agentleFS
dboskdbosk/claude-skills/backing-claims/SKILL.md

backing-claims

Skill1 starsChanged 9 days agoNo licenceView on GitHub

Back factual and empirical claims with a small two-sided literature review — searches for literature that supports AND refutes/qualifies the claim (COUNTER) — verify sources in full text, and record provenance (how found, why picked, quote, counter-search outcome). Format-independent: papers, reports, memos, evidence logs, survey answers — any output resting on a factual claim, not just TeX. Use proactively when: (1) adding OR reusing a citation, page number, or attribution for a factual/empirical claim (inherited citations are NOT pre-verified), (2) attributing a claim to a source ("X found that…"), (3) the user asks to find a reference or check a citation — or wants an answer or decision backed by evidence, research, or literature, (4) writing related-work, background, or claims sections, (5) mentions of scholar, BibTeX, DOI, arXiv, OpenAlex, Crossref, or a literature search, (6) writing or reviewing ADVICE — rules, conventions, best practices, "do X because Y" — or a statement that a text "makes no claims needing a search": advice asserts a benefit, and that benefit is an empirical claim to audit even when nobody planned to cite anything. (7) DELEGATING literature research to a subagent or teammate — the subagent prompt must tell it to load this skill, run every search under a named scholar session, and document alphaXiv/WebSearch complements in the appendix (see "Delegating research to subagents"). Trigger BEFORE citing; this skill owns finding/verifying/justifying the reference (markup: writing-crypto/latex-writing).

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 7 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

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.