Research Ops
Research current facts with Muse the evidence-first way: classify the ask, take the lightest useful path (exa-search, deep-research, market-research, lead-intelligence), report with explicit evidence boundaries and dates.
- What
- Research current facts with Muse the evidence-first way: classify the ask, take the lightest useful path (exa-search, deep-research, market-research, lead-intelligence), report with explicit evidence boundaries and dates.
- Cost
- Free
- Needs
- none to install. Pure workflow guidance; having exa-search, deep-research, or market-research available makes the lanes real.
- Level
- Beginner
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: Research Ops, the operator wrapper around the ECC research stack, for when you want fresh facts, comparisons, enrichment, or recommendations built from current public evidence. It is explicit that it does not replace deep-research, exa-search, or market-research: it tells you when and how to use them together. The workflow starts from what the user already supplied, normalizing it into already-evidenced facts, needs verification, and open questions, instead of restarting analysis from zero. Then it classifies the ask into one of four lanes, quick factual answer, comparison or decision memo, lead or enrichment pass, or recurring monitoring candidate, and takes the lightest useful evidence path first: exa-search for fast discovery, deep-research when multi-source synthesis matters, market-research when the outcome should end in a recommendation, lead-intelligence when the real ask is target ranking. Guardrails are the point: never answer current questions from stale memory when fresh search is cheap, and always separate sourced facts from user-provided evidence, inference, and recommendation. The output format is fixed with QUESTION TYPE, EVIDENCE, INFERENCE, and RECOMMENDATION sections, freshness-sensitive answers carry concrete dates, and the workflow ends by deciding whether the task should become a monitor instead of a repeated manual search. By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: it only works if you actually have the underlying search skills available; a heavyweight research pass for an answer sitting in local code is waste. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Research Ops is a free Muse skill that teaches your Muse to research current facts the evidence-first way, classifying the ask and taking the lightest useful path among exa-search, deep-research, market-research, and lead-intelligence, then reporting with explicit evidence boundaries and dates. It starts from what you already supplied, normalizing it into evidenced facts, needs verification, and open questions.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 4eb71d9Pinned version: install the code at commit 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Use "Research Ops" with your Muse. Prerequisites: none to install. Pure workflow guidance; having exa-search, deep-research, or market-research available makes the lanes real. 1. Open the skill: https://raw.githubusercontent.com/affaan-m/ECC/4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2/skills/research-ops/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Research this: [your question]. Classify the lane first." 3. Review the output with its evidence boundaries, and ask Muse whether this should become a recurring monitor. Tip: include any evidence you already have in your first message; the workflow factors it in instead of starting from zero. Safety: a skill is plain-text instructions; it runs nothing by itself. Review generated commands before running them.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 4eb71d9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 21, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.