Content
67%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.
An effective, well-organized routing skill with concrete commands and a strong decision tree, undermined by significant structural redundancy across five overlapping sections. Progressive disclosure is good but references could be cleaner.
Suggestions
Collapse the Example Invocations section (or trim it heavily) since it duplicates the Routing Logic and Decision Tree; keep only cases that add new routing decisions.
Convert file references to markdown link form (e.g. '[memory-debugging](skills/memory-debugging.md)') and consolidate cross-suite pointers into a single 'Related skills' map.
Trim the Anti-Rationalization table to the highest-value rows to reduce token cost while preserving the strongest rebuttals.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is dense and assumes Claude's competence (no concept explanations), but Routing Logic, Decision Tree, Anti-Rationalization, Example Invocations, and Critical Patterns heavily overlap, with the ~130-line Example Invocations largely duplicating earlier sections. | 3 / 5 |
Actionability | Routing guidance is concrete and executable: specific slash commands ('/axiom:audit memory', '/axiom:profile', '/axiom:console'), named agents, and exact file paths per case, with only minor gaps for a router-style skill. | 4 / 5 |
Workflow Clarity | The numbered Decision Tree provides a clear sequenced procedure with explicit YES/NO branching (e.g. item 4), though it lacks validation/feedback loops; routing is not a destructive/batch operation so the cap does not apply. | 4 / 5 |
Progressive Disclosure | A well-structured router with clear section headers and one-level-deep references ('See skills/X.md'), but references are plain paths rather than link-formatted and several cross-suite pointers add minor navigation friction. | 4 / 5 |
Total | 15 / 20 Passed |