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.
A well-structured method skill: executable commands with documented refusal exit codes, a gated four-step workflow, and verified one-level-deep bundle organization. Its only weakness is light philosophical restatement (Newport doctrine the model already knows) in the intro and Rules sections that could be trimmed for token efficiency.
Suggestions
Trim the 'What this does' opening paragraph and the Rules section to operational statements only — e.g., replace 'More than 4 deep hours is fake depth' with 'Refuse schedules exceeding 4 deep hours; defer the excess' — since the rationale already lives in references/deep_work_canon.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and command-driven, but the 'What this does' intro ('A calendar full of reactions is not a plan') and the Rules section editorialize Newport philosophy Claude already knows ('More than 4 deep hours is fake depth', 'open loops steal tomorrow's first block') rather than instructing. This is 'efficient with minor instances of over-explanation that could be trimmed' (4), not 5, since a few sentences are motivational restatement rather than operational content. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands with real flags and example values for all three scripts (e.g., 'python scripts/time_block_planner.py --start 08:30 --end 17:00 --lunch 12:30 --task "Write product spec:120:deep"'), documented exit codes, and a script role table. Matches the score-5 anchor: specific examples cover the common cases. | 5 / 5 |
Workflow Clarity | Steps 1–4 are clearly sequenced (classify → budget gate → block → log → shutdown) with explicit validation checkpoints and feedback loops: 'OVER-BUDGET (exit 2) means cut, batch, or delegate before any schedule is built' and 'Two refusals, both exit 2 ... the planner names what to defer / what to drop — the day never silently extends'. This matches the score-5 anchor with explicit validation and error-recovery guidance. | 5 / 5 |
Progressive Disclosure | The SKILL.md is a clear overview with a script table, and well-signaled one-level-deep references and assets ('references/deep_work_canon.md', 'references/time_blocking_method.md', 'references/shallow_work_budget.md', 'assets/example_time_block_plan.md', 'assets/shutdown_checklist.md' — all verified to exist with no nested references inside them), each with a one-line role description. Matches the score-5 anchor: appropriate split, easy navigation. | 5 / 5 |
Total | 19 / 20 Passed |