Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an ambitious, comprehensive research methodology skill that suffers from significant verbosity and structural redundancy. The dual pipeline (general P0-P7 and enterprise E1-E7) creates confusion with overlapping descriptions, and the skill inlines extensive detail that should be in reference files while also referencing external files that aren't provided. The core workflow concept is sound but the presentation undermines usability.
Suggestions
Reduce redundancy by removing the duplicate enterprise workflow descriptions — define the enterprise pipeline once and clearly state how it maps to/extends the general P0-P7 pipeline.
Move detailed tables (source governance classifications, quality gates thresholds, registry output format) into the referenced files and keep only summary rules in SKILL.md to cut length by ~40%.
Replace pseudocode examples (like the SendMessage counter-review dispatch) with either actual executable patterns or remove them — they add length without actionability.
Add a clear decision tree or flowchart at the top showing: trigger → mode selection → which pipeline to follow → which reference files to load, so Claude can quickly navigate the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines with significant redundancy. Enterprise workflow is described in P0, then repeated in the Enterprise Research Mode section. E3-E5 are described in detail and then summarized again as 'E3-E7'. Source governance rules, quality gates, and anti-patterns contain substantial overlap. Many concepts Claude already understands (what SWOT is, what a PDF is equivalent here being what 'official' vs 'journalism' sources are) are over-explained. | 1 / 3 |
Actionability | The skill provides structured workflows with specific steps, status report templates, and registry output formats, which is good. However, it lacks truly executable code/commands — the bash example for counter-review is pseudocode (SendMessage to fictional agents), there are no actual CLI commands or scripts, and many instructions are procedural descriptions rather than copy-paste-ready guidance. The references to external files that aren't provided also reduce actionability. | 2 / 3 |
Workflow Clarity | The P0-P7 pipeline is clearly sequenced with status checkpoints at each phase, which is strong. However, the Enterprise Research workflow (E1-E7) overlaps confusingly with the general P0-P7 pipeline — it's unclear when to follow which, and the enterprise sections are described twice (once in detail, once as a summary). The relationship between the two workflows creates ambiguity. Validation steps exist (L1/L2/L3, P6 counter-review, P7 verify) but are mostly delegated to external reference files not provided. | 2 / 3 |
Progressive Disclosure | The skill references many external files (subagent_prompt.md, research_notes_format.md, enterprise_analysis_frameworks.md, etc.) with clear tables showing when to load each, which is good structure. However, no bundle files were provided, making it impossible to verify these references work. More critically, the SKILL.md itself is a monolithic wall of text that inlines too much detail (full source governance tables, complete registry format, detailed enterprise workflow) that should be in reference files, while simultaneously pointing to reference files for other content. | 2 / 3 |
Total | 7 / 12 Passed |