verify SKILL.md skillA

verify from borda/ai-rig is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add borda/ai-rig/verify@git:20261023.0d5e714

Pins git:20261023.0d5e714 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
borda/ai-rig
Path
plugins/cc_research/skills/verify/SKILL.md
Versions recorded
16
Latest version
git:20261023.0d5e714, committed Oct 23, 2026
First version recorded
Aug 8, 2026
Size
31,895 bytes
Repository stars
31
License
Apache-2.0

Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF path / arXiv URL / pasted text), maps claims to codebase, emits verification table with match status and severity.

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

<constants>

```yaml
HARD_CUTOFF: 900  # seconds — advisory; Agent() runs in background and cannot be interrupted mid-flight
```

</constants>

<objective>

Paper-vs-code consistency audit. After `research:scientist` implements method from paper, verify implementation matches paper claims. Audits five dimensions — formula matching, hyperparameter parity, eval protocol, notation consistency, citation chain. Emits verification table with match status and severity.

NOT for: running experiments (use `/research:run`); judging experimental methodology (use `/research:judge`); literature search (use `/research:topic`); general code review (use `/develop:review` (requires `develop` plugin)). Verify audits implementation-vs-paper fidelity only — does not evaluate whether paper's claims are valid.

</objective>

<workflow>

## Agent Resolution

`research:scientist` same plugin as this skill — no fallback needed if research plugin installed. Scientist handles all five audit dimensions in single spawn to preserve cross-dimension context (e.g., notation inconsistency explaining formula mismatch needs holistic paper understanding).

## Verify Mode (Steps V1–V6)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add borda/ai-rig/verify@sha256:84d8a86dff147911

The line at the top of this page pins the label git:20261023.0d5e714, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7yc76oo2dlrvlbzk.svg)](https://markdownregistry.com/a/art_7yc76oo2dlrvlbzk)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 16 versions of this file, between Aug 8, 2026 and Oct 23, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20261023.0d5e714 latest2026-10-23 0d5e714 31,895 BA view · diff
git:20261021.076157a2026-10-21 076157a 31,444 BA view · diff
git:20261021.7b6ff282026-10-21 7b6ff28 30,114 BA view · diff
git:20261009.253fdb32026-10-09 253fdb3 28,218 BA view · diff
git:20261005.6367f832026-10-05 6367f83 28,107 BA view · diff
git:20261002.e974f382026-10-02 e974f38 28,098 BA view · diff
git:20261002.381549d2026-10-02 381549d 27,946 BA view · diff
git:20260923.39e3a482026-09-23 39e3a48 27,628 BA view · diff
git:20260922.5a946b62026-09-22 5a946b6 25,324 BA view · diff
git:20260918.3e1a63d2026-09-18 3e1a63d 24,547 BA view · diff
git:20260911.be7b3082026-09-11 be7b308 24,953 BA view · diff
git:20260822.a5f4fd62026-08-22 a5f4fd6 24,896 BA view · diff
git:20260821.d9793192026-08-21 d979319 23,923 BA view · diff
git:20260808.5143e562026-08-08 5143e56 23,952 BA view · diff
git:20260808.a8a70fe2026-08-08 a8a70fe 23,922 BA view · diff
git:20260808.c2ee8972026-08-08 c2ee897 23,636 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (31895 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

GitHub

borda/ai-rig · 31 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7yc76oo2dlrvlbzk
GET https://markdownregistry.com/api/v1/resolve?ref=borda/ai-rig/verify
GET https://markdownregistry.com/api/v1/blob/84d8a86dff147911e593b306efa81e261a662fd6d163aae94d888a63c6db2e67

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 borda/ai-rig

AGENTS.md AGENTS.md file
borda/ai-rig · AGENTS.md
git:20261101.17fd3ab · audit A · 31 stars
CLAUDE.md CLAUDE.md file
borda/ai-rig · CLAUDE.md
git:20261101.17fd3ab · audit A · 31 stars
AGENTS.md@benchmarks AGENTS.md file
borda/ai-rig · benchmarks/AGENTS.md
git:20260814.b9c6b5a · audit A · 31 stars
llms.txt@docs llms.txt file
borda/ai-rig · docs/llms.txt
git:20260814.1bd25c1 · audit A · 31 stars
AGENTS.md@plugins AGENTS.md file
borda/ai-rig · plugins/AGENTS.md
git:20261101.17fd3ab · audit A · 31 stars
CLAUDE.md@plugins CLAUDE.md file
borda/ai-rig · plugins/CLAUDE.md
git:20261102.52ad0cc · audit B · 31 stars
advise SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/advise/SKILL.md · Ask Codex a read-only question with explicit model, effort, budget, and compact results.
git:20261025.90f4430 · audit A · 31 stars
cancel SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/cancel/SKILL.md · Request cancellation of a running detached Codex bridge job.
git:20261021.7b6ff28 · audit A · 31 stars
implement SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/implement/SKILL.md · Ask Codex for one bounded write-capable change with compact results.
git:20261025.90f4430 · audit A · 31 stars
result SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/result/SKILL.md · Read a completed detached Codex bridge job's compact result.
git:20261021.7b6ff28 · audit A · 31 stars
review SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/review/SKILL.md · Request a read-only adversarial Codex review with explicit model, effort, budget, and compact findings.
git:20261025.90f4430 · audit A · 31 stars
setup SKILL.md skill
borda/ai-rig · plugins/bridge_cc-codex/claude-skills/setup/SKILL.md · Configure, authenticate, repair, and verify the Claude Code to Codex Bridge; safe stages run by default and sensitive…
git:20261021.7b6ff28 · audit A · 31 stars

Every file in borda/ai-rig

Other files named verify

verify SKILL.md skill
garrytan/gstack · verify/SKILL.md · Use when coding: run the checks and tests /ship picks until green. (gstack)
v0.1.0 · audit A · 140,694 stars
verify SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/verify/SKILL.md · Verify that a change really works before you claim completion
git:20260401.ff9223c · audit A · 40,624 stars
verify SKILL.md skill
amir20/dozzle · .claude/skills/verify/SKILL.md · Prove a change works before opening a PR for Dozzle. Runs the checks CI runs for what the diff touches, shows the new…
git:20261105.67821dc · audit A · 14,814 stars
verify SKILL.md skill
zenbu-labs/terminal-browser · .claude/skills/verify/SKILL.md · Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video +…
git:20260721.c3339dc · audit A · 4,449 stars
verify SKILL.md skill
alsk1992/cloddsbot · src/skills/bundled/verify/SKILL.md · Verify agent identity using ERC-8004 on-chain registry
git:20260130.5926fbf · audit A · 3,076 stars
verify SKILL.md skill
ethanyoq/ai-novel-writer · .claude/skills/verify/SKILL.md · 在真实 Electron 里驱动书童做实机验证:截图、复现界面缺陷、跑 redesign 场景、测启动耗时与内存、读只读诊断。Use for real-app verification of Pagekin (书童) -…
git:20261106.0d92f96 · audit A · 2,388 stars
verify SKILL.md skill
zereight/gitlab-mcp · .github/skills/verify/SKILL.md · Verify that a change really works before claiming completion. Activate when user says: verify this, check if it works…
git:20260412.9d9ce51 · audit A · 2,088 stars
verify SKILL.md skill
codeaholicguy/ai-devkit · skills/verify/SKILL.md · AI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when…
git:20261028.9c55339 · audit A · 1,661 stars

Browse by kind, by grade A, or by owner.