hinna0818/ukbanalytica_v2/skill-creator

Claude Code and agent skill by hinna0818/ukbanalytica_v2

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Create, update, review, and validate Codex/OpenAI agent skills in this repository. Use when the user asks to add a new skill, revise an existing SKILL.md, design skill references/scripts/assets, audit trigger descriptions, add smoke tests, package skills under inst/skills, or align skills with UKBAnalytica/RAP privacy and reproducibility standards.

Install

npx vskill@latest install hinna0818/ukbanalytica_v2/skill-creator

SKILL.md

Skill Creator

Purpose

Use this skill to create and maintain repo-bundled Codex skills. Keep every skill concise, triggerable, testable, and safe for UK Biobank RAP workflows.

Workflow

  1. Inspect the existing skill tree before editing:
bash
find inst/skills -maxdepth 3 -type f | sort
  1. Decide the target:
  • New standalone skill: inst/skills/<skill-name>/SKILL.md.
  • New UKBAnalytica workflow skill: inst/skills/UKBAnalytica_skills/<ukbsci-name>/SKILL.md.
  • Existing skill update: patch only the relevant skill and directly referenced resources.
  1. Write SKILL.md first. The frontmatter must contain only:
yaml
---
name: lower-hyphen-name
description: Clear trigger description with what the skill does and when to use it.
---
  1. Keep the body procedural and short. Put detailed examples, disease catalogs,

function lists, or long checklists in one-hop references/ files.

  1. Add resources only when they materially improve reuse:
  • references/: detailed guidance loaded only when needed.
  • scripts/: deterministic checks or generation utilities.
  • assets/: templates or media used in outputs.
  • agents/openai.yaml: UI metadata. Its default_prompt must mention $<skill-name>.
  1. Validate after edits:
bash
python3 inst/skills/skill-creator/scripts/validate_skill.py inst/skills/<skill-name>

For all repo skills:

bash
python3 inst/skills/skill-creator/scripts/validate_skill.py inst/skills

UKBAnalytica Standards

  • Preserve the strict RAP privacy boundary: local agents generate scripts and

interpret aggregate outputs only. They must not read, inspect, summarize, or process real UK Biobank participant-level RAP data or logs containing row values.

  • Allow script generation, package guidance, simulated-data smoke tests, and

interpretation of aggregate tables/figures.

  • Prefer package functions over ad hoc code in examples.
  • Remind users to install or load the latest UKBAnalytica before high-level

workflow examples.

  • Add minimal smoke tests when a skill depends on package functions whose

interfaces may change.

Reference Files

Read only the needed reference:

  • references/skill-structure.md: SKILL.md, resource layout, and UI metadata.
  • references/ukbanalytica-skill-standards.md: UKBAnalytica-specific privacy,

function, and analysis workflow standards.

  • references/evaluation-and-smoke-tests.md: validation and smoke-test design.

Completion Checklist

  • SKILL.md has valid frontmatter and no placeholder text.
  • description contains the trigger conditions.
  • Long details are moved into direct references/ files.
  • agents/openai.yaml, if present, matches the skill and mentions $skill-name.
  • Validation script passes.
  • For package-facing skills, a small smoke test exists or the reason for

omitting one is clear.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
35
7-day trend score
18

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 27 Aug 2026, 2 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/hinna0818/ukbanalytica_v2/skill-creator/badge)](https://verified-skill.com/skills/hinna0818/ukbanalytica_v2/skill-creator)

Something wrong with this skill or its page? Tell us.