Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/night-market-failure-archaeology
Chronicles settled battles, reverts, and dead ends.
Passed 16 of 18 test cases with the skill, and 2 of 18 without it.
and 26 more in the full report
17 fixed3 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
To speed up PR checks, a developer wants to configure `mypy` to run only on `--changed` files with suppressed error codes. Check our settled battles for past typechecking gate modifications and state the rule on gate coverage.
| Checked | Without skill | With skill |
|---|---|---|
| References the neutered mypy gate failure in SB10. | Missed | Passed |
| Requires running strict mypy typechecking across all files. | Passed | Passed |
The instructions your model reads when the skill loads.
This is a reference document, not a runbook. It records every major
investigation, dead end, rejected fix, and revert in this repo as
symptom, root cause, evidence, status, and lesson, so nobody re-fights
a settled battle. For triage of a failure happening right now, use
night-market-debugging-playbook. Come here when a proposed change
smells like something the repo already tried and rejected.
Jargon used below:
.github/workflows/python39-compat.yml.git log --format='%h %s' -1 <hash>.tasks_manager.py copies in attune,
sanctum, and spec-kit looked like textbook duplication.scripts/tasks_manager.py (1,169 lines deleted across 6 files)
broke plugin self-containment. Plugins are independent deployables
that run from a Claude Code cache directory, so they cannot import
from the repo root.054e2679 (consolidate, 2026-01-23), 29961cd2 (revert,test cases passed, vs 2 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.