Implements guild-plan.md §6.1 (researcher · deep-dive) under §6.4 engineering principles: evidence is the source list — every non-trivial claim cites a source with a URL and a confidence label.
What you do
Synthesize what is actually known about a topic from multiple sources, separate claims by confidence, and surface the open questions the team still has to answer. The brief is scannable in five minutes and auditable in thirty.
Pull from at least 3–5 distinct sources; note primary vs secondary and date of each.
Group findings into claims with a confidence tag: well-established, contested, emerging, speculative.
Quote exactly when a claim is load-bearing — paraphrase only when safe.
Distinguish what is known from what is inferred; flag inferences.
End with explicit open questions the sources do not answer.
Include a TL;DR at the top (3–5 bullets) the reader can cite directly.
Output shape
Markdown file at .guild/runs/<run-id>/research/<slug>.md:
TL;DR — 3–5 bullets.
Scope & framing — what question this brief answers, what it deliberately doesn't.
Key findings — each finding tagged with confidence and linked sources.
Contested / open questions — what the sources disagree about.
Sources — numbered list: title · author · date · URL · primary/secondary.
Methodology note — one paragraph on how the brief was assembled (search strategy, exclusions).
Anti-patterns
Unsourced claims — "it's widely known that…" is not a source.
One-source synthesis — echoing a single article dressed up as research.
Editorial opinion as finding — if it's your take, label it and put it in a clearly-marked section.
No summary — a 20-page brief without a TL;DR won't be read.
Cherry-picked quotes — quoting the 10% of a source that agrees with a preferred answer.
Handoff
Return the brief path to the invoking researcher specialist. If the brief names specific options to compare, the researcher chains into researcher-comparison-table; if it names a specific paper to dig into, into researcher-paper-digest. This skill does not dispatch.
1---2name: lookatitude-guild-researcher-deep-dive3description: researcher-deep-dive4---56# researcher-deep-dive78Implements `guild-plan.md §6.1` (researcher · deep-dive) under `§6.4` engineering principles: evidence is the source list — every non-trivial claim cites a source with a URL and a confidence label.910## What you do1112Synthesize what is actually known about a topic from multiple sources, separate claims by confidence, and surface the open questions the team still has to answer. The brief is scannable in five minutes and auditable in thirty.1314- Pull from at least 3–5 distinct sources; note primary vs secondary and date of each.15- Group findings into claims with a confidence tag: *well-established*, *contested*, *emerging*, *speculative*.16- Quote exactly when a claim is load-bearing — paraphrase only when safe.17- Distinguish what is known from what is inferred; flag inferences.18- End with explicit open questions the sources do not answer.19- Include a TL;DR at the top (3–5 bullets) the reader can cite directly.2021## Output shape2223Markdown file at `.guild/runs/<run-id>/research/<slug>.md`:24251. **TL;DR** — 3–5 bullets.262. **Scope & framing** — what question this brief answers, what it deliberately doesn't.273. **Key findings** — each finding tagged with confidence and linked sources.284. **Contested / open questions** — what the sources disagree about.295. **Sources** — numbered list: title · author · date · URL · primary/secondary.306. **Methodology note** — one paragraph on how the brief was assembled (search strategy, exclusions).3132## Anti-patterns3334- Unsourced claims — "it's widely known that…" is not a source.35- One-source synthesis — echoing a single article dressed up as research.36- Editorial opinion as finding — if it's your take, label it and put it in a clearly-marked section.37- No confidence calibration — stapling "research shows" onto contested claims flattens signal.38- No summary — a 20-page brief without a TL;DR won't be read.39- Cherry-picked quotes — quoting the 10% of a source that agrees with a preferred answer.4041## Handoff4243Return the brief path to the invoking `researcher` specialist. If the brief names specific options to compare, the researcher chains into `researcher-comparison-table`; if it names a specific paper to dig into, into `researcher-paper-digest`. This skill does not dispatch.4445---46> Source: [lookatitude/guild](https://github.com/lookatitude/guild) — distributed by [TomeVault](https://tomevault.io).47<!-- tomevault:4.0:skill_md:2026-05-23 -->
Run npx skillmds@latest add tomevault-io/lookatitude-guild-researcher-deep-dive in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
researcher-deep-dive It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.