Content
38%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body contains genuinely useful domain reference material (track formats, color schemes, troubleshooting), but it is buried in a bloated, self-contradictory document with template filler, an inaccurate CLI reference that would fail as written, and no meaningful use of the bundle's references/ directory. It needs aggressive pruning and relocation of detail content into reference files.
Suggestions
Cut the SKILL.md body to a lean overview (quick start, CLI reference verified against scripts/main.py's argparse, pointers to detail files), and move Common Patterns, Troubleshooting, Quality Checklist, and Color Scheme Reference into separate files under references/ linked one level deep.
Fix the Parameters/Usage section to match the actual CLI: --color-scheme (not --colors), no --radius flag, --type choices variation/cell-comm/custom, --output default '.', and document --render and --config.
Delete the duplicated template sections (When to Use / Key Features / Implementation Details that repeat the description verbatim or cross-reference misplaced anchors) and resolve the contradictory dependency statements (Python version, yaml requirement, 'no external packages').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~1,160-line body is heavily padded: the frontmatter description is repeated verbatim in 'When to Use' and 'Key Features'; sections point at each other with wrong anchors ('See ## Prerequisites above' while Prerequisites appears ~1,000 lines later); dependencies are stated twice with contradictions (Python 3.10+ vs 3.7+, yaml required vs 'No external packages required'); and generic template filler ('Scope-focused workflow', 'Output discipline') fills several sections. Not 1 because the second half carries genuine domain content (track data formats, color schemes, troubleshooting) rather than re-teaching concepts Claude already knows. | 2 / 5 |
Actionability | There is substantial concrete guidance (Python API examples, complete CLI workflow with correct flags, input format tables), but the 'Parameters' table and 'Basic Usage' section document flags that do not exist in scripts/main.py ('--colors' vs the actual '--color-scheme', '--radius', '--type cell-communication' vs the actual 'cell-comm', default 'circos.svg' vs the actual '.'), so those commands fail as written. This is a systematic reference-section mismatch rather than a minor gap, placing it at anchor 3 rather than 4. | 3 / 5 |
Workflow Clarity | A concrete three-step Complete Workflow Example (create sample data, generate config, render) exists alongside validation smoke checks (py_compile, --help) and quality checklists, but the primary 'Workflow' section is abstract template text, there is no validate-fix-retry feedback loop, and workflow guidance is scattered across redundant sections ('Workflow', 'Implementation Details', 'Complete Workflow Example'). Sequence present but checkpoints implicit — anchor 3. | 3 / 5 |
Progressive Disclosure | Over 1,100 lines of material that clearly belongs in separate reference files (Common Patterns, Troubleshooting, Color Scheme Reference, Parameters, Quality Checklist) are inlined in SKILL.md. Worse, the body claims '(No reference files currently available for this skill)' while references/runtime_checklist.md actually exists in the bundle and is never linked, so the reference is both buried and misrepresented — anchor 2. | 2 / 5 |
Total | 10 / 20 Passed |