Content
82%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 tight, executable skill body: copy-paste commands verified against the bundled detector script, a clearly sequenced preferred path with a fallback and stop conditions, and bulk detail properly delegated to bundle files. Remaining weaknesses are a slightly redundant evidence-lens restatement of the canonical cautions and no error-recovery guidance for detector failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | No padding or explanations of known concepts; every section carries operational instructions, and the heavy rulebook and 193KB pattern data are correctly kept out of the body. Minor over-explanation exists: the evidence-lens bullets ("consider false positives and genre/register effects", "never convert pattern detection into an authorship classifier claim") partially restate the canonical cautions already invoked in the Authority section, so it does not reach the 5 anchor. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands covering the common input cases — stdin ("printf '%s' \"$TEXT\" | node scripts/detect.js --context general"), file input, and frontmatter-bearing Markdown (--source-mode rendered-markdown) — with flags that match the actual bundled script, plus an explicit no-Node fallback. This matches the 5 anchor's coverage of common cases with ready-to-run commands. | 5 / 5 |
Workflow Clarity | The Preferred path is a clear numbered sequence with explicit flag-selection conditionals, an execution-status checkpoint ("Never claim execution unless the command actually ran"), a fallback branch for missing Node, and explicit stop conditions. It falls short of the 5 anchor because there is no error-recovery guidance if the detector command itself fails; it is above the 3 anchor since a real checkpoint (execution evidence) is present. | 4 / 5 |
Progressive Disclosure | Well-organized sections with clearly signaled, one-level-deep references: scripts/detect.js is a real bundled file, and cross-skill pointers (../avoid-ai-writing/SKILL.md, router references) are named explicitly rather than buried. It does not reach 5 because a sizable inline connection-contract section could live in a reference file, and several referenced paths sit outside this bundle where their content cannot be verified. | 4 / 5 |
Total | 17 / 20 Passed |