smooth-experience
Use when a developer wants to reduce repeated agent permission prompts, audit permanent tool permissions, or inspect recent Claude Code and Codex sessions for safe allow rules
- License 许可
- Apache-2.0
- 所属仓库
- zak-keown/moe
- 最近更新
- 2026-09-05
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- smooth-experience
- description
- Use when a developer wants to reduce repeated agent permission prompts, audit permanent tool permissions, or inspect recent Claude Code and Codex sessions for safe allow rules
02 资源文件 11
- 脚本scripts/lib/discovery.mjs3.3 KB
- 脚本scripts/lib/evidence.mjs5.3 KB
- 脚本scripts/lib/harnesses/claude.mjs21.4 KB
- 脚本scripts/lib/harnesses/codex.mjs35.2 KB
- 脚本scripts/lib/mutation.mjs13.2 KB
- 脚本scripts/lib/rank.mjs10.2 KB
- 脚本scripts/lib/safety/filesystem.mjs2.7 KB
- 脚本scripts/lib/safety/mcp.mjs830 B
- 脚本scripts/lib/safety/network.mjs1.7 KB
- 脚本scripts/lib/safety/shell.mjs7.3 KB
- 脚本scripts/smooth.mjs24.1 KB
03 SKILL.md 正文
Smoothing the Experience
Run the skill-owned helper with Node. The audit is local, deterministic, on demand, and never a background service. It evaluates Claude Code and Codex on a best-effort basis. Report any other installed harness as not evaluated; do not imply that Moe audited it. In the steps below, $SKILL is the absolute path to skills/smooth-experience/scripts.
- Run
node "$SKILL/smooth.mjs" scan --days 30. - Present Claude Code and Codex separately. Preserve
not evaluated,blocked, andno narrow rendererdispositions. - Ask the user to select individual candidate IDs. Never offer select-all.
- Run
node "$SKILL/smooth.mjs" plan --select <comma-separated-ids>for exactly one harness and show the exact diff. - Explain the destination and whether a new session is required.
- Do not run
applyuntil the user explicitly confirms that exact diff, one harness at a time. - Pass the plan path and printed confirmation token to
node "$SKILL/smooth.mjs" apply --plan <path> --confirm <token>. Report whether the change applied and whether the user must start a new session. Leave every other harness unchanged.
Never summarize raw transcripts, broaden a rule, reinterpret an ineligible item, or bypass a helper refusal.
04 同仓库更多 Skills
write-skill
Use when creating new skills, editing existing skills, or verifying skills work before deployment
write-plan
Use when you have a spec or requirements for a multi-step task, before touching code
write-clearly
Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
windows-vm
Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.
verify-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating MRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
using-moe
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions