Content
100%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.
An exemplary instruction-only skill: a diagnostic intake, a situation-routing table, seven numbered plays with scripts and benchmarks, explicit done-when conditions and handoff gates, a fill-in deliverable, a grading rubric, red flags, and clean one-level-deep references. Nothing is padded and nothing Claude already knows is re-explained; the only conceivable trim is the inline quotes, which serve a verification purpose and duplicate only a small sample of quotes.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 180-line body is dense signal with zero concept padding: no 'what is sales/ICV/procurement' exposition, just expert-derived specifics like 'Abel says the mid-market does not exist', '48-72 hours, 3-4 daily power users', and 'expect procurement to take ~30 days'. Every line carries an instruction, script, threshold, or benchmark — matching anchor 5; anchor 4 would require over-explanation to trim, and none is present. | 5 / 5 |
Actionability | Guidance is fully executable for an instruction-only skill: verbatim call scripts ('I'll keep this informal; I might not need the full 30 minutes'), concrete numbers (30-lead test, 15-20 min per note, ~70% second-meeting rate, demo the 20%), a fill-in markdown deliverable template, and a 1/3/5-anchored grading rubric. This is copy-paste-ready guidance covering the common cases, matching anchor 5. | 5 / 5 |
Workflow Clarity | Clear three-step sequence (Diagnose the 4 questions -> routing table to pick a play -> numbered Plays A-G) with explicit validation checkpoints and feedback loops: 'Zero replies: change the message or the role and try another 30', 'Done when: reply rate is known... and 10 first meetings booked', the Play F handoff gate (15-25% win rate over 50-100 at-bats), and 'Target about 80% pilot success; below that, qualification or product is off'. Matches anchor 5 including error-recovery loops and the red-flags checklist. | 5 / 5 |
Progressive Disclosure | The body is a distilled overview-plus-plays; both bundle files exist and are well-signaled one level deep in 'Go deeper' with one-line descriptions ('references/frameworks.md - every framework in this skill, how to run it', 'references/quotes.md - verified quotes with timestamps'), plus pointers to four related skills for handoff. Verified against the actual bundle: frameworks.md (8 sections) and quotes.md (~49 quotes) hold the bulk detail, with only a 6-quote sample inlined as receipts. Content is appropriately split and easy to navigate, matching anchor 5. | 5 / 5 |
Total | 20 / 20 Passed |