skills/use-context-reviewer-silence/SKILL.md
Silent failure detection. Do NOT use for security (use-context-reviewer-security) or readability (use-context-reviewer-readability).
npx skillsauth add thkt/claude-config use-context-reviewer-silenceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| ID | Pattern | Fix |
| --- | -------------------------------- | --------------------------------------- |
| SF1 | catch (e) {} | catch (e) { logger.error(e); throw } |
| SF1 | catch (e) { console.log(e) } | Show user feedback + log context |
| SF2 | .then(fn) without .catch() | Add .catch() or use try/catch |
| SF2 | async () => { await fn() } | Wrap in try/catch, handle error |
| SF3 | No error UI states | Add error boundary, feedback component |
| SF4 | value ?? defaultValue silently | Log when using fallback |
| SF4 | data?.nested?.value | Check and report if unexpected null |
| SF5 | catch { return defaultValue } | Log root cause before returning default |
| SF5 | config.x \|\| fallback | Validate config, warn on missing keys |
| Topic | File | | --------- | ---------------------------------------------------- | | Detection | ${CLAUDE_SKILL_DIR}/references/detection-patterns.md |
tools
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
development
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
development
Create Decision Records (DR) in MADR v4 format with auto-numbering.
development
Codex review + cleanup. Findings are challenged by critic-audit, not aggregated as facts, and fixes are applied directly. Do NOT use for internal multi-reviewer deep audits or findings reports (use /audit).