robust-lit-review: Skill for Claude Code

.claude/skills/claim-appraise/SKILL.md

claim-appraise is a skill for Claude Code from htlin222/robust-lit-review. It costs 69 tokens per session (1,357 once invoked), scanned A, original, MIT.

A workflow for evaluating a specific health or product claim against published research. It breaks the claim into focused questions and produces evidence-based verdicts with confidence ratings.

In plain words
What is it for?
Use it to appraise diets, supplements, health products, or protocols through systematic reviews, DOI checks, evidence grading, and claim-level conclusions.
Why use it?
It helps separate a real claim into answerable parts and check whether supporting studies are recent, relevant, verifiable, and strong enough to trust.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is htlin222/robust-lit-review's own configuration. It tells Claude Code how to work on robust-lit-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything robust-lit-review configures →

Reuse

Borrowing it

Nothing to install: this file belongs to htlin222/robust-lit-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/htlin222/robust-lit-review/main/.claude/skills/claim-appraise/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/htlin222/robust-lit-review

Made for: Claude Code.

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 claim-appraise

README.md
[![agentmods](https://agentmods.dev/badge/skills/htlin222/robust-lit-review/claim-appraise/github.svg)](https://agentmods.dev/skills/htlin222/robust-lit-review/claim-appraise)
Your own site
<a href="https://agentmods.dev/skills/htlin222/robust-lit-review/claim-appraise"><img src="https://agentmods.dev/badge/skills/htlin222/robust-lit-review/claim-appraise/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 claim-appraise

Your own site · 80×15
<a href="https://agentmods.dev/skills/htlin222/robust-lit-review/claim-appraise"><img src="https://agentmods.dev/badge/skills/htlin222/robust-lit-review/claim-appraise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,357 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 $0.00069 $0.01357
Opus 5 $0.00034 $0.00678
Sonnet 5 $0.00014 $0.00271
Haiku 4.5 $0.00007 $0.00136

Measured 12d ago against content hash dd29f62d7c12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claim-appraise 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 12d ago.

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.

.claude/skills/claim-appraise/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claim Appraisal Workflow (/claim-appraise)

You are turning ONE real-world claim into a defensible, peer-checkable evidence appraisal. Unlike /lit-review (which reviews a topic into a manuscript), this adjudicates a claim and renders a verdict per sub-question.

Worked example shipped with this repo: the 4+2R 代謝飲食法 appraisal → https://verdict-4plus2r-sr.pages.dev/.

When to use

"Is legit?", "appraise the diet/supplement/protocol", "fact-check this health claim".

Hard quality gates (non-negotiable)

  • Literature ≥ 2016 and Q1 journals only (assess_journal_quality(strict=True) + filter_by_year).
  • Every DOI resolved via doi.org and CrossRef-verified to exist (utils/crossref.py) — the anti-hallucination gate. Never cite a work CrossRef can't confirm.
  • Per sub-question GRADE certainty (recomputed deterministically, LLM rating is advisory).
  • OpenEvidence cross-check where the relay is available (non-fatal if not).
  • Overall verdict logic audited with /argdown before wording ships.
  • Attach the claim's primary source URL so peers can confirm no 斷章取義 (cherry-picking).

Steps

  1. Identify the real claims. Read the claim's PRIMARY source (official site / book), not secondary blogs. Enumerate every distinct sub-claim. Save the source URL(s).

  2. Decompose into PICO sub-questions — one per distinct outcome domain (efficacy AND safety AND any over-extended claims). See scripts/run_4plus2r.py for the PICOQuestion shape. Get the list approved before searching (wrong PICOs waste the run).

  3. Run the per-PICO SR (real API search; needs .env keys). For each PICO: ClaimAppraisalPipeline.run_pico_search → Scopus+PubMed+Embase → dedup → year≥2016 → Q1-strict → DOI-validate → CrossRef-verify → PicoPrismaFlow + included studies. Drive it like scripts/run_4plus2r.py (saves output/<claim>/pico_NN.json).

  4. Write one chapter per PICO following output/4plus2r/CHAPTER_SPEC.md: dispatch a subagent per chapter that reads only its pico_NN.json, selects the most relevant HUMAN studies (flag animal/in-vitro as 機轉假說), assigns a verdict chip (vc-strong/moderate/weak/contra/risk/unproven) and GRADE pips, and cites via <cite class="ref" data-doi="DOI">. NEVER invent a citation.

Read the full file on GitHub · 67 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. 12d ago First seen · 67 lines · 69 tokens per session scan A dd29f62d7c12

Subscribe to this mod's changes

claim-appraise is a skill published in the GitHub repository htlin222/robust-lit-review (56 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 1,357 once invoked, about $0.0003 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

cirq

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for…

LeonChaoX/qinyan-academic-skills · 67 tokens

qiskit

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use…

LeonChaoX/qinyan-academic-skills · 73 tokens

geopandas-spatial

Geospatial and climate data analysis with geopandas and xarray. Use when: (1) geographic vector data analysis, (2) climate and weather NetCDF data, (3) spatial joins and overlay operations, (4) map visualization, (5) CRS transformations and area calculations. NOT for: satellite imagery ML (use rasterio/torchgeo)…

beita6969/ScienceClaw · 96 tokens

pymatgen-materials

Materials science computation with pymatgen. Use when: (1) crystal structure creation and manipulation, (2) phase diagram construction, (3) electronic structure analysis, (4) symmetry and space group operations, (5) VASP input/output parsing. NOT for: molecular chemistry (use rdkit-chemistry), protein structure (use…

beita6969/ScienceClaw · 91 tokens

rdkit-chemistry

Molecular chemistry operations via RDKit. Use when: user asks about molecular structures, SMILES, chemical properties, or fingerprints. NOT for: reaction databases or wet lab protocols.

beita6969/ScienceClaw · 42 tokens

research-agent

Project-first Research pipeline with live gates, source/PDF evidence, claim boundaries, compute and publication controls; includes an optional PubMed/arXiv standard-library helper.

ellmos-ai/skills · 36 tokens