Content
71%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 dense, highly actionable workflow skill with excellent conditional referencing and strong validation gates for a read-only retrieval flow. Its main weaknesses are token efficiency — the runtime-update policy is run-on prose and several caveats are repeated — and the absence of a sample search-result JSON structure needed to execute the merge and output steps precisely.
Suggestions
Restructure the Runtime compatibility gate as a numbered decision procedure or table, or move the 1.x-to-2.x update-route detail into a reference file; sentences like "test whether QODO_UPDATE_BASE_URL is set; never print its value. If set, stop for the user to resolve the source override" force multiple re-reads.
Add a short example of the `qodo read rules search --json` output (rule `id`, `name`, `severity`, `reference`) so the dedup/merge and output steps can be executed without guessing field names.
State the Windows-shell and rules-reuse guidance once in their authoritative sections instead of repeating them across Execution, Runtime compatibility gate, Quick start, and Search and merge.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | No tokens are spent on concepts Claude already knows, but sections like the Runtime compatibility gate are run-on policy prose ("Only when the runtime needs an update, before any update check/change, test whether QODO_UPDATE_BASE_URL is set; never print its value") and Windows-shell/reuse caveats are repeated across Execution, Runtime gate, Quick start, and Search and merge. This matches anchor 3 (mostly efficient but could be tightened) rather than 4, and is not 2 because nearly every sentence carries task-specific information rather than padding. | 3 / 5 |
Actionability | Concrete, copy-paste-ready commands with a filled example query ("qodo read rules search --query "Name: JWT Authentication Endpoint Validation..." --top-k 20 --scopes "/owner/repo/" --json"), a three-line query template, a concrete launcher fallback ("${QODO_HOME:-$HOME/.qodo}/bin/qodo"), a numeric retry threshold ("< 3 rules → re-run it once with a broadened Content line"), and a severity enforcement table. It falls just short of anchor 5 because the returned JSON shape (rule id/name/severity/reference fields) that the merge, dedup, and output steps depend on is never shown. | 4 / 5 |
Workflow Clarity | The sequence is explicitly stated ("First check the reuse condition in Preflight... go directly to Output") with real validation gates and recovery loops ("run `<qodo> --version`... run this FIRST", "Check `isError`, then read `structuredContent`", "Make one approved runtime attempt, then rerun the unadorned version probe"). Not anchor 5 because the step order is scattered across sections (Quick start precedes Preflight, which holds the first logical step) and the update-path loop is hard to track through dense prose; well above anchor 3's implicit checkpoints. | 4 / 5 |
Progressive Disclosure | Three references, all verified to exist, one level deep, each with an explicit conditional read trigger: "read [shell guidance](references/windows-shells.md) before the first call; [launcher recovery](references/windows-launcher.md) only if invocation fails" and "follow the [manual-update procedure](references/skill-updates.md)". Platform-specific detail is appropriately externalized while the core workflow stays in SKILL.md — a clean match for anchor 5. | 5 / 5 |
Total | 16 / 20 Passed |