Content
26%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 reads as a marketing-flavored overview of the Shape Up philosophy rather than an operational skill: it explains concepts Claude already knows and provides no workflow, templates, or concrete procedure for actually running a shaping session. Structure is acceptable for a single short file, but token budget and actionability are the clear weaknesses.
Suggestions
Add a concrete, sequenced shaping workflow (e.g., 1. Clarify the problem and constraints, 2. Set the appetite (6 or 2 weeks), 3. Sketch at fat-marker fidelity, 4. De-risk technical unknowns, 5. Write the pitch using a standard template, 6. Present at the betting table) with explicit checkpoints.
Include a copy-paste-ready pitch template (Problem, Appetite, Solution, Rabbit holes, No-gos) so the skill produces concrete artifacts instead of philosophy.
Cut the padding: remove the "Domain Context" boilerplate, the generic "Input Requirements" section, and the Basecamp/DHH history anecdote, and merge the duplicate "Resources"/"Further Reading" sections into one.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body re-explains Shape Up, a methodology Claude already knows: "Shape Up is a product development methodology built on one core insight...", plus the 17-years-of-Basecamp/DHH history anecdote. The "Domain Context" section ("This skill implements a proven product management framework. The approach combines best practices from industry leaders...") and the generic "Input Requirements" boilerplate are pure padding, matching 'Noticeably verbose; several unnecessary explanations or padded sections'. It is not 3 because the padding spans multiple sections rather than isolated sentences. | 2 / 5 |
Actionability | The content is instruction-free philosophy: there is no pitch template, no appetite-setting procedure, no steps for running a shaping session or betting table — only descriptive framing plus when-to-use checklists. As an instruction-only skill its lack of code is not penalized, but the guidance stays at the 'high-level hints' level ('Move from "What's the estimate for this?" to "What version of this can we confidently ship..."'), missing the specific steps to execute, matching the 2 anchor rather than 3. | 2 / 5 |
Workflow Clarity | No multi-step process is presented anywhere: the body never sequences a shaping workflow (set appetite → sketch → de-risk → write pitch → bet) and has no checkpoints or validation steps. This matches the 1 anchor ('Steps missing or incoherent; no sequence'); it cannot be 2 because even a rough step sequence is absent — the sections are conceptual, not procedural. | 1 / 5 |
Progressive Disclosure | The skill is a single short file with no bundle directories and no nested references, and sections are headers-based and scannable, which fits 'Good structure; most content is appropriately placed'. It misses 5 because of minor organization gaps: template-boilerplate sections ("Domain Context", "Input Requirements") stacked above the real content, two heading hierarchies (`## Domain Context` before `# Shape Up`), and redundant split "Resources"/"Further Reading" sections. | 4 / 5 |
Total | 9 / 20 Passed |