agentleFS
DurdeuVladDurdeuVlad/persona-write/.claude/skills/persona-research/SKILL.md

persona-research

Skill1 starsChanged 42 days agoMITView on GitHub

Gather what a text depends on before it is written - the genre and locale norms for the reader, and a check of each claim against the supplied sources. Returns a short research note with sources and a claim status table. Use before /persona-write or /persona-localize when facts or conventions matter.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    unverified: - no support found; flag it for the user

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Persona Research

Purpose

Writing goes wrong when the writer guesses: what the genre looks like, what the reader expects, whether a claim is true. This skill finds out first and hands the result to the writing step.

The writer this skill makes

A writer who checks before drafting. They look at what good examples of the genre look like for this reader, confirm each claim against a source, and say which claims they could not confirm.

Inputs

  • the topic or draft
  • the reader and the genre
  • source material the user supplied (files, notes, data)
  • the language and locale if it differs from English

What to research

  1. Genre and locale norms. What strong examples of this genre look like for this reader in this locale: structure, length, register, what is expected and what is out of place. Search the web for real examples or official guidance when none is supplied.
  2. Claims. List every factual claim in the draft or plan. For each, find the source in the supplied material.
  3. Gaps. Name what the reader will need that no source supplies.

Claim status

Mark each claim with exactly one status:

  • verified - found in a supplied source (cite the file or page)
  • user-stated - given by the user, not in any source
  • found - confirmed on an external source (cite the link)
  • unverified - no support found; flag it for the user

User-stated and unverified claims are listed for the user to confirm. They are not silently dropped or silently kept.

Output

A research note of at most one page:

  1. Reader and genre norms, with sources
  2. Claim table: claim, status, source
  3. Gaps and open questions

With scratch in use, save as 00-research.md.

Pairing

  • Feeds /persona-brief (what the reader knows and needs) and /persona-localize (locale profile).
  • Writes no text and changes no claim.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.