evaluate-attempt

github:brazil-bench/pourpoise · first committed 2025-12-02 · source · badge

This SOP evaluates a completed brazil-bench attempt against the spec.md requirements, capturing metrics for comparison across orchestration patterns. Supports Python and Swift/iOS projects.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

8 commits to this file on GitHub (newest first).

2026-01-13 · commit 13e9bca · Standardize evaluation to 16 canonical requirements
2026-01-04 · commit ad35f8f · Add context header block requirement (v1.4/v2.0)
2026-01-04 · commit 3b0f4c1 · Stricter test requirements: zero skip tolerance, integration tests required
2026-01-04 · commit 0284ff4 · Require self-contained integration tests with testcontainers (v1.2/v1.8)
2026-01-04 · commit e6582aa · Add Swift/iOS support to evaluate-attempt and file-issues SOPs
2026-01-03 · commit 84ad2e5 · Add documentation quality evaluation to SOPs (v1.5)
2025-12-16 · commit edc472b · Add effective tests methodology with skip penalty scoring (v3)
2025-12-02 · commit bcc0649 · Add data strategy assessment and timeline analysis to evaluations

Archived snapshots