research
Answer a bounded question with current cited evidence. Triggers: "research", "investigate", "find evidence".
How do I install this agent skill?
npx skills add https://github.com/boshu2/agentops --skill researchIs this agent skill safe to install?
- Gen Agent Trust Hubwarn
The research skill automates deep codebase exploration and knowledge synthesis. While highly functional, it contains shell command templates that directly interpolate user-provided topics, which could lead to command injection if malicious topics are provided. It also accesses files in the global ~/.claude directory and manages multiple sub-agents, creating a significant security surface that requires careful oversight.
- Socketwarn
1 alert: gptAnomaly
- Snykwarn
Risk: MEDIUM · 1 issue
- Runlayerwarn
5/13 files flagged
- ZeroLeakspass
Score: 93/100 · 2 sections analyzed
What does this agent skill do?
Research
Answer one bounded question with current evidence. Research informs a caller; it does not select work, approve a plan, mutate lifecycle state, or decide what happens next.
Contract
- State the question, decision it informs, scope, non-goals, and evidence required for a useful answer.
- Search the smallest relevant local sources. For changing external facts, use current primary sources.
- Verify structural or semantic-search leads against authoritative content.
- Separate observation, inference, contradiction, and unknown.
- Lead with the answer and cite every load-bearing claim.
- Report unchecked scope and stop.
Use the current agent inline by default. Parallel readers or alternate runtimes are optional execution choices only when the caller authorizes them. Prior research, CASS, MS, codebase recon, and pattern mining are advisory sources, not required phases.
Output
For a quick question, return the cited answer directly. When the caller asks for a durable artifact, write one report containing:
- question and scope;
- answer;
- evidence references;
- contradictions and unknowns;
- checked and unchecked areas.
Do not emit approval, confidence gates, retry instructions, owner, next action, or delivery state.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/boshu2/agentops/research">View research on skillZs</a>