Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Researcher Skill · joelmeaders | DecimalAI

researchby joelmeaders

Researcher Skill

joelmeaders/researcher

Source joelmeaders/agent-skill-builder ↗License Not recorded

A comprehensive research assistant skill that enables agents to gather, analyze, and synthesize information from multiple sources.

NewMaintained

Automatic

Research pack

Last verified 8/3/2026

What it changes

Passed 7 of 15 test cases with the skill, and 7 of 15 without it.

Without skill45%

With skill45%

Checks it passed that the model alone missed

The call_subordinate invocations set reset=true.
The call_subordinate invocations set profile='researcher'.
Each call_subordinate invocation sets profile='researcher'.

and 5 more in the full report

4 fixed6 passed either way8 still failing4 broke

Pass-rate lift: 0 pp
Tokens: +71%
Agent turns: 0%
Response time: +3%

Model gemini-3.6-flashMeasured 8/3/2026v110 of 22 cases passed with skill · 15 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/joelmeaders-researcher/SKILL.md https://app.decimal.ai/s/joelmeaders-researcher/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add joelmeaders-researcher, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/joelmeaders-researcher/ and pins it in .decimal/skills.lock

decimalai skills add joelmeaders-researcher

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/joelmeaders-researcher/SKILL.md https://app.decimal.ai/s/joelmeaders-researcher/SKILL.md

Raw file: /s/joelmeaders-researcher/SKILL.md ↗ · machine-readable summary at /s/joelmeaders-researcher.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

What tool should be utilized during research analysis when processing raw numerical survey data or generating benchmark visualization tables?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies code_execution_tool for processing data.	Missed	Passed

case-16 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md280 lines6 filesincludes scripts

Researcher Skill

Overview

This skill enables AI agents to perform comprehensive research tasks by leveraging web search, document analysis, information synthesis, and subagent delegation capabilities. The researcher skill transforms raw information into structured, actionable insights with proper citations.

When to Use

Activate this skill when the user needs:

Deep research on any topic
Fact-checking and verification of claims
Comparative analysis between products, technologies, or approaches
Competitive analysis and market research
Literature reviews and academic research
Data analysis and interpretation
Comprehensive reports with sources

Capabilities

Web Search & Information Retrieval
- Search multiple sources simultaneously
- Filter by recency, relevance, and source credibility
- Extract key information from search results
Document Analysis
- Parse and analyze web documents, PDFs, and text
- Extract key findings, statistics, and insights
- Identify patterns and trends across sources
Information Synthesis
- Combine findings from multiple sources
- Identify consensus and conflicting viewpoints
- Create coherent narratives from disparate data
Fact-Checking
- Verify claims against multiple reliable sources
- Identify misinformation and biases
- Provide confidence levels for claims
Report Generation
- Structure findings into clear sections
- Include proper citations and sources

Track record

Benchmark

7 / 15

test cases passed, vs 7 / 15 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

joelmeaders / agent-skill-builder

researcher/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 5 files · scripts

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Researcher Skill

Overview

When to Use

Capabilities

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills