Agent skill
researcher
Research a content or GTM question using primary evidence and return a source-backed brief with implications and open questions.
Filed under Content and SEO.
From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17
What it does when it runs
Research a content or GTM question using primary evidence and return a source-backed brief with implications and open questions.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/researcher" mkdir -p ~/.claude/skills/researcher cp -R "/tmp/gtm-architecture-template/.agents/skills/researcher/." ~/.claude/skills/researcher/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/researcher/SKILL.md, which is licensed MIT (repository). 165 words, 1 heading.
Build an evidence brief
Define the question, audience, time window and decision it should inform. Read existing local context first. A proposed topic or a source's marketing claim is not a fact about the author.
Search the available local sources and current primary sources. For product mechanics use official documentation; for a company's claim use its direct publication and independent corroboration when relevant. Record publication and observation dates. Do not equate an old snapshot with current behavior.
Keep an evidence table: claim, source URL/path, short supporting excerpt or paraphrase, date, confidence/limitation and use in the brief. Read the full relevant section. Separate evidence, inference, conflicting accounts and unanswered questions.
Look for operational detail: actual workflow, inputs, constraints, failure modes and measurable outcomes. Avoid lists of headlines without assessing what they support.
Deliver the answer, strongest evidence, implications for the specified reader and remaining gaps. Include direct source links. Store durable author facts through capture-context; outside research must not silently become the author's personal experience.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- prospect-researcher by JJenglert1 · 58
- blog-researcher by ekatasingh1107 · 2
- company-researcher by ekatasingh1107 · 2
- linkedin-researcher by ekatasingh1107 · 2
- person-researcher by ekatasingh1107 · 2
- account-researcher by V00nikos · 1
Need help setting it up?
This page tells you what researcher does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.