AI Readiness Policy
Helps pick or write an AgentRC policy to customize AI-readiness scoring rules.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 11, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · ba24762
Verbatim install is clean — one self-contained SKILL.md, strict-YAML frontmatter, no missing assets — and the trigger description is specific and non-overlapping with its sibling skills. Two hidden deps to note: the 'apply' sub-command hands report rendering off to the sibling acreadiness-assess skill / ai-readiness-reporter agent (not installed by this card's command), and the underlying `npx github:microsoft/agentrc` calls need an unstated Node.js 20+; neither blocks the core pick/write-a-policy workflow, so verdict is pass rather than setup. A/B: both arms produced a valid, near-identical policy JSON, but the skill armed run nailed the actual enablement convention (agentrc.config.json with a 'policies' array) while the base arm guessed uncertainly at '.agentrc.json' and added a questionable level:5 override — the skill's domain grounding made the load-bearing 'how to enable' half correct.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 7/10
- Docs & honesty 4/5
What AI Readiness Policy does
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
How to install AI Readiness Policy
git clone https://github.com/github/awesome-copilot
cd awesome-copilot
mkdir -p ~/.claude/skills
cp -r skills/acreadiness-policy ~/.claude/skills/acreadiness-policy
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger AI Readiness Policy
-
/acreadiness-policyHelps pick or write an AgentRC policy to customize AI-readiness scoring rules.
It also activates on plain-language prompts like these:
-
Write a custom AgentRC policy for strict mode -
Set custom weights for our AI-readiness scoring -
Configure CI gating thresholds for readiness checks
Frequently asked questions
- Is the AI Readiness Policy skill free?
- Yes. The skill itself is free from github/awesome-copilot. SkillProof publishes the install command and an independent test verdict at no cost.
- Does AI Readiness Policy work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 11, 2026. Verdict: Tested · Works. Verbatim install is clean — one self-contained SKILL.md, strict-YAML frontmatter, no missing assets — and the trigger description is specific and non-overlapping with its sibling skills. Two hidden deps to note: the 'apply' sub-command hands report rendering off to the sibling acreadiness-assess skill / ai-readiness-reporter agent (not installed by this card's command), and the underlying `npx github:microsoft/agentrc` calls need an unstated Node.js 20+; neither blocks the core pick/write-a-policy workflow, so verdict is pass rather than setup. A/B: both arms produced a valid, near-identical policy JSON, but the skill armed run nailed the actual enablement convention (agentrc.config.json with a 'policies' array) while the base arm guessed uncertainly at '.agentrc.json' and added a questionable level:5 override — the skill's domain grounding made the load-bearing 'how to enable' half correct.
- What is the AI Readiness Policy SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
- How do I install AI Readiness Policy?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use AI Readiness Policy with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.