AI Policy Assessment Skill

Checks an existing AI policy and answers the two questions a management team asks: what does the law require of us that we have not covered, and where are we stricter than the law asks, at our own cost. Output is one self-contained HTML report for a business reader: coverage figures, a risk-versus-strictness grid, and 27 criteria with the policy sentence each finding rests on. The client picks the depth up front (quick, standard, extensive); the run then produces the report without an approval step. No network, no plugins; also runs as plain attachments in a chat assistant. Use it for "check o

9 stars 1 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add accilium/accilium-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add accilium/accilium-skills --skill ai-policy-assessment-skill
Manual install
git clone --depth 1 https://github.com/accilium/accilium-skills.git /tmp/accilium-skills
mkdir -p ~/.claude/skills
cp -r /tmp/accilium-skills/ai-policy-assessment-skill ~/.claude/skills/ai-policy-assessment-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Policy Assessment Skill

Checks an existing AI policy and answers two questions a management team actually
asks: **what does the law require of us that we have not covered**, and **where are
we stricter than the law asks, at our own cost**.

The output is one self-contained HTML file. Everything in the report is written in
**English**, in language a managing director can read without a security background.

Two errors count equally. A gap is a finding: real risk with no rule. A flat no
where the law allows a graduated answer is also a finding: the strictness was a
decision, not a requirement, and it can be revisited. A report that only knows gaps
pushes every policy towards "stricter is better", which is why so many policies
constrain the business more than the law does.

## Files

Load each file at the step that names it. Nothing is read up front.

| File | Load at | Contents |
|---|---|---|
| `references/method.md` | steps 1-3 | run modes, the intake questions, the legal trigger rules, the scoring |
| `references/criteria.md` | step 3 | 27 criteria with activation conditions, norms and search hints · the scope rule that keeps findings inside an AI policy · the OWASP risk mapping |
| `references/report.md` | step 4 | the data object the template expects, and the checklist |
| `references/report-template.html` | step 4 | the template. Copied verbatim; only the data object is replaced |
Read the full skill on GitHub

Details

Skill name
ai-policy-assessment-skill
Path
ai-policy-assessment-skill/SKILL.md
License
MIT
Repo updated
1 September 2026

FAQ

What does the AI Policy Assessment Skill skill do?

Checks an existing AI policy and answers the two questions a management team asks: what does the law require of us that we have not covered, and where are we stricter than the law asks, at our own cost. Output is one self-contained HTML report for a business reader: coverage figures, a risk-versus-strictness grid, and 27 criteria with the policy sentence each finding rests on. The client picks the depth up front (quick, standard, extensive); the run then produces the report without an approval step. No network, no plugins; also runs as plain attachments in a chat assistant. Use it for "check o

How do I install the AI Policy Assessment Skill skill?

Claude Code plugin: /plugin marketplace add accilium/accilium-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Policy Assessment Skill popular?

It lives in accilium/accilium-skills, which has 9 GitHub stars and 1 forks.

Related skills

Case Cortex

9

accilium/accilium-skills

Build and maintain a Case Cortex — a structured, living, machine-readable representation of a single bounded knowledge-work problem (a "case") that agents and humans share as their reasoning substrate. Use whenever the user wants to set up, seed, update, query, or regenerate artifacts from a Case Cortex. Triggers on phrases like "build a cortex for X", "start a new case", "initialize a case", "seed my cortex", "update the cortex", "add to the cortex", "ingest this document into the cortex", "what does the cortex say about Y", "regenerate the briefing", or "lint the cortex". A Cortex fits bound

AI, LLMs & Agents

Agent Design Coach

6

dadwadw233/claude-code-philosophy

Help developers design or review useful, controllable, extensible agentic systems and products. Use when the user is designing an agent architecture, harness, tool system, memory strategy, permission model, interaction loop, recovery plan, or evaluation strategy, or when they want to turn a vague vibe-coded agent idea into a disciplined product plan. Do not use for simple code generation, generic brainstorming, or purely cosmetic UI critique.

AI, LLMs & AgentsIn 1 list

Multi Agent Verify

9

leyuan0602-glitch/cc-claude-codex

Multi-agent parallel verification. Spawns 3 independent agents (OpenCode CLI, Codex CLI, Claude Task subagent) in separate git worktrees to review, test, and fix code. Synthesizes results and applies final fixes on the original branch.

AI, LLMs & Agents

Replit Prd

9

haberlah/replit-prd-skill

Generate sequential PRD prompt sequences optimized for Replit Agent development. Use when: building applications with Replit Agent, creating PRDs or technical specifications for Replit, experiencing Replit Agent failures and needing better prompting strategy, or decomposing complex projects for Replit Agent. Triggers on phrases like "build with Replit", "Replit Agent", "Replit PRD", "vibe coding".

AI, LLMs & Agents

Adversarial Verification

9

kadaliao/claude-code-skills-collection

对抗性验证技能 — 验证代码变更/部署/任务交付物的正确性。不是确认"它能工作",而是尝试"把它搞坏"。用于:(1) 完成非平凡任务后自验 (2) 审查 PR/MR (3) 部署后验证 (4) bobooo 说"验证一下"。灵感源自 Claude Code Verification Agent 设计。

AI, LLMs & Agents

Powabase

9

powabase-ai/agent-skills

Use for ANY task building on Powabase, the multi-tenant AI Backend-as-a-Service (projects on *.p.powabase.ai, the /api/* surface). Triggers: RAG & knowledge bases (Sources, document upload/extraction, indexing strategies chunk_embed/full_document/page_index/graph_index/doc2json, retrieval vector/full-text/hybrid/tree search, reranking, query enrichment, multimodal/image retrieval, embeddings, pgvector); agents (ReAct loops, builtin/custom/MCP tools, sessions, streaming, approval/human-in-the-loop); multi-agent orchestrations (supervisor/sequential/parallel); workflows (block graphs, webhooks,

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.