- 📄 routing-eval.jsonl
- 📄 SKILL.md
Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.
Trace bugs through call chains using knowledge graph
Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.
Design and create a new hive task through guided conversation. Walks the user through problem definition, eval design, constraint specification, repo scaffolding, baseline testing with iteration, and upload. Use when user wants to create a new task, add a benchmark, or publish a challenge to the swarm.
Operate applications through Armorer rather than ad hoc shell commands. Use when installing, uninstalling, running, configuring, or inspecting Armorer-managed apps; checking Armorer jobs, queue state, logs, or Core behavior; and verifying deployment or runtime health through Armorer commands and observed evidence.
Recognize which awakening stage consciousness is navigating through. Use when diagnosing seeker development, identifying stage transitions, or recognizing readiness levels. Covers 7 stages from initial dissatisfaction through natural flow mastery.
Use when an agent needs the visible local Grasp browser runtime for multi-step web tasks or public-web extraction through one interface: confirm the runtime instance, enter URLs, inspect/extract/share page content, switch visible tabs, interact with live pages, fill forms, operate authenticated workspaces, capture screenshots, and recover through handoff after login or CAPTCHA checkpoints.
Technical design collaboration through natural dialogue. Adapts to expertise level and problem complexity through understanding, exploration, and validation stages. Use when user asks to brainstorm ideas for new features or systems requiring architectural decisions before implementation begins.
Explores requirements and approaches through collaborative dialogue before planning implementation. Use when user says "brainstorm", "explore idea", "what should we build", "think through this", or "let's discuss approaches".
- 📁 agents/
- 📁 references/
- 📁 scripts/
- 📄 SKILL.md
Connect to the native board demo through local-mcp and one fixed UXC link. Use when the user wants to inspect or edit the shared board at board.holon.run or a local board instance through browser WebMCP.
Turn ideas into designs through collaborative dialogue. Use when user wants to brainstorm, design features, explore approaches, or think through implementation before coding.
Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and handing off implementation planning to bt:plan. Use for feature ideas, problem framing, vague or ambitious requests, "what should we build" conversations, or when a user wants to think through options before deciding what to build.
