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.
A well-organized router skill with a clear routing table, explicit priority ordering, and concrete commands, but it is padded by repetitive behavioral-enforcement rhetoric and its referenced detail files are absent from the bundle, leaving the progressive disclosure unverified.
Suggestions
Trim the EXTREMELY-IMPORTANT block and consolidate the Red Flags table; the 'check skills first' rule is stated repeatedly across The Rule, Red Flags, and Using Axiom Router Skills sections.
Include the referenced skills/*.md files (xclog-ref, xcsym-ref, xcui-ref, xcprof-ref, device-control-ref, getting-started) in the bundle so the one-level-deep progressive disclosure is actually navigable.
Replace the rhetorical enforcement lines ('This is not negotiable. This is not optional. You cannot rationalize your way out of this.') with a single concise imperative to reduce token cost without losing the routing discipline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient and free of basic-concept padding, but the rhetorical enforcement block ("This is not negotiable. This is not optional. You cannot rationalize your way out of this.") and the 11-row Red Flags table restate the same 'check first' message across multiple sections, so it could be tightened — matching score-3 rather than score-4's 'minor instances'. | 3 / 5 |
Actionability | Provides concrete, executable guidance — a Question→Read routing table, specific commands ("/skill axiom-concurrency", "/axiom:fix-build", "xcui resize sweep") and exact file paths — with only minor gaps because the actual tool usage lives in the referenced files, matching score-4 rather than score-5's fully copy-paste-ready coverage. | 4 / 5 |
Workflow Clarity | The routing workflow is clearly sequenced with an explicit skill-priority ordering (Environment/Build → Architecture → Implementation) and concrete multi-domain invoke-both examples; no destructive/batch operations are present so the validation cap does not apply, placing it at score-4 rather than score-3 (which implies missing checkpoints) or score-5 (which requires explicit validation feedback loops). | 4 / 5 |
Progressive Disclosure | The body is a well-structured router with a routing table and one-level-deep inline links to skills/*.md files (the score-5 pattern), but the referenced bundle files (skills/xclog-ref.md, skills/xcsym-ref.md, etc.) and scripts/build-inlined-auditors.ts are not present in the provided bundle, so the disclosure cannot be verified against real files — dropping it to score-4 (good structure, minor organization gap). | 4 / 5 |
Total | 15 / 20 Passed |