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 content is highly actionable, with complete prompt templates and a clear six-step process that faithfully implements the council methodology. Its main weaknesses are verbosity (motivational asides and trigger guidance duplicating the description) and a monolithic single-file structure that inlines template and example content better suited to reference files.
Suggestions
Trim the motivational prose in the intro and advisor sections, and remove or drastically shorten the 'when to run the council' section since that guidance already lives in the frontmatter description.
Move the three sub-agent prompt templates and the worked example into a references/ file (e.g. references/prompt-templates.md and references/example-session.md), keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.
Add a brief validation step after the advisor and peer-review rounds — e.g. what to do if a response is hedged, off-angle, or a sub-agent fails — so the workflow has explicit checkpoints rather than assuming ideal outputs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly functional but carries noticeable padding: motivational prose ("That answer might be great. It might be mid.", "This is the most underrated advisor", "That's the point."), and a "when to run the council" section that duplicates the frontmatter trigger guidance. It sits at anchor 3 ('some unnecessary explanation or could be tightened') rather than 4, where over-explanation would be only minor. | 3 / 5 |
Actionability | The skill provides complete, copy-paste-ready sub-agent prompt templates for the advisor, reviewer, and chairman rounds, exact output filenames (council-report-[timestamp].html, council-transcript-[timestamp].md), a specified report structure, and a fully worked example of a session. This matches anchor 5: 'copy-paste ready... specific examples cover the common cases'. | 5 / 5 |
Workflow Clarity | Six steps are clearly sequenced with parallelism, anonymization, and file outputs specified, and step 1 includes an error-recovery loop ("If the question is too vague... ask one clarifying question"). It falls short of anchor 5 because there are no explicit validation checkpoints for sub-agent outputs — no handling for weak, hedged, or failed advisor responses. | 4 / 5 |
Progressive Disclosure | There are no bundle files (no references/, scripts/, or assets/), so everything lives in a single ~190-line SKILL.md. The sections are well-organized, but ~80 lines of prompt templates plus a worked example are inlined content that would serve better as one-level-deep reference files — matching anchor 3 ('content that should be separate is inline') rather than 4. | 3 / 5 |
Total | 15 / 20 Passed |