Content
57%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 delivers a coherent, actionable lead-research workflow with a strong output specification, but it is held back by redundant sections, absent validation checkpoints for a batch-output process, and a monolithic single-file structure. Trimming the duplicated overview sections and adding verification steps would lift it substantially.
Suggestions
Cut the "What This Skill Does" and "Related Use Cases" sections (they duplicate "Instructions" and "How to Use") and fold "Tips for Best Results" into the usage prompts to remove padding.
Add an explicit validation step to the workflow, e.g. "Verify each lead: confirm the company is active, the website/LinkedIn URL resolves, and stated signals (job postings, funding) are current before including it".
Move the full output template and the two examples into references/ files (e.g. references/output-template.md, references/examples.md) and link to them from a lean SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The core Instructions and output template are efficient, but "What This Skill Does" nearly duplicates the Instructions section, "Tips for Best Results" restates "How to Use", and "Related Use Cases" adds padding — several sections could be cut or tightened. It is not a 2 because the guidance avoids explaining concepts Claude already knows and the bulk of the body is direct instruction, not conceptual filler. | 3 / 5 |
Actionability | Concrete, executable guidance throughout: copy-paste user prompt templates, a 1-10 fit-score scheme with named factors, an exact per-lead output field list (Company Name, Priority Score, Decision Maker, LinkedIn URL, Conversation Starters), and a full markdown output template. It is not a 5 because the research steps themselves ("Search for companies matching the criteria", "Check for budget indicators") remain high-level hints with no concrete search strategies or commands. | 4 / 5 |
Workflow Clarity | A clear 7-step sequence is present (understand product → define ICP → research → score → output → format → next steps), but there are no validation checkpoints — nothing verifies that identified companies are real, currently operating, or match the stated criteria, which is a batch operation producing 10-20 lead profiles. The rubric's cap for batch operations without validation holds it at 3; it is not a 2 because the sequence itself is coherent and well defined. | 3 / 5 |
Progressive Disclosure | The body has good section headers but is a single ~195-line file with no bundle files; the 40-line output template and the Examples section are content that could live in one-level-deep reference files. It is not a 2 because structure is solid with clear, navigable sections; not a 4-5 because nothing is split out and the file is well over the ~50-line threshold where inline-only organization would suffice. | 3 / 5 |
Total | 13 / 20 Passed |