AVIDS2

Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.

Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether session_start is useful.

Use when choosing or confirming tech stack for a product or feature: frontend framework, database, auth, email, payments, hosting, search, or agent runtime. Applies AVID defaults (React/Vue, SQLite→Postgres/Supabase, Resend, Stripe, Playwright, Tavily,…

Use when starting product, feature, build, stack, research, agent-framework, or implementation work. Loads AVID personal workflow defaults and skill routing. Defaults are advisory and scene-dependent — not absolute hard blocks. Skip or adapt when the…

Use when choosing or implementing agent runtimes: LangGraph workflows, Pi / pi-ai / embedded Pi harness agents, thin provider SDK loops, model API wire protocol (Chat Completions vs Responses vs Messages), or "which agent framework" decisions. Scene-based…

Prefer when a required CLI, library, MCP, or skill is missing. Install official or best community option when practical. Advisory — hand-roll is allowed with an explicit reason (license, abandoned, fundamental mismatch, user order).

Use for high-stakes decisions: architecture forks, build-vs-buy, competitive response, major refactors, or when the user wants multi-agent debate. Spawns diverse perspectives (or Codex second opinion) and synthesizes a recommendation. Do NOT use for trivial…

Prefer before greenfield products, new verticals, or "做个X/从零做" work. Advisory research + grill-me + MVP cut. Strongly recommended to avoid blind builds, but not an absolute block if the user already has research/spec or explicitly wants a spike. Do NOT use…

Prefer before self-implementing a non-trivial library, service, or subsystem. Advisory find-before-found. Not a hard block on prototypes the user accepts.

Use when designing knowledge bases, RAG, wiki, knowledge graphs, memory for agents, or "how should we store docs for humans vs agents". Produces a clear consumer/form/retrieval decision. Avoids buzzword soup. Do NOT use for ordinary app CRUD databases.

Use for open-ended questions that need a bounded, source-grounded report with a plan, parallel retrieval, full-page reading, claim verification, uncertainty tracking, and citations. Do not use for a single factual lookup or a project-only evidence search.

Use for a bounded, read-only BidPilot tender investigation that must cite traceable official sources, verify dates and eligibility, deduplicate candidates, and end with a short decision-ready shortlist. Load deep-research for the generic research runtime; do…

Use only when the user explicitly asks to create, continue, revise, or perform final compliance review of a bid response or technical proposal for a known project. Do not use for opportunity discovery, market research, notice lookup, general questions,…

Research external sources for a bid project, discover confirmed tender attachments safely, and store only user-approved evidence or artifacts with citations.

Always resolve outline section_key before drafting or writing chapter content.

Use this when implementing, refactoring, or debugging code in the DocPilot/BidPilot repository. It loads the project's stack, architecture constraints, required docs, and verification workflow.