paper-claim-audit SKILL.md skillA
paper-claim-audit from wanshuiyin/auto-claude-code-research-in-sleep is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit@git:20261019.8fdc2d5Pins git:20261019.8fdc2d5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wanshuiyin/auto-claude-code-research-in-sleep
- Path
skills/paper-claim-audit/SKILL.md- Versions recorded
- 7
- Latest version
- git:20261019.8fdc2d5, committed Oct 19, 2026
- First version recorded
- May 29, 2026
- Size
- 15,356 bytes
- Repository stars
- 18,690
- License
- MIT
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Paper Claim Audit: Zero-Context Evidence Verification > **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md): > resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP) > with `reviewer_route.py` through the canonical helper resolver, preserving this > slot's tier, fresh contexts, source/image inputs and deterministic gates. > Codex examples/pins below apply only to `backend=codex`; other routes use their > own first-call/reply contract. Save the route and actual returned identity; > unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual > families/completion/scope. Forward invocation reviewer/model/effort overrides > to reviewer-bearing children. Generation workers are unchanged. > 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is > verdict-bearing — it judges paper-to-evidence fidelity with a deliberately > zero-context fresh reviewer. Re-firing that verdict on a wall-clock timer adds > no new signal (it changes only when the *paper or results* change). Schedule > the *external wait that precedes it* — paper draft ready → then audit > **once**. See …
Read the whole file at its exact version.
How to install
mdr add wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit@sha256:3cf3ecdf14899aa0The line at the top of this page pins the label git:20261019.8fdc2d5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_55hrcmgzntego6ux)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between May 29, 2026 and Oct 19, 2026, about one every 24 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261019.8fdc2d5 latest | 2026-10-19 | 8fdc2d5 | 15,356 B | A | view · diff |
| git:20260928.3e7691b | 2026-09-28 | 3e7691b | 14,255 B | A | view · diff |
| git:20260906.0472e53 | 2026-09-06 | 0472e53 | 14,248 B | A | view · diff |
| git:20260713.e67ae16 | 2026-07-13 | e67ae16 | 14,248 B | A | view · diff |
| git:20260710.6142715 | 2026-07-10 | 6142715 | 14,246 B | A | view · diff |
| git:20260531.7f0f632 | 2026-05-31 | 7f0f632 | 14,123 B | A | view · diff |
| git:20260529.5817146 | 2026-05-29 | 5817146 | 14,123 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15356 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wanshuiyin/auto-claude-code-research-in-sleep · 18,690 stars · license MIT · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_55hrcmgzntego6ux GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/auto-claude-code-research-in-sleep/paper-claim-audit GET https://markdownregistry.com/api/v1/blob/3cf3ecdf14899aa011c7f5baf5efcba7a67e940a65e7938170426f4af2b032ea
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from wanshuiyin/auto-claude-code-research-in-sleep
Every file in wanshuiyin/auto-claude-code-research-in-sleep