Content
81%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 strong, highly actionable skill body with a clear five-step workflow, pre-flight validation, and error recovery, held back mainly by redundant content. Consolidating the duplicated setup/error tables and the repeated `opencli doctor` explanations would lift both conciseness and progressive disclosure.
Suggestions
Merge the 'Common setup issues' table (Step 1) with the 'Error Reference' table at the end — three of four rows are duplicates; keep one canonical table and point to it from the other section.
Fold Step 5 (Diagnostics) into the doctor coverage in Step 1 or the Error Reference, since `opencli doctor` and what it checks are explained twice.
Move the detailed extension-installation steps out of SKILL.md into references/commands.md (where they already appear) and keep only a one-line pointer plus the verify command in the body, reducing token cost and the duplication across files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean tables and commands, but contains genuine redundancy: the "Common setup issues" table and the "Error Reference" table repeat three of four rows (Extension not connected, No session, AuthRequiredError), and `opencli doctor` is explained in both Step 1 and Step 5. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim level 4. | 3 / 5 |
Actionability | Commands are copy-paste ready and cover the common cases — `opencli linkedin timeline --limit 20 -f json`, `opencli linkedin search "portfolio manager" --location "New York" --limit 15 -f json`, `--details` for full listings — plus an install command, a format-flag table, and named output columns, matching the fully-executable top anchor. | 5 / 5 |
Workflow Clarity | The five-step sequence (setup → identify → execute → present → diagnostics) has explicit validation and feedback loops: a pre-flight probe branching on READY/NOT_INSTALLED/SETUP_NEEDED, the rule "run `opencli doctor` before any other command if unsure", and an error table with fixes for retry. As a read-only skill, the destructive/batch validation cap does not apply. | 5 / 5 |
Progressive Disclosure | `references/commands.md` is a real, well-signaled, one-level-deep reference with clear guidance on when to read it, and the body is a reasonable overview. However, the setup and extension-install content is duplicated between SKILL.md and references/commands.md rather than split, a minor organization gap that keeps this just below the top anchor. | 4 / 5 |
Total | 17 / 20 Passed |