Research Assistant

Structured web research framework for AI agents. Teaches your agent to conduct multi-source research, synthesize findings into actionable briefs, maintain a...

Security Scan

The skill is generally coherent with a research-assistant purpose, but it asks you (or your agent) to modify system prompts/persistent agent instructions and to set up automated triggers — combined with a detected 'system-prompt-override' pattern and unknown source, this creates persistence and prompt-injection risk that you should review before installing.

Purpose & Capability

The name/description match the instructions: the SKILL.md explains planning, searching, synthesizing, and storing briefs in a local research/ directory. Asking the user/agent to create a research folder and save briefs is consistent with the stated purpose. The only slightly disproportionate bit is the explicit instruction to add lines to AGENTS.md, SOUL.md, or the system prompt — that is plausible for integrating a workflow but is a privileged action (persisting behavior across sessions).

Instruction Scope

The instructions direct the agent (or the user) to read and write files under a research/ workspace (expected), but also to add content to the agent's system prompt or AGENTS.md / SOUL.md. That effectively modifies the agent's long-term behavior and could be used for prompt persistence. The pre-scan flagged 'system-prompt-override' pattern appears because the SKILL.md explicitly shows text intended to be copied into a system prompt; while expected for integration, it raises prompt-injection/persistence risk and should be reviewed manually before pasting into privileged prompts. The SKILL.md does not ask to read unrelated system files or secrets, which is good.

Install Mechanism

Instruction-only skill with no install spec and no code files; nothing will be downloaded or written by an installer. This minimizes supply-chain risk.

Credentials

The skill requests no environment variables, credentials, or external config paths. All required actions are local file reads/writes within a user-created research/ directory, which is proportionate to the stated function.

Persistence & Privilege

The skill itself doesn't request always: true or autonomous privileges, but it instructs the user/agent to add persistent instructions to system prompts and to set up automated 'monitor' triggers. If you follow those instructions, the behavior becomes persistent and can lead to recurring autonomous actions by the agent. This is a user-driven persistence risk rather than an automatic installer privilege, but it deserves caution.

Scan Findings in Context

[system-prompt-override] expected: The SKILL.md explicitly includes text intended to be copied into an agent system prompt (e.g., 'Add to your AGENTS.md, SOUL.md, or system prompt'). For a research-assistant blueprint this is plausible, but it is exactly the pattern that enables prompt persistence/injection so it should be treated as a security-sensitive action and reviewed before applying to privileged prompts.

What to consider before installing

This skill appears to be what it says (a structured research workflow) but contains instructions that can persistently change your agent's behavior. Before installing or copying anything into agent/system prompts: 1) Verify the author/source — there is no homepage and the publisher is unknown. 2) Never paste these instructions directly into a privileged system prompt without review; instead, implement them as a user-level guideline or in a sandboxed agent. 3) If you want automated monitoring, prefer an external scheduler you control (cron, task runner) rather than granting the agent autonomous scheduling. 4) Review and limit the agent's autonomy and outgoing channels (no webhooks, no ability to send data externally) so created briefs/monitor files cannot be exfiltrated. 5) Monitor the research/ directory after first runs and remove or restrict any persistent prompt changes if unexpected behavior occurs. If you can confirm the skill's author identity or get an explicit explanation of how automated triggers are executed (e.g., they require you to run a scheduler you control), that would increase confidence and could make this benign.

By The Agent Ledger — Subscribe for more agent skills and premium blueprints.

Turn your AI agent into a structured research analyst. No more copy-pasting search results — your agent learns to plan research, cross-reference sources, synthesize findings, and maintain an evolving knowledge base.

---

What This Skill Does

• Structured Research Protocol — Plan → Search → Evaluate → Synthesize → Store
• Research Brief Format — Consistent, scannable output for every research task
• Source Quality Scoring — Teaches your agent to evaluate and rank sources
• Research Library — Organized storage for findings that persists across sessions
• Topic Monitoring — Track evolving topics with periodic re-research
• Competitor/Market Analysis Templates — Ready-to-use frameworks

---

Setup (5 Minutes)

Step 1: Create Research Directory

research/
├── README.md          ← Library index (auto-maintained)
├── briefs/            ← Completed research briefs
├── monitoring/        ← Topics being tracked over time
└── templates/         ← Custom research templates (optional)

Step 2: Create research/README.md

# Research Library

## Recent Briefs
<!-- Agent maintains this list automatically -->

## Monitored Topics
<!-- Topics being tracked with periodic updates -->

## Quick Stats
- Total briefs: 0
- Active monitors: 0
- Last research: never

Step 3: Add to Your Agent Instructions

Add to your AGENTS.md, SOUL.md, or system prompt:

## Research Protocol

When asked to research something:
1. Read `research/README.md` for existing work on this topic
2. Follow the Research Protocol below
3. Save the brief to `research/briefs/YYYY-MM-DD-<slug>.md`
4. Update `research/README.md` index

---

Research Protocol

Phase 1: Plan

Before searching, define:

• Research Question — What specifically are we trying to answer?
• Scope — Broad survey or deep dive? Time range? Geography?
• Sources Needed — How many independent sources for confidence?
• Output Format — Brief, comparison table, recommendation, or raw dump?

Phase 2: Search & Collect

Execute searches with these principles:

• Multiple queries — Rephrase the question 2-3 ways for coverage
• Source diversity — Mix official sources, industry analysis, community discussion
• Recency check — Note publication dates; flag anything older than 6 months
• Contradiction hunting — Actively look for sources that disagree

Phase 3: Evaluate Sources

Score each source on:

Factor	Weight	Criteria
Authority	High	Known publication? Expert author? Official source?
Recency	High	Published within relevant timeframe?
Specificity	Medium	Concrete data/examples vs. vague claims?
Corroboration	Medium	Do other sources confirm this?
Bias Check	Low	Obvious commercial or political motivation?

Drop sources scoring poorly on Authority + Recency. Flag but keep sources with clear bias if they contain unique data.

Phase 4: Synthesize

Structure findings into a Research Brief (see format below). Key rules:

• Lead with the answer — Don't bury the conclusion
• Quantify when possible — Numbers > adjectives
• Flag uncertainty — Clearly mark low-confidence claims
• Note gaps — What couldn't you find? What needs deeper research?

Phase 5: Store & Index

Save to research/briefs/YYYY-MM-DD-<slug>.md and update the library index.

---

Research Brief Format

# [Research Question]

**Date:** YYYY-MM-DD
**Requested by:** [context]
**Confidence:** High / Medium / Low
**Staleness risk:** [when this research might become outdated]

## TL;DR
[2-3 sentence executive summary with the key finding]

## Key Findings

### Finding 1: [Title]
[Detail with supporting evidence]
- Source: [name] ([link]) — [date]
- Confidence: High/Medium/Low

### Finding 2: [Title]
[Detail with supporting evidence]
- Source: [name] ([link]) — [date]
- Confidence: High/Medium/Low

[Continue as needed]

## Data Points
| Metric | Value | Source | Date |
|--------|-------|--------|------|
| [key stat] | [value] | [source] | [date] |

## Contradictions & Caveats
- [Any conflicting information found]
- [Limitations of this research]

## Knowledge Gaps
- [What we couldn't find]
- [What needs deeper investigation]

## Sources
1. [Full citation with URL and access date]
2. [...]

## Recommendations
- [Actionable next steps based on findings]

---
*Research conducted by AI agent using the Research Assistant skill by [The Agent Ledger](https://theagentledger.com)*

---

Topic Monitoring

For topics that evolve over time (market trends, competitor moves, regulatory changes):

Setup a Monitor

Create research/monitoring/<topic-slug>.md:

# Monitoring: [Topic Name]

**Started:** YYYY-MM-DD
**Frequency:** [daily / weekly / bi-weekly]
**Search queries:** 
- "[query 1]"
- "[query 2]"
**Alert triggers:** [what constitutes a notable change]

## Updates

### YYYY-MM-DD
- [What changed since last check]
- [New data points]
- [Assessment: significant / minor / no change]

Periodic Check Protocol

When running a monitoring check:

1. Read the monitor file for context and previous findings
2. Run the saved search queries
3. Compare new results against last update
4. Only log if something changed or enough time has passed
5. Flag significant changes prominently

Integration with Heartbeats/Cron

Add to your HEARTBEAT.md or set up a cron:

## Research Monitors
Check research/monitoring/ for topics due for refresh.
Only check topics whose frequency interval has elapsed.

---

Specialized Templates

Competitor Analysis

# Competitor Analysis: [Company/Product]

**Date:** YYYY-MM-DD

## Overview
| Factor | Competitor | Us |
|--------|-----------|-----|
| Pricing | | |
| Features | | |
| Market position | | |
| Strengths | | |
| Weaknesses | | |

## Their Recent Moves
- [Latest product launches, pivots, funding]

## Opportunities
- [Gaps we can exploit]

## Threats
- [Where they're ahead]

Market Sizing

# Market Analysis: [Market Name]

**Date:** YYYY-MM-DD

## Market Size
- **TAM:** $X ([source])
- **SAM:** $X ([source])
- **SOM:** $X (our estimate)
- **Growth rate:** X% CAGR ([source])

## Key Players
| Player | Est. Share | Notes |
|--------|-----------|-------|
| | | |

## Trends
1. [Trend + supporting evidence]

## Entry Barriers
- [What makes this hard]

## Our Angle
- [How we'd compete]

Decision Research

# Decision: [What we're deciding]

**Date:** YYYY-MM-DD
**Decision needed by:** YYYY-MM-DD

## Options
### Option A: [Name]
- **Pros:** 
- **Cons:**
- **Cost:** 
- **Risk level:** High/Medium/Low

### Option B: [Name]
- **Pros:**
- **Cons:**
- **Cost:**
- **Risk level:** High/Medium/Low

## Recommendation
[Which option and why]

## What would change our mind
[Conditions that would flip the recommendation]

---

Customization

Adjust Research Depth

Add to your agent instructions:

Research depth levels:
- **Quick scan** — 3-5 sources, 5 minutes, key facts only
- **Standard brief** — 8-12 sources, full brief format
- **Deep dive** — 15+ sources, include academic/primary sources, extended analysis
Default to standard unless specified.

Domain-Specific Research

For specialized fields, add context:

When researching [your domain]:
- Prioritize sources from: [trusted sources list]
- Key metrics to always check: [domain-specific KPIs]
- Common pitfalls: [domain-specific biases to watch for]

Citation Style

Citation preference: [choose one]
- Inline links (default) — [Source Name](url)
- Numbered footnotes — [1], [2], etc.
- Academic — Author (Year). Title. Publication.

---

Troubleshooting

Issue	Fix
Research is too surface-level	Increase depth level; add "find primary sources" to prompt
Too many sources, no synthesis	Emphasize Phase 4; ask for "TL;DR first, then details"
Findings are outdated	Add recency filter: "only sources from last 6 months"
Agent dumps raw search results	Reinforce the brief format; remind to synthesize, not copy
Monitor checks too frequent	Adjust frequency in monitor file; use staleness risk to guide
Research library getting messy	Run periodic cleanup: archive briefs older than 6 months

---

Integration with Other Agent Ledger Skills

• Solopreneur Assistant — Feed research into business decisions and opportunity scoring
• Daily Briefing — Include monitor alerts in daily briefings
• Project Tracker — Link research briefs to project milestones
• Memory OS — Store key research insights in long-term memory

---

Part of the free skill library by The Agent Ledger. Subscribe for premium blueprints, playbooks, and the complete agent configuration guide.

License: CC-BY-NC-4.0

DISCLAIMER: This skill was created by an AI agent. It is provided "as is" for informational and educational purposes only. It does not constitute professional, financial, legal, or technical advice. Review all generated files before use. The Agent Ledger assumes no liability for outcomes resulting from use. Use at your own risk.