Content
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive orchestration skill with excellent workflow clarity and state management, but it suffers significantly from verbosity. The repeated preference-check pattern (appearing 3 times with nearly identical logic) and the inline progress bars bloat the content substantially. The skill would benefit greatly from extracting repeated patterns into shared references, which would also improve progressive disclosure.
Suggestions
Extract the repeated preference check pattern (two-tier lookup → branch on value → gate → 'remember this?' follow-up → write-back) into a shared reference file like `references/preference-gate-pattern.md` and reference it from each gate, reducing ~60% of the repetition.
Add a concrete YAML example showing the expected structure of `~/.arness/workflow-preferences.yaml` and `.arness/workflow.local.yaml` rather than describing the read/write operations procedurally each time.
Move the detailed G1 option presentation logic (greenfield backlog variants with conditional option counts) into a reference file, keeping only the routing summary inline.
Consider removing the repeated ASCII progress bars or replacing them with a single reference showing the full pipeline and just noting the current step name at each gate.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines. While it's an orchestration skill, there is massive repetition — the preference check pattern (two-tier lookup, write-back logic, 'remember this?' follow-up) is duplicated nearly identically across G2, G3, and G4. This could be factored into a shared reference. The progress bar ASCII art is repeated 10 times. Many decision trees could be expressed more compactly as tables or references. | 1 / 3 |
Actionability | The skill provides very specific routing logic, decision tables, and exact skill invocation syntax. However, it contains no executable code — all actions are described procedurally rather than with concrete commands or code snippets. The preference file read/write operations describe what to do but never show the actual YAML structure or file manipulation commands. | 2 / 3 |
Workflow Clarity | The workflow is exceptionally well-sequenced with numbered steps, explicit gates (G1-G5), clear decision tables for routing, state detection with resume points, progress indicators at each step, and error handling with recovery paths. Validation checkpoints exist at spec review and plan review stages with explicit feedback loops. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (scope-router-criteria.md, preferences-schema.md, step-0-fast-path.md) and delegates to sub-skills. However, the massive inline content — particularly the repeated preference check patterns and the detailed G1/G2/G3/G4 gate logic — should be factored into reference files. The skill states it 'MUST NOT duplicate sub-skill logic' but then includes extensive inline decision trees that could live in references. | 2 / 3 |
Total | 8 / 12 Passed |