Content
47%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 brief, well-sectioned stub that delegates everything substantive to an external repository. It is efficient in length but provides almost no executable guidance — a single clone command — and no workflow or validation structure, so it cannot function as a usable skill on its own.
Suggestions
Inline the core usage steps (how the 10 agents are orchestrated, how to invoke the skill, what output to expect) instead of deferring entirely to the external repository.
Remove the duplicated frontmatter description in the '## Description' section and the 'battle-tested' marketing phrase to eliminate redundant tokens.
Add at least a minimal sequenced workflow with a validation checkpoint (e.g., verify the repo is cloned and the entrypoint runs) before pointing users to external instructions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is short and mostly lean, but the '## Description' section restates the frontmatter description verbatim and repeats the 'battle-tested with real case studies' fluff — minor padding that could be trimmed. This matches anchor 4 (efficient with minor instances of over-explanation) rather than anchor 5, where every token would earn its place. | 4 / 5 |
Actionability | The only concrete command is 'git clone https://github.com/sstklen/infinite-gratitude'; everything else is high-level direction ('refer to the official repository for installation and usage instructions') with no specific steps for actually executing research. This matches anchor 2 (minimal concrete guidance, missing the steps to execute), not 3, because there is no partial workflow — just a pointer. | 2 / 5 |
Workflow Clarity | There is a rough hint of sequence (clone the repo, refer to it for usage) but no defined steps for the research workflow itself and no validation checkpoints. This matches anchor 2 (rough sequence with many gaps, steps poorly defined); it is above anchor 1 only because the clone command gives a starting action. | 2 / 5 |
Progressive Disclosure | The skill is under 50 lines with clean, well-labeled sections (Description, When to Use, How to Use) and no nested internal references, which per the rubric can support a high score. It falls short of 5 because all substantive content is deferred to an external URL rather than organized one-level-deep bundle files, leaving the skill body without any locally actionable detail. | 4 / 5 |
Total | 12 / 20 Passed |