Content
92%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 is a tight, well-structured procedure that assumes competence, carries only domain-specific context Claude lacks, and routes detail into two clearly signaled reference files. Validation and feedback loops are explicit throughout the run/backtest/tune cycle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and domain-specific: it explains only what Claude would not know (how a Tessl review uses a lens — the six facts) and avoids generic padding about code review basics; every section earns its place. | 5 / 5 |
Actionability | Concrete procedural steps and executable bash commands for publishing/pinning ('tessl code review --skill ./review-lenses/...' and the pinned '@1.0.0#...' form), but the actual lens-authoring detail is delegated to references/lens-anatomy.md rather than carried inline. | 4 / 5 |
Workflow Clarity | A clearly sequenced six-step procedure with explicit validation checkpoints — run on a should-trip and a should-not change, backtest against known-good feedback — and a feedback loop ('Tune and re-run until... Report counts, not impressions' and 'Re-backtest against the same set before adopting'). | 5 / 5 |
Progressive Disclosure | SKILL.md is an overview that signals one-level-deep references inline ('Read references/lens-anatomy.md first, for...') to two real bundle files (lens-anatomy.md, validation.md); content is appropriately split and easy to navigate. | 5 / 5 |
Total | 19 / 20 Passed |