Research Ops
Orchestrate ECC’s evidence-first research stack when you need current facts, option comparisons, or a recommendation backed by live web sources plus any local context you supply.
Overview
Research Ops is an agent skill most often used in Idea (also Validate and Build) that orchestrates ECC research skills for current, cited evidence and recommendations.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill research-opsWhat is this skill?
- Operator wrapper that picks among exa-search, deep-research, market-research, lead-intelligence, and knowledge-ops inste
- Triggers on “research”, “look up”, “compare”, “who should I talk to”, and “what’s the latest” with explicit stale-memory
- Supports one-off lookups and recurring monitors when a topic needs ongoing evidence
- Factors user-supplied evidence into fresh public-source synthesis and ranked recommendations
- Stacks with knowledge-ops when results should land in durable project context
- 5 named ECC skills in the research stack (exa-search, deep-research, market-research, lead-intelligence, knowledge-ops)
Adoption & trust: 3k installs on skills.sh; 210k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need an up-to-date answer or ranked choice, but ad-hoc chat or stale training data cannot safely represent what changed this week on the web.
Who is it for?
Solo builders running ECC who compare tools, markets, or contacts and want the agent to pick exa-search, deep-research, or market-research deliberately.
Skip if: Purely offline reasoning with no need for current public evidence, or teams that want a single monolithic deep-research call with no stack orchestration.
When should I use this skill?
User wants fresh facts, comparisons, enrichment, recommendations from current public evidence, or recurring monitored research—not answers from stale memory.
What do I get? / Deliverables
You get a routed research run using the right ECC search and synthesis skills, with guardrails against stale answers and an optional handoff to knowledge-ops for durable storage.
- Evidence-backed comparison or recommendation
- Optional monitor definition for repeat lookups
- Handoff brief for knowledge-ops storage
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The canonical shelf is Idea because the workflow starts with discovering what is true today before you commit scope, vendors, or outreach lists. It routes discovery through exa-search, deep-research, market-research, and related ECC skills—the core “research the landscape” moment in the solo journey.
Where it fits
Compare three AI hosting options with fresh pricing and feature pages before you pick a stack.
Rank MVP feature cuts using market-research after exa-search surfaces recent competitor launches.
Validate whether an MCP or API still matches current docs before you wire it into your agent.
Enrich companies and contacts for outbound with lead-intelligence instead of generic web blurbs.
How it compares
Use as the workflow coordinator atop ECC search skills instead of invoking deep-research or exa-search in isolation without routing rules.
Common Questions / FAQ
Who is research-ops for?
ECC users and solo builders who need fresh comparisons, enrichment, or recommendations and already have or want the repo’s native research skills wired in.
When should I use research-ops?
During idea research for competitors and trends, during validate when comparing scope or vendors, and during build when integrating tools—whenever the answer must reflect current public evidence.
Is research-ops safe to install?
Review the Security Audits panel on this Prism page and treat outbound search and any stored context as sensitive before you paste proprietary data into prompts.
Workflow Chain
Then invoke: knowledge ops
SKILL.md
READMESKILL.md - Research Ops
# Research Ops Use this when the user asks to research something current, compare options, enrich people or companies, or turn repeated lookups into a monitored workflow. This is the operator wrapper around the repo's research stack. It is not a replacement for `deep-research`, `exa-search`, or `market-research`; it tells you when and how to use them together. ## Skill Stack Pull these ECC-native skills into the workflow when relevant: - `exa-search` for fast current-web discovery - `deep-research` for multi-source synthesis with citations - `market-research` when the end result should be a recommendation or ranked decision - `lead-intelligence` when the task is people/company targeting instead of generic research - `knowledge-ops` when the result should be stored in durable context afterward ## When to Use - user says "research", "look up", "compare", "who should I talk to", or "what's the latest" - the answer depends on current public information - the user already supplied evidence and wants it factored into a fresh recommendation - the task may be recurring enough that it should become a monitor instead of a one-off lookup ## Guardrails - do not answer current questions from stale memory when fresh search is cheap - separate: - sourced fact - user-provided evidence - inference - recommendation - do not spin up a heavyweight research pass if the answer is already in local code or docs ## Workflow ### 1. Start from what the user already gave you Normalize any supplied material into: - already-evidenced facts - needs verification - open questions Do not restart the analysis from zero if the user already built part of the model. ### 2. Classify the ask Choose the right lane before searching: - quick factual answer - comparison or decision memo - lead/enrichment pass - recurring monitoring candidate ### 3. Take the lightest useful evidence path first - use `exa-search` for fast discovery - escalate to `deep-research` when synthesis or multiple sources matter - use `market-research` when the outcome should end in a recommendation - hand off to `lead-intelligence` when the real ask is target ranking or warm-path discovery ### 4. Report with explicit evidence boundaries For important claims, say whether they are: - sourced facts - user-supplied context - inference - recommendation Freshness-sensitive answers should include concrete dates. ### 5. Decide whether the task should stay manual If the user is likely to ask the same research question repeatedly, say so explicitly and recommend a monitoring or workflow layer instead of repeating the same manual search forever. ## Output Format ```text QUESTION TYPE - factual / comparison / enrichment / monitoring EVIDENCE - sourced facts - user-provided context INFERENCE - what follows from the evidence RECOMMENDATION - answer or next move - whether this should become a monitor ``` ## Pitfalls - do not mix inference into sourced facts without labeling it - do not ignore user-provided evidence - do not use a heavy research lane for a question local repo context can answer - do not give freshness-sensitive answers without dates ## Verification - important claims are labeled by evidence type - freshness-sensitive outputs include dates - the final recommendation matches the actual research mode used