Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-sequenced, actionable ritual with explicit validation checkpoints and feedback loops, staying lean throughout. It exemplifies the verify-before-claim contract it teaches.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence — no generic concept explanations; every section earns its place, and the emphatic lines ('EVIDENCE BEFORE CLAIMS, ALWAYS') are load-bearing rather than padding. | 3 / 3 |
Actionability | Concrete claim→command table, named tools (async_bash, bg_shell, gsd_*, browser_assert), and copy-paste-style evidence examples ('84/84', 'exit 0'); project-specific commands are placeholders with justified flexibility. | 3 / 3 |
Workflow Clarity | A clear 5-step sequence with explicit validation checkpoints (Step 3 failure→loop back, Step 4 staleness re-run), feedback loops, and a success checklist closing the process. | 3 / 3 |
Progressive Disclosure | A single self-contained file (~80 lines) with well-organized sections and no external references; per the rubric's simple-skills note, this scores 3 without bundle files. | 3 / 3 |
Total | 12 / 12 Passed |