research-synthesis

research-synthesis is a skill for Claude Code, Codex from TrentM6/baseline-core. It costs 35 tokens per session (2,717 once invoked), scanned A, original, MIT.

A method for studying users and turning interviews, tests, and other evidence into useful findings. It covers learning what people need, checking proposed solutions, and comparing alternatives.

In plain words
What is it for?
Use it to plan interviews, conduct user research, analyze competitor products, evaluate designs, and write research reports.
Why use it?
It prevents recommendations based only on assumptions or opinions. It connects observations to clear decisions and next steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is Follow the [Workflow Orchestration Pattern](../../frameworks/workflow-orchestration.md) for the universal workflow approach. Below are the research-specific det.

Good fit Use it to plan interviews, conduct user research, analyze competitor products, evaluate designs, and write research reports.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/TrentM6/baseline-core
agentmods
npx agentmods add skills/trentm6/baseline-core/research-synthesis

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for research-synthesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/trentm6/baseline-core/research-synthesis/github.svg)](https://agentmods.dev/skills/trentm6/baseline-core/research-synthesis)
Your own site
<a href="https://agentmods.dev/skills/trentm6/baseline-core/research-synthesis"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/research-synthesis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for research-synthesis

Your own site · 80×15
<a href="https://agentmods.dev/skills/trentm6/baseline-core/research-synthesis"><img src="https://agentmods.dev/badge/skills/trentm6/baseline-core/research-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.02717
Opus 5.5 $0.00014 $0.01087
Sonnet 5.5 $0.00007 $0.00543
Haiku 4.5 $0.00003 $0.00272

Measured yesterday against content hash 4da4bfe6de40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

research-synthesis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/research-synthesis/research-synthesis-skill.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research & Synthesis

Research & Synthesis is the discipline of understanding users deeply through structured inquiry and turning raw observations into actionable insights. It spans discovery, validation, and synthesis — from uncovering user problems to testing whether solutions resonate.


Core Principles

  1. Research before recommendations. Never skip straight to solutions. Understand the problem space first — the best recommendations come from deep understanding.

  2. Evidence over opinion. Ground every insight in data. Quote users. Show your work. If you can't point to evidence, it's an assumption.

  3. Actionable or it's not an insight. Every finding must answer "so what?" If it doesn't lead to a decision or action, dig deeper or reframe.

  4. Honest findings, even when uncomfortable. Report what you found, not what stakeholders want to hear. Clients hire you for truth, not validation.

  5. Appropriate rigor for the stakes. Match methodology to the question. Don't over-engineer small decisions or under-research big bets.

  6. Past behavior, not hypotheticals. People can't predict what they'll do. Ask what they actually did. "Tell me about the last time..." beats "Would you ever..."

  7. Follow the energy. When participants lean in or get animated, go deeper. That's where the real insights live.

Industry Principles

  1. The right method for the right question. Discovery for understanding problems. Validation for testing solutions. Don't conflate them.

  2. Sample size matters, but not infinitely. You'll hear the main themes after 5 interviews. More adds nuance but not new themes.

  3. Synthesis is where value is created. Raw notes aren't insights. The work of organizing, patterning, and interpreting is where research earns its value.

  4. Confidence levels matter. "5 of 5 users struggled" is different from "2 of 5 mentioned." State your confidence.

  5. Research is a team sport. Include stakeholders in synthesis. Insights they help discover stick better than insights you present.

Read the full file on GitHub · 309 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 309 lines · 35 tokens per session scan A 4da4bfe6de40

Subscribe to this mod's changes

research-synthesis is a skill published in the GitHub repository TrentM6/baseline-core (23 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 2,717 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-17.

Related

research-synthesis compared with skills from other repositories

research-synthesis next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
research-synthesisTrentM6/baseline-coreSkill232d agoMITA35Claude Code, Codex
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code