides writing and editing Mermaid diagrams in GitHub-rendered Markdown so they remain readable across themes and preserve placeholder labels.
The English summary is being prepared. Showing the original description.
zoltanmaric/coppersushi69Updated Oct 14, 2026