Content
88%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 skill body is highly actionable with concrete commands, a clear workflow, and strong validation via exit codes and escalation rules. Its main weakness is that a large pattern-tag table and several worked examples are inlined where progressive disclosure would favor a separate reference file.
Suggestions
Move the full pattern_tag → fix guidance table into a references file (e.g. pattern-tags.md) and keep only the top few common patterns inline, with a pointer to the rest.
Move the multi-step worked examples (dSYM mismatch, missing dSYM, timeout) into an examples reference, leaving a single representative example in SKILL.md.
Trim the legacy manual-parsing fallback note or relocate it to a reference, since it describes an older-Axiom path that most users will not hit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and operational with minimal concept padding, but the large pattern-tag table and three worked examples include some detail that could be trimmed or moved to a reference. | 4 / 5 |
Actionability | Fully executable commands (command -v xcsym, xcsym crash <file> --format=standard, find-dsym, verify) with concrete exit-code tables and per-pattern fix steps covering the common cases. | 5 / 5 |
Workflow Clarity | Clear sequenced workflow (check xcsym, run crash, interpret exit code, map pattern_tag to fix) with explicit validation checkpoints via exit codes and escalation criteria for hang/unclassified/truncated inputs. | 5 / 5 |
Progressive Disclosure | Well-structured with clear section headers and a Related section pointing one level deep to other skills, but the pattern-tag table and worked examples are inlined in SKILL.md rather than split into a separate reference file; no bundle files are present to absorb them. | 4 / 5 |
Total | 18 / 20 Passed |