Skip to content
Published studies are shown for demonstration purposes, not because they are good or bad research. Demonstrator · items marked Example are invented · what exists today
Search

Skills · Found in a collection

skill-auditor

“A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.” (the skill's description, quoted from its SKILL.md)

Found on: AIPOCH, Medical Research Skills, github.com/aipoch/medical-research-skills (MIT), version 686e09d of 17 September 2026, read 14 October 2026

AIPOCH's skill

AIPOCH wrote this skill for AI assistants that read SKILL.md files, such as Claude Code and Codex, and keeps it in Medical Research Skills on GitHub; the collection also has an install script for OpenClaw. e2er lists it in Skills so that it can be found next to e2er's own skills; its files stay in AIPOCH's repository.

Folder
skill-auditor
Category
none: a folder at the top of the repository
Licence
MIT, as its SKILL.md states
Files
SKILL.md and 13 other files, scripts among them

AIPOCH's own audit

The skill's folder holds no MedSkillAudit report.

MedSkillAudit is AIPOCH's framework for auditing its medical research skills (skill-auditor). The grade is AIPOCH's assessment of its own skill. e2er has not evaluated this skill.

Can e2er use it?

Not by default: no e2er specialist reads it. e2er's specialists read skills that are single Markdown files, e2er's own and the packs from the RISE catalogue that e2er skills install fetches, and AIPOCH's collection is not in that catalogue.

A specialist can read this skill's instructions if you save its SKILL.md as ~/.e2er/skills/aipoch/skill-auditor.md and name it under [skills] in a template:

[skills]
<specialist> = ["aipoch/skill-auditor"]

e2er then reads that one file as text, and the study's dossier lists the skill as aipoch/skill-auditor, which leads back to this page. The folder's 13 other files stay unread, and e2er runs none of its scripts.

In Claude Code, Codex or OpenClaw, add the whole folder as the collection's README describes.

Description

Data model
Discipline
Biomedical
Method family
not specified
Design
not specified
Research stage
not specified
Authors
none: the source is cited on this page
Usage
not used in published research yet
Source
Found on a list or in a collection · aipoch/medical-research-skills · @686e09dfdb45d9fa1a08664f06bb93769b3c9d91
Record
skill:aipoch/skill-auditor · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.