Skill | Added | Review |
|---|---|---|
intent Turn rough ideas into clear work orders before planning or building. Use when request is vague like "add a button", "make it better", "fix the thing". Triggers on ambiguous or underspecified requests. Produces a brief with scope, acceptance criteria, and stop conditions. | 95 1.00x No change in agent success vs baseline Impact 76% 1.00xAverage score across 3 eval scenarios Securityby  Passed No known issues Reviewed: Version: e876ef5 | |
bond Assesses team fitness and composes agent teams. Use when "set up a team", "team for this", "should I use agents", "design a team", "how many agents", "agent team". | 93 1.74x Agent success vs baseline Impact 94% 1.74xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e876ef5 | |
seed Generate a project-level CLAUDE.md from stack detection and user-selected rule categories. Use when starting a new project, onboarding a repo, or when the user says "seed claude.md", "create project rules", "set up CLAUDE.md", "configure this project for me", or wants to establish coding conventions. | 87 1.26x Agent success vs baseline Impact 92% 1.26xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: e876ef5 | |
shape Bridge WHAT (intent) to HOW (implementation). Use when spec is clear but approach is not. Triggers on "shape this", "how should I build", "implementation approach". | 64 1.53x Agent success vs baseline Impact 72% 1.53xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 6227365 | |
consult Simulates expert perspectives grounded in documented positions. Use when asking "what would [expert] say", "best practice", "panel", "debate", or needing domain guidance. Triggers on expert names, style requests, tradeoff questions, or "stuck on". | 84 1.54x Agent success vs baseline Impact 79% 1.54xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 6227365 |