Content
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-architected troubleshooting skill: a concise overview with concrete commands, a clear symptom-to-action decision tree, explicit checkpoints and red-flag feedback loops, and a verified one-level-deep reference structure. It models progressive disclosure effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean, directive body that assumes Claude's competence (no explaining what Go or pprof is); the emphatic repetition ('NEVER', 'IS NOT ACCEPTABLE') is enforcement tone rather than explanatory padding, and every section earns its place. | 3 / 3 |
Actionability | The Quick Decision Tree maps each symptom to exact, executable commands (e.g. 'go build ./... 2>&1, go vet ./... ', 'go test -race ./...', 'curl localhost:6060/debug/pprof/goroutine?debug=2', 'go install github.com/go-delve/delve/cmd/dlv@latest'), copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear sequenced process (Decision Tree -> Golden Rules -> Methodology -> Red Flags) with explicit checkpoints and feedback loops, e.g. '3+ fix attempts on the same issue - You have the wrong mental model. Re-read the code, trace the data flow from scratch.' | 3 / 3 |
Progressive Disclosure | SKILL.md acts as an overview with a well-signaled one-level-deep 'Reference Files' section describing all 10 references, each of which was verified to exist on disk; deep detail is split out rather than inlined. | 3 / 3 |
Total | 12 / 12 Passed |