Agent skills

Conduct and maintain source-grounded research for a concrete Workbench workflow.

For NKR opinion — result and recommendation: orders norm, burden of proof, and counterargument; result: review product with risk and next...

Implement and consume the NLWeb /ask REST endpoint — request shape (GET/POST, query-string and v0.55 structured body), SSE streaming…

Configure NLWeb authentication and multi-tenant deployments — OAuth providers (GitHub, Google, Microsoft, Facebook), session storage, the…

Integrate NLWeb with ChatGPT's Apps SDK — the Node.js MCP server in `openai-apps-sdk-integration/`, the `nlweb-list` tool, the React…

NLWeb development patterns — the mixed-mode programming philosophy, FastTrack vs Analysis parallel paths, config file precedence and the…

Expose NLWeb as an MCP (Model Context Protocol) server — JSON-RPC 2.0 endpoint at /mcp, the `ask` / `list_sites` / `who` tools, MCP…

Customize NLWeb's LLM prompts and per-Schema.org-type behavior via `prompts.xml` and `site_types.xml` — covers the `<promptString>`…

Prepare and structure site content as Schema.org JSON-LD for NLWeb ingestion — covers the supported types (Recipe, Product, Movie, Event…

Design and implement NLWeb tools — the per-Schema.org-type handlers that turn a query into a specialized response (search, item_details…

Guide reliable deployments without CI/CD platforms (GitHub Actions / GitLab CI).

Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

This skill has no YAML frontmatter at all.

For "No High Risk Confirmed" — the end-to-end roadmap: outlines standards, burden of proof, and counterarguments; result: test product…

Enter "offline mode" — for security reasons, do NOT use any tool or command that touches the internet or an external network.

Silent mode — do the work with NO conversational talk.

Never burn time blocking on a wait. Forbids foreground `sleep`/idle-polling to wait for a long job (a download, fetch, build, backtest…

Use when implementing, testing, releasing, handing off, or reviewing a multi-step workflow where local success could hide a broken…

Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind…

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

Build Node.js backends for Medusa v2 — Express middleware chain, MikroORM entity patterns, PostgreSQL connection pooling, async patterns…