[fix] minor typos (#7)

* fix: claude.md typo

* fix: logging verbal typo
This commit is contained in:
Barkhayot Juraev
2026-03-30 10:33:53 +02:00
committed by GitHub
parent 91421f5305
commit 63d45d0f6e
2 changed files with 2 additions and 2 deletions
+1 -1
View File
@@ -412,7 +412,7 @@ The `mcp__context7__*` tools may still be listed in `allowed-tools` frontmatter
### Adversarial evaluation design
Run skill evaluation with the pattern recommanded by `/skill-creator`. Use `/tmp/{skill-name}-workspace` as default workspace for ephemeral files.
Run skill evaluation with the pattern recommended by `/skill-creator`. Use `/tmp/{skill-name}-workspace` as default workspace for ephemeral files.
Evals MUST be adversarial — they test the skill's **unique value**, not common knowledge the model already has. A good eval has a "trap" the model falls into without the skill but avoids with it. Every rules of a skill must have its test.
@@ -21,7 +21,7 @@ slog.Error("user creation failed",
## Handler Setup
```go
// Production MUST use JSON — because plain-text multiline logs (eg. stack traces) would be splitted into separate records by log collectors
// Production MUST use JSON — because plain-text multiline logs (eg. stack traces) would be split into separate records by log collectors
logger := slog.New(slog.NewJSONHandler(os.Stdout, &slog.HandlerOptions{
Level: slog.LevelInfo,
}))