roundtable
What this produces
- Each persona gives 5 specific points (positive or negative), grounded in actual source files
- The personas hold a roundtable discussion — they compare notes, challenge each other, and converge
- A joint top 5 of problems, omissions, or improvements, with concrete fixes
Step 1: Establish personas
If the user specified personas, use those. If not, stop and ask before proceeding. Offer 4–6 suggestions tailored to the project type. Examples:
- Web app: staff engineer, UX designer, first-time user, accessibility auditor
- Language learning app: teacher in the subject, beginner student, advanced student, UX designer
- API or library: security engineer, consumer developer, technical writer, performance engineer
- CLI tool: power user, occasional user, DevOps engineer, open-source contributor
Keep it to 4 personas maximum. More than 4 produces diminishing returns and a bloated discussion.
For each persona, decide:
- Name and role (e.g. "Amira, Staff Engineer")
More from goblindegook/skills
grill-me
Use when user wants to stress-test an idea or plan, review a design, or says "grill me".
10rca
Use when asked for RCA, 5-Whys, postmortem, causal-tree analysis, or help identifying root causes for incidents, defects, outages, delays, or quality regressions.
10tdd
Use when implementing behavior changes or bug fixes where automated tests can drive the implementation, or when asked to use TDD.
8test-desiderata
Critiques and scores a project's test suite against Kent Beck's 12 test desiderata, assigning a 1–5 score to each property and surfacing the top 3 highest-impact improvements. Use this skill whenever the user wants to evaluate test quality, audit their test suite, understand what makes tests good, or get actionable feedback on how to improve their tests. Trigger on phrases like "review my tests", "how good are my tests", "test quality", "test audit", "improve my test suite", "evaluate my tests", "rate my tests", "Kent Beck", "test desiderata", or any request to assess or grade tests.
1