Results for “context-poisoning”

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.

Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, and a verification plan. Load when prompts are underspecified, the agent is missing key files or decisions, the user says "use the right context", "here's the repo", or when work is drifting due to missing constraints. Also triggers on "context engineering", "gather context", "what do you need from me", "before you start". Not for cross-session continuity (use memory-startup/memory-recall).

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Optimizes agent context setup by structuring rules, specs, source files, error output, and conversation history to improve output quality.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Use this skill for context gathering, file triage, source maps, assumptions, task framing, prompt hygiene. Trigger when the task involves programming work related to Context Engineering, production implementation, audits, debugging, strategy, or validation.

Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas. Use when context is growing large, responses are slow, or switching between unrelated tasks. Covers context analysis, compacting, targeted pruning, MCP-first strategies, and focused scoping by area.

`task-agent`/`review-agent`: use when image layers, build context, runtime user, secrets, health checks, shutdown, or provenance change; skip when container behavior is unaffected.

Progressively refines context retrieval in multi-agent workflows to solve the subagent context problem.

Explains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.

Build a task-aware context bundle (relevant code + applicable standards + related past decisions) via the local RAG index, capped at a token budget. Use at the start of any implementation/refactor/debug task instead of reading files blindly. Replaces "read whole file" with "retrieve the function + callers + rules + prior ADR."

Agente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.