Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, well-organized reference that respects the token budget and needs no external files; its only gap is that it presents configuration values as a listing rather than demonstrating how to apply them.
Suggestions
Add one short worked example showing a typical configuration, e.g. setting 'CODEX_RULES_MODE=static' with 'CODEX_RULES_ENABLED_SOURCES=CONTEXT.md,.omo/rules', to push actionability to level 3.
Briefly note how to verify rules are being injected (e.g. expected session-start behavior) so users can confirm configuration took effect.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — short bullets stating what is injected, the supported source paths, and the env knobs — with no padded explanation of concepts Claude already knows, so every token earns its place. | 3 / 3 |
Actionability | It lists concrete, copy-paste-ready values (e.g. 'CODEX_RULES_DISABLED=1', '.omo/rules/**/*.md'), but as a reference listing it gives no worked example or instruction applying them to a task, leaving the guidance concrete yet incomplete. | 2 / 3 |
Workflow Clarity | This is a simple informational skill with no multi-step or destructive process; per the simple-skills note, its single purpose is conveyed unambiguously through well-ordered sections. | 3 / 3 |
Progressive Disclosure | The skill is under 50 lines with no bundle files and no need for external references, and its content is organized into clear sections, satisfying the simple-skills allowance for level 3. | 3 / 3 |
Total | 11 / 12 Passed |