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.
The body is a short, well-organized, mostly executable guide: installation, prerequisite checks, and the core profile commands are all concrete and copy-paste ready. Its weaknesses are modest — a few marketing/filler sentences that waste tokens, no error-handling or output-interpretation guidance, and an unexplained pip/npm packaging arrangement.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is compact overall but includes several unnecessary bits: the marketing opener "Intelwatch bridges the gap between hacker OSINT and B2B Sales/M&A data… in seconds", the redundant "This CLI is installed as part of the cli-anything-intelwatch package" sentence, and the filler "The output is human-readable and provides a deep breakdown of the company". Matches anchor 3 ("mostly efficient but includes some unnecessary explanation or could be tightened"); not a 4 because the padding goes beyond minor instances. | 3 / 5 |
Actionability | Commands are concrete and copy-paste ready ("pip install cli-anything-intelwatch", "node -v && npx -v", "cli-anything-intelwatch profile kpmg.fr --ai") and cover the main use cases. Minor gaps remain: no guidance on interpreting or acting on the output, no error-handling examples, and the pip-install-of-an-npx-tool arrangement is left unexplained. Matches anchor 4 ("mostly executable guidance; concrete code or commands with minor gaps"); not a 5 because of these gaps. | 4 / 5 |
Workflow Clarity | The sequence is clear: verify Node.js prerequisites ("node -v" and "npx -v" act as a checkpoint), install, then run the profile command with or without --ai. Operations are read-only, so the destructive/batch validation cap does not apply, but failure handling and post-run verification are absent. Matches anchor 4 ("clear sequence with most checkpoints present; minor validation gaps"); not a 3 because a real prerequisite checkpoint exists and the single action is unambiguous. | 4 / 5 |
Progressive Disclosure | The skill body is under 50 lines, single-purpose, and needs no external references — no references/, scripts/, or assets/ files exist in the bundle, so there is nothing to mis-link. Sections (Installation, Usage, For AI Agents, Example Scenarios) are well-organized, which per the rubric guideline earns a 5 for simple skills. | 5 / 5 |
Total | 16 / 20 Passed |