Content
63%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 lean, well-sectioned instruction skill with a sensible workflow and an explicit iteration/feedback step, but its actionability hinges on a `hooks.md` that is neither bundled nor prominently referenced, and it includes no example hook JSON. Surfacing or inlining the hook template would resolve the biggest weakness.
Suggestions
Include `hooks.md` in the bundle (e.g., `references/hooks.md`) and reference it in a clearly signaled section, or inline a minimal executable hook JSON example if the file is intentionally external.
Add a validation checkpoint in the Iterate loop, e.g. verify the drafted JSON parses and the hook fires on the target event before finalizing.
Trim editorial sentences in Path Conventions ("Absolute paths are fine when intentional — just be deliberate about which you use") to tighten the body further.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is efficient with well-scoped sections and no explanation of concepts Claude already knows, matching 'efficient; minor instances of over-explanation that could be trimmed'. Not 5 because a few sentences pad rather than instruct (e.g., "Absolute paths are fine when intentional — just be deliberate about which you use" restates the preceding rule); not 3 because verbosity is only minor. | 4 / 5 |
Actionability | Guidance includes concrete specifics (hook location `.github/hooks/`, event names like PreToolUse/SessionStart/Stop, extraction checklist), but the actual hook template and format are delegated to a `hooks.md` that is not present in the bundle, so the body never shows a hook JSON example — 'some concrete guidance but incomplete; missing key details'. Not 4 because the core executable artifact is missing rather than a minor gap; not 2 because the workflow steps and path rules are specific and followable. | 3 / 5 |
Workflow Clarity | A clear sequence (extract from conversation → clarify → path conventions → draft → review weak parts → finalize with testing suggestions) with a built-in feedback loop ("identify the most ambiguous or weak parts and ask about those") matches 'clear sequence with most checkpoints present; minor validation gaps'. Not 5 because there is no checkpoint that the drafted hook JSON is syntactically valid or actually fires before finalizing. | 4 / 5 |
Progressive Disclosure | Sections are well organized, but the reference to `hooks.md` — the file that supposedly holds the template and principles — is buried in an intro sentence rather than clearly signaled, and no such bundle file exists in this skill's directory. This matches 'some structure but could be better organized; references present but not clearly signaled'. Not 4 because the key reference is neither prominent nor verifiable in the bundle; not 2 because the body itself is short and sectioned rather than a wall of inline content. | 3 / 5 |
Total | 14 / 20 Passed |