Content
85%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, highly actionable workflow skill with clear sequencing and validation checkpoints and appropriate one-level-deep reference splitting. Its main weakness is verbosity from redundant restating of key rules across sections.
Suggestions
Consolidate the repeated gh api body=@file prohibition: state it once in Hard Rules and reference it from Red Flags and commands.md rather than re-explaining in each place.
Trim the Public API behavior worked example (the cuBQL block) to a shorter illustration or move it into commands.md, keeping the SKILL.md body leaner.
Consider folding the probe 'Avoid' bullets into the 'Prefer' bullets as a single compact list to reduce duplicated framing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and information-rich but long; while mostly efficient and free of obvious concept re-explanation, the repeated restating of rules (e.g. the gh api body=@file prohibition appears in Hard Rules, Red Flags, and commands.md) and elaborate sectioning could be tightened to respect the token budget. | 2 / 3 |
Actionability | It provides concrete executable guidance: exact gh/git commands and shell snippets in commands.md, a fill-in draft template, comment-shape blocks, and specific classification tables, all copy-paste ready. | 3 / 3 |
Workflow Clarity | A numbered nine-step Checklist sequences the process with explicit validation checkpoints (draft-before-write, confirm-before-post, verify posted body before closing, stop-and-report on failure), matching the clear-sequence-with-validation anchor. | 3 / 3 |
Progressive Disclosure | The SKILL.md body serves as a well-organized overview that signals a single one-level-deep reference (commands.md) for executable snippets, with the reference path verified as a real file and clearly linked. | 3 / 3 |
Total | 11 / 12 Passed |