cliffhall
0febaa0f6f
docs: address Copilot review round 7 on #2203
Strip YAML properties (tags, anchors, in either order) before deciding
whether a description scalar is quoted — testing the first character alone
read `© "Counts # safely"` as unquoted and rejected a `#` the quotes
make harmless.
Count the positive-case floor by distinct prompt rather than by entry: the
floor exists for breadth, so five copies of one prompt cleared it while
exercising exactly the single trigger it is meant to look past. Compare on
collapsed, case-folded text so trivial edits do not read as a new situation.
Re-aim the two positive prompts that measured the wrong thing — the
project-structure case now poses a concrete "which piece handles what"
question, and the test-servers case names running a real MCP server.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SyBPs7caoMcyvnp9ArMBhV
Signed-off-by: cliffhall <cliff@futurescale.com>
|
2026-09-01 12:21:09 -04:00 |
| .. |
|
board-ops
|
docs: address Copilot review round 1 on #2203
|
2026-09-01 10:10:06 -04:00 |
|
issue-create
|
docs: tune skill eval cases and document how to write them
|
2026-08-31 23:22:25 -04:00 |
|
issue-triage
|
docs: tune skill eval cases and document how to write them
|
2026-08-31 23:22:25 -04:00 |
|
local-dev
|
docs: address Copilot review round 4 on #2203
|
2026-09-01 11:14:06 -04:00 |
|
pr-flow
|
docs: tune skill eval cases and document how to write them
|
2026-08-31 23:22:25 -04:00 |
|
pre-push-gate
|
docs: tune skill eval cases and document how to write them
|
2026-08-31 23:22:25 -04:00 |
|
project-structure
|
docs: address Copilot review round 7 on #2203
|
2026-09-01 12:21:09 -04:00 |
|
release
|
chore: address Copilot review round 18
|
2026-08-29 05:05:47 -04:00 |
|
test-servers
|
docs: address Copilot review round 7 on #2203
|
2026-09-01 12:21:09 -04:00 |
|
testing
|
docs: accept several skill names in skills:eval and re-aim overlapping cases
|
2026-09-01 00:18:43 -04:00 |