Content
92%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 body is a model of a compact, single-purpose operational skill: copy-paste-ready commands for both agent platforms, explicit error-recovery branches, and management commands, with no filler. Its only ding is the inline version-gated instruction, which will age.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and operational throughout — no padding or explanations of concepts Claude already knows — but the time-sensitive version reference "In Claude Code 2.1.98 or later" sits inline rather than in a versioned/deprecated section, which the guidelines penalize. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands for every common case: `github-wake ISSUE_URL`, `github-wake --codex-home ~/.codex-rja ISSUE_URL`, `github-wake --claude-monitor ISSUE_URL`, plus `--status` and `--cancel WATCH_ID`, with a concrete example directory value. | 5 / 5 |
Workflow Clarity | Clear sequence from precondition checklist to per-agent command to management and post-delivery behavior, with explicit feedback loops for error recovery ("If it reports that none or several do, pass the actual account directory"; "If `Monitor` is unavailable, explain that Claude Code must be upgraded") and `--status` for verification. | 5 / 5 |
Progressive Disclosure | Self-contained skill with no bundle files and no external references; ~60 well-organized lines with clean section headers (Codex, Claude Code, Both agents) — the simple-skill case where well-organized sections alone merit full credit. | 5 / 5 |
Total | 19 / 20 Passed |