Content
82%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 content is a lean, well-structured, practitioner-grade screening playbook: concrete thresholds, clear five-step sequencing, and a ready-to-use idea presentation template. Its main gaps are the unspecified execution mechanism for running screens or thematic sweeps and the absence of explicit validation checkpoints before presenting ideas.
Suggestions
Specify how to execute the screens — the data source or tool to use for fundamentals (e.g., a specific data feed, web-search procedure, or a scripts/ helper) — so 'Run screens based on the style' is directly executable rather than left to inference.
Add an explicit validation checkpoint between screening and presentation (e.g., sanity-check that metrics reconcile across sources and flag stale or missing data before writing the idea summary), which the 'Screens surface candidates, not conclusions' note implies but never operationalizes.
Consider moving the per-style screen criteria (Value/Growth/Quality/Short/Special Situation) into a references/ file (e.g., screens.md) referenced from Step 2, keeping SKILL.md focused on the workflow and presentation format.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~115-line body is dense with information Claude does not already know — concrete thresholds ("Free cash flow yield >5%", "ROIC >15%", "Strong net retention (>110% for SaaS)") and practitioner judgment ("Contrarian ideas need a catalyst — being early without a catalyst is the same as being wrong") — with no padding or explanation of known concepts. Every token earns its place. | 5 / 5 |
Actionability | Screen criteria are fully concrete ("P/E below sector median", "Rising receivables / inventory vs. sales") and the idea-presentation template is copy-ready (metric table with "EV/EBITDA (NTM)", "P/E (NTM)", "FCF yield"). However, "Run screens based on the style" and "research the theme" never specify the execution mechanism — no tool, data source, or command — leaving a minor gap that keeps it below fully executable. | 4 / 5 |
Workflow Clarity | A clear five-step sequence (Define Search Criteria → Quantitative Screens → Thematic Sweep → Idea Presentation → Output) with a well-defined output artifact ("Shortlist of 5-10 ideas... Prioritized list"). Validation is only implied by the caution "Screens surface candidates, not conclusions" — no explicit checkpoint or sanity-check step, so it fits 'clear sequence with most checkpoints present; minor validation gaps' rather than the full-checkpoint anchor. | 4 / 5 |
Progressive Disclosure | A single self-contained file with well-organized sections (per-style screens, workflow steps, Important Notes) and no bundle files. Good structure for its size, though the ~40 lines of per-style screen criteria (Value/Growth/Quality/Short/Special Situation) could arguably be split into a references/ file, and the under-50-line simple-skill exception does not strictly apply. | 4 / 5 |
Total | 17 / 20 Passed |