Content
88%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: every step is executable with concrete URLs, commands, paths, and an output template, and the batch workflow includes explicit validation and blocker-reporting loops. The main weaknesses are mild verbosity in a couple of enumerations and missed opportunities to move detail (report table spec, voice rules) into a reference file.
Suggestions
Trim the 'Solt Wagner-style' example to one line ('e.g., a curated list of creative tools and resources') instead of enumerating seven tool categories, and compress the report-table column specification.
Consider moving the Report table structure and the Voice use/avoid lists into a reference file (e.g., references/report-format.md, references/voice-rules.md), keeping SKILL.md as the overview with one-level-deep pointers.
The voice-guidance material is split across 'Calibrate Voice From 100 Posts' and 'Voice'; merging or cross-linking the overlapping rules (e.g., avoid-list vs. 'match the moves') would remove repetition and tighten token usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense with project-specific operational guidance and avoids explaining concepts Claude already knows, but a few passages could be trimmed — notably the "Solt Wagner-style list… such as image generators, dither tools, mockup tools, Framer templates, dock widgets, motion tools, and gradient tools" enumeration and the long report-table column specification. This fits the efficient-with-minor-trimmable-instances anchor, not the every-token-earns-its-place anchor at 5. | 4 / 5 |
Actionability | Guidance is fully executable: exact URLs (https://x.com/i/bookmarks, the from:<handle> search URL), a copy-paste-ready commit command, a concrete `git diff --check -- data/x-growth/bookmark-quote-posts/YYYY-MM-DD.md` validation, dated file paths, and a complete output-file template. It is not the minimal-hints level of 4 because specific examples cover the common cases end to end. | 5 / 5 |
Workflow Clarity | The Start → Calibrate Voice → Collect → Draft → Verify → Report sequence is explicit with a pre-commit validation checklist ("Ensure every draft has a source URL", git diff --check) and error-recovery paths ("If X is logged out, CAPTCHA-blocked… stop and report the exact blocker", "do not invent a commit; report the blocker"). Despite being a batch operation, validation and feedback loops are present, so the batch-cap at 3 does not apply. | 5 / 5 |
Progressive Disclosure | The skill is a well-organized single file with clear section headers and no bundle files to reference, so navigation is easy. However, at ~170 lines some self-contained detail — the report-table column spec and the voice avoid-lists — could be split into a one-level-deep reference file, which keeps it at good-structure-with-minor-gaps rather than the ideal split of the 5 anchor. | 4 / 5 |
Total | 18 / 20 Passed |