Cognitive systems skill for reasoning, memory, and agent behavior; use when designing agent workflows or mental-model tooling.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Domain: agent | Depth: axiom
| Library | Purpose |
|---|---|
| torch | Attention, embeddings |
| numpy | Probability and belief arrays |
| scipy | Statistical reasoning |
| chromadb | Semantic memory backend |
agents/skills/cognitive.py
chain_of_thought(problem, steps) — structured reasoning scaffoldconfidence(logits) — softmax confidence from raw scoresbayesian_update(prior, likelihood, evidence) — posterior beliefattention_score(query, keys) — dot-product attention weightssummarize_context(turns, max_tokens) — compress working memoryretrieve_relevant(concept, memory, n) — semantic memory retrievalNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
The English summary is being prepared. Showing the original description.
Algorithm design and analysis skill for DSH; use when working on optimization, data structures, or computational procedures.
The English summary is being prepared. Showing the original description.
Design and implement scalable API gateways, RESTful APIs, GraphQL endpoints, WebSocket handlers, and microservice communication patterns. Use when creating API routes, designing endpoints, implementing middleware, or setting up service mesh architectures.
The English summary is being prepared. Showing the original description.
Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates all candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".
The English summary is being prepared. Showing the original description.
Check your work with a verification subagent. Spawns a verifier that reviews diffs, runs builds and tests, and evaluates correctness. Use when asked to "check work", "verify changes", "self-verify", "/check", "/verify", "/check-work", or "/self-verify".
The English summary is being prepared. Showing the original description.
CI/CD pipeline design, GitHub Actions workflows, deployment automation, infrastructure as code, and release management. Use when setting up CI/CD, automating deployments, configuring build pipelines, or managing releases.
The English summary is being prepared. Showing the original description.