exa-data-handling
Manages Exa search result payloads, including content scoping, caching, and token budget optimization.
Install
mkdir -p .claude/skills/exa-data-handling && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/5388" && unzip -o skill.zip -d .claude/skills/exa-data-handling && rm skill.zipInstalls to .claude/skills/exa-data-handling
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Implement Exa search result processing, content extraction, caching,Key capabilities
- →Control content extraction scope for cost management
- →Implement in-memory caching with TTL
- →Manage token budgets for LLM context windows
- →Deduplicate search results by domain and title
- →Extract structured data using summary schemas
How it works
This skill provides methods to process, cache, and format Exa search results to fit within LLM token constraints and improve performance.
Inputs & outputs
When to use exa-data-handling
- →Implement caching for search results
- →Manage token budgets for LLM context
- →Extract content from search metadata
- →Build citation pipelines
About this skill
Exa Retrieved-content Governance
Overview
Govern queries, public-web retrieval, generated summaries, citations, and downstream copies across their full retention lifecycle. Treat credentials, queries, retrieved content, generated output, spend, and destructive state as separately governed boundaries.
Prerequisites
- The target repository, environment, Exa team, product surface, and accountable owner.
- The workload's data classification, latency and freshness promise, cost ceiling, and retention policy.
- Current first-party documentation plus credentials only for a narrowly approved live check.
Current Contract
Search and Contents can return page text, highlights, summaries, links, images, and subpages; Agent and Answer can generate cited output. Public availability does not remove privacy, copyright, contractual, prompt-injection, or retention obligations. Enterprise Zero Data Retention and request-scoped HIPAA behavior require explicit enablement.
Authentication
For normal REST work, inject EXA_API_KEY from an approved server-side secret manager and send it only as Authorization: Bearer to the configured first-party Exa API host. Team Management service keys, hosted MCP OAuth or enterprise managed authorization, and payment-protocol calls are separate trust models. Never print, commit, place in a URL, or expose a credential to an untrusted client.
Instructions
- Classify query intent, target domains, returned content, generated output, and citations.
- Request the smallest content mode and character budget that supports the task.
- Apply domain, moderation, malware, prompt-injection, and personal-data controls.
- Keep source attribution and generated claims distinguishable downstream.
- Define cache, vector-store, log, backup, and deletion propagation before persistence.
- Verify downstream deletion and preserve only content-free operational receipts.
Tool Discipline
Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. Do not call Exa, run paid research, create or alter a Monitor, Webset, Agent run, Batch, team, member, API key, budget, webhook, or deployment merely because this skill was invoked.
Approval Boundaries
Require an accountable owner before live queries involving sensitive intent, production credentials, spend or rate-limit changes, forced live crawling, generated summaries, external delivery, deployment, member or key changes, schedule creation, or destructive cancellation, stopping, deletion, or revocation. Read-only repository inspection and synthetic offline validation do not authorize live vendor actions.
Failure Modes
- Highlights are source excerpts; summaries are generated and need different labeling.
- Vector databases and model traces can outlive the application cache.
- Zero Data Retention at the vendor does not delete customer-controlled downstream copies.
Output
Return the operation scope, environment, team and product surface, authorization class, contract and policy decisions, deterministic validation results, content-free identifiers, status and cost counts, risks, cleanup or rollback state, and a concise pass or fail receipt. Exclude credentials, raw queries, prompts, presigned URLs, retrieved content, generated output, and customer-derived data unless separately approved.
Example
- Store approved highlights with source URL and expiry, exclude raw full text from logs, and propagate deletion to embeddings and backups.
- Finish with request or resource IDs, assertion counts, cost and terminal state, rollback or deletion status, and the decision owner; never reproduce secrets or retrieved content.
Validation
Rerun the smallest relevant deterministic test, compare actual behavior with the requested outcome and current first-party contract, verify sensitive fields are absent from evidence, and confirm deadlines, terminal state, downstream retention, and rollback before reporting success.
References
Review the dated first-party evidence map before relying on any endpoint, parameter, search type, price, limit, beta, compliance, identity, retry, or lifecycle claim.
When not to use it
- →When real-time data is required without any caching
- →When raw, unformatted API responses are preferred
Prerequisites
Limitations
- →Cache TTL must be managed manually to avoid stale data
- →Token estimation is an approximation based on character count
How it compares
It focuses on data transformation and optimization for RAG pipelines rather than just executing the search.
Compared to similar skills
exa-data-handling side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| exa-data-handling (this skill) | 1 | 2mo | Review | Intermediate |
| langchain | 26 | 10mo | Review | Intermediate |
| reasoningbank-with-agentdb | 5 | 11mo | Review | Intermediate |
| iterative-retrieval | 10 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
langchain
zechenzhangAGI
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
reasoningbank-with-agentdb
ruvnet
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
iterative-retrieval
affaan-m
Pattern for progressively refining context retrieval to solve the subagent context problem
prompt-caching
davila7
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
agent-memory-mcp
davila7
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory-systems
davila7
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm