Content
77%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 lean, highly actionable process skill: explicit formulas, thresholds, defaults, and a gated four-phase workflow with real validation checkpoints. Its weakness is navigation — the 'verified' repo-asset paths point outside the skill and no bundle files exist to back them, so the progressive-disclosure structure is partly broken.
Suggestions
Fix the asset paths so they resolve relative to the skill's own directory (e.g., `assets/sprint_planning_template.md`, `references/sprint-planning-guide.md`) and actually ship those files in the skill's bundle, or drop the 'Repo Assets (verified paths)' section.
Show the generator invocation with its expected input/arguments (e.g., an example epic source) rather than a bare `python3 .../user_story_generator.py`.
Trim the redundant Usage block and the duplicated script path in 'Repo Assets' to tighten token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is imperative and dense — no padding explaining what a sprint or INVEST is, and it assumes Claude's competence throughout. Minor redundancy keeps it below anchor 5: the Usage section repeats the frontmatter invocation, and the 'Repo Assets (verified paths)' section duplicates the script path already given in Phase 3. | 4 / 5 |
Actionability | Concrete, executable decision rules throughout: focus factor default 0.7, explicit deduction categories, the '>15% over trailing velocity → plan to velocity' rule, the '~30% carry-over → recommend smaller commitment' flag, a five-item DoR checklist, and a defined output structure. The one code command (`python3 product-team/.../user_story_generator.py`) is copy-pasteable but shows no arguments or expected input, a minor gap that fits anchor 4 rather than 5. | 4 / 5 |
Workflow Clarity | Four phases are clearly sequenced (capacity math → carry-over → DoR gate → output) with explicit validation checkpoints: the velocity cross-check in Phase 1, the per-story DoR gate in Phase 3 with a defined failure path ("goes to 'needs refinement', not the sprint"), and the Phase 4 invariant that committed scope sums to ≤ the planning number. The DoR checklist plus recovery path matches anchor 5's validation-with-feedback-loop pattern; this is not a destructive/batch operation, so no cap applies. | 5 / 5 |
Progressive Disclosure | The body is well-sectioned, but every referenced supporting file (sprint_planning_template.md, sprint-planning-guide.md, user_story_generator.py) points into a `product-team/agile-product-owner/...` tree outside the skill, and the skill's own bundle (references/, scripts/, assets/) is empty — none of the paths resolve from the skill's location. Structure exists but the references cannot be followed, which matches anchor 3 rather than 4's 'references mostly clear, minor gaps'. | 3 / 5 |
Total | 16 / 20 Passed |