silbaram
UserSpec-driven development harness for AI coding agents with human-in-the-loop approval gates. Turns one-sentence ideas into approved specs, dependency-aware task graphs, and verified run logs for Claude Code, Codex, and Gemini CLI.
Categories
Indexed Skills (9)
p2a-dev-execution
Use when preparing or owning an approved Plan2Agent execution objective through implementation, verification, correction, and recorded closeout.
p2a-harness
Use when turning a concise product document into a gated Plan2Agent scope, specification, and execution-ready iteration.
p2a-intake
Use when extracting requirements, assumptions, and clarification questions from a one-sentence Plan2Agent product idea.
p2a-spec
Use when converting Plan2Agent intake output and user answers into product and implementation specs.
p2a-task-author
Use when authoring and validating a Gate C task graph draft from a Plan2Agent context bundle before canonical promotion.
p2a-task-breakdown
Use when splitting an approved Plan2Agent implementation spec into a dependency-aware task graph.
p2a-next
Use when a Plan2Agent user asks what to do next, wants to resume a project, or needs one state-based next action in an agent session.
p2a-visual-experience
Use when a Plan2Agent Gate B spec has a visual interface and needs structured screen composition, offline HTML prototype candidates, and explicit visual approval.
p2a-review
Use when reviewing a Plan2Agent spec, implementation plan, or task graph for missing decisions and execution risk.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.