plugins/steroids/skills/skill-console/SKILL.md
Generate a local HTML dashboard for auditing installed Skills, token usage, description token budgets, duplicate Skill names, Skill paths, and selected Skill exports. Use when the user wants to inspect many Skills, decide which Skills to disable, compare duplicates, preview SKILL.md contents, sort by token usage, or export selected Skills as JSON.
npx skillsauth add kanlac/agent-steroids skill-consoleInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when Skill inventory itself is the object of work: too many Skills are loaded, token budget is unclear, duplicate names need explanation, or the user wants to hand back a compact list of selected Skills.
Generate the self-contained HTML page with the bundled script:
python3 "${SKILL_PATH}/scripts/generate_skill_console.py" --project-root "$PWD" --output skill-console.html
Open the resulting HTML locally and verify it visually when changing the page or when the user is relying on dense table columns. The dashboard is designed for:
SKILL.md, and line countSKILL.mdJSON export is intentionally minimal. It must be an array of selected Skills only:
[
{
"name": "skill-name",
"path": "~/.claude/skills/skill-name"
}
]
path is always the Skill directory path, not the SKILL.md file path. Keep SKILL.md paths internal to preview and token accounting.
Treat the dashboard as an audit and planning tool. For local user or workspace Skills, prefer moving whole Skill directories to a sibling skills.disabled/ directory so the action is reversible. For plugin-backed Skills, prefer disabling the owning plugin in runtime config instead of editing plugin cache contents directly.
Only delete or move Skills after the user explicitly asks for that operation and the paths have been checked against the selected JSON or dashboard rows.
Dense Skill tables must define column priorities and widths before visual QA. Long fields such as description, duplicate paths, plugin IDs, and Skill paths need explicit wrapping or a details surface; do not depend on browser automatic table layout.
devops
自建机场(代理服务端)搭建与运维。涵盖 VPS 初始化/加固、3X-UI 面板、Xray VLESS Reality+Vision 入站、多用户独立订阅(UUID/subId/到期/续期)、把节点渲染成 Clash/Mihomo 订阅 YAML、Profile 显示名与到期时间下发、域名/ACME 证书、出口测速、IP 被墙/被滥用风险判断、备份恢复。用户要在 VPS 上部署或维护自建节点/机场、调试 3X-UI 订阅、Reality 入站、订阅链接显示名/到期、面板安全、证书申请、速度低或 IP 风险时用这个 skill。客户端 Clash Verge / mihomo 的配置即代码、规则不命中、DNS 泄漏排查见 clash-verge-config skill。
tools
Turn a YouTube link into a polished single-file bilingual (Chinese + original) transcript reading page. Use when the user gives a YouTube URL and asks to "转录" "做转录稿" "生成转录页面" "中英对照" "bilingual transcript" "transcribe this video", or wants a readable HTML transcript with clickable timestamps, chapter navigation, highlighted key points, and proper-noun annotations. Fetches captions + chapters via yt-dlp, the agent translates and curates, then a script renders the HTML.
development
Use when a user asks the agent to "learn" from a file, example, correction, failed workflow, or feedback and persist that learning into skills or agent instructions. Guides semantic skill refactoring: extract the transferable behavior, update the owning skill so it becomes clearer and easier to execute, avoid append-only note dumping, and decide when not to create new reference files.
development
以「配置即代码」管理、调试 Clash Verge Rev(mihomo 内核)客户端配置。涵盖:哪些字段扩展脚本能改 / 不能改(external-controller、secret、各端口、log-level 被内核接管)、改了为什么不生效、enhance 管线与字段归属、纯命令行让配置重新生成并生效、mihomo external controller RESTful API、external-ui 自托管面板、判断流量走没走代理 / 命中哪条规则、DNS 泄漏排查、profiles.yaml 里 profile 显示名与到期信息从哪来、节点突然全超时时先排除 IP 被墙与 TUN 回环、远程机器复用本地代理。用户在改 Clash Verge / mihomo 扩展脚本(script) / 扩展配置(merge) / 订阅规则、external-controller / secret / 端口,或抱怨「配置改了不生效」「规则不命中」「远程连不上面板」「DNS 泄漏」「profile 显示名 / 到期不对」「节点突然连不上 / 延迟测试超时」「想自动化更新代理配置」时用这个 skill。机场 / 订阅服务端搭建见 airport-deploy skill。