parcadei/discovery-interview
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
npx skills add https://github.com/parcadei/continuous-claude-v3/tree/main/skills/discovery-interviewDeep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
Batched file operations for autonomous Claude Code runs. Collapses N reads/greps/globs into one Bash round-trip — fewer output tokens, less cache growth, less wall time.
Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contradiction detection, knowledge graph, autonomous consolidation. Backed by the YantrikDB Rust engine. Install: pip install yantrikdb-mcp.
Mimeograph an expert into a SKILL.md or AGENTS.md for your agent.
Orchestration system for Claude Code — skills, shared memory, hooks, plugin
Specification + validator for the agent-skills standard — machine-readable .well-known/agent-skills/SKILL.md files that let AI assistants (ChatGPT, Claude, Perplexity, Gemini) execute capabilities on your site's behalf.
Pre-meeting intelligence pack — 6-section brief + 3/3/3 framework. Agent skill.