create-retrospective

create-retrospective is a Model training & evaluation skill for AI agents, published by vlasenkoalexey in the tpu_performance_autoresearch_wiki repository on GitHub. Skillspace rates create-retrospective D (61/100) and it passed the safety scan; the rating is based on static analysis only.

Generate a comprehensive retrospective for a `(model, lane)` pair that maps the explored search space, identifies coverage gaps from the topic taxonomy (`model-optimization-index.md`) and Pallas kernel catalog, surfaces premature-exhaustion signals (single-axis-probe vs kernel-port imbalance, frontier-stuck duration), and proposes ranked next directions. **Reads ALL experiment pages in the lane** — not a sample — because the retrospective's value depends on comprehensive coverage of what's been tried. Includes a lightweight cross-lane brief by default. Manually callable; intended to be invoked when the agent reports "out of ideas" or hits the stuck-frontier signature, BEFORE concluding the lane is exhausted. Output is a dated analysis page at `wiki/analyses/<YYYY-MM-DD>-<model>-<lane>-retrospective.md`; the skill does NOT act on its own recommendations — it produces analysis, the loop / `/formulate-hypothesis` acts.

Grade

D

Quality

61 / 100

Safety

Passed

GitHub stars

45

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.