Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Viy1204/recruiting-copilot --skill interview-schedulegit clone --depth 1 https://github.com/Viy1204/recruiting-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/viy1204/recruiting-copilot/interview-schedule)<a href="https://agentmods.dev/skills/viy1204/recruiting-copilot/interview-schedule"><img src="https://agentmods.dev/badge/skills/viy1204/recruiting-copilot/interview-schedule/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/viy1204/recruiting-copilot/interview-schedule"><img src="https://agentmods.dev/badge/skills/viy1204/recruiting-copilot/interview-schedule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 17 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00137 | $0.01594 |
| Opus 5 | $0.00068 | $0.00797 |
| Sonnet 5 | $0.00027 | $0.00319 |
| Haiku 4.5 | $0.00014 | $0.00159 |
Grade A, and why
interview-schedule scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
面试预约
把"约面试"从口头变成一次做全：日历日程（含飞书视频会议）+ 面试官进会 + 候选人邀约话术 + 档案台账同步。
前置
lark-cli已配置（飞书日程/会议是本流程的本体）。没有 → 走文末"无飞书降级"，其余照做。- 候选人应已在台账/
03-interview/里。不在 → 先补档（走skills/resume-review/SKILL.md或手动建档），别凭空约。
流程
1. 收集要素（缺什么问什么，一次问全）
- 候选人与轮次：从
03-interview/<姓名>.md读基本信息和已有面试记录，判断这是第几轮。 - 面试官：姓名（可多人）。
- 时间与时长：用户给了就用；只给模糊范围（"明天下午"）→ 先查面试官忙闲再提议。时长默认 60 分钟。
- 形式：默认视频面（飞书会议）；现场面则不需要会议链接，改在描述里写清地点。
2. 面试官姓名 → 飞书 ID
lark-cli contact 按姓名解析 open_id（ou_ 前缀；命令细节 lark-cli contact --help）。
同名多人 → 列出部门让用户选，别猜。
3. 查忙闲，定时间
lark-cli calendar +freebusy --start <日期> --end <日期> --user-id <ou_面试官> --as user
逐个面试官查，找共同空闲。用户给的时间撞了别人的日程 → 报冲突并给 2-3 个可选时段，让用户定。
4. 建日程（写操作，建前必须把要素给用户过目确认）
确认口径一句话："<日期时间>，<候选人>（<岗位> <轮次>），面试官 <名单>，视频面试，建吗？"
lark-cli calendar +create --as user \
--summary "面试：<岗位>-<候选人姓名>（<轮次>）" \
--start "<ISO 8601，如 2026-07-15T14:00+08:00>" \
--end "<ISO 8601>" \
--attendee-ids <ou_面试官1>,<ou_面试官2> \
--description "<候选人一句话背景 + 初筛待验证点（从档案抄）+ 档案路径 + JD 要点>"
要点：
+create默认自带飞书视频会议，日程里就有会议链接，面试官点日程即可入会——不用单独建会。- description 是给面试官的"面前必读"：把档案里的待验证点抄进去，面试官不用翻文件。
- 候选人一般不是公司飞书用户，不加进参会人；把会议链接发给他即可。若候选人有邮箱且用户要求日历直邀，
可用完整 API 以
third_party（邮箱）类型添加。
5. 通知候选人（对外动作，默认不代发）
从创建结果取会议链接（丢了用 calendar +get 或 +meeting 查），生成邀约话术：
您好，
<岗位>岗位约您<日期时间>视频面试（约<时长>），面试官是<称谓即可，不必全名>。 会议链接：<链接>。请提前测试摄像头麦克风；如时间不便请回复调整。
默认把话术交给用户自己发（Boss/猎聘/微信渠道由用户定）。用户明确说"帮我在 Boss 上发给他"
才代发，发完回报。这是对外不可逆动作，规矩同 recruit-daily 打招呼。
6. 同步档案与台账
03-interview/<姓名>.md「面试安排」表加一行：轮次｜时间｜形式｜面试官｜状态=已约。02-sourcing/dedup-ledger.csv：状态推进为已约谈（首轮）或保持面试中（后续轮）。
完成判据
日程已建且含会议链接、每位面试官都在参会人里、候选人邀约话术已交付（或经确认已代发）、 档案排期表和台账状态都已更新——五样缺一即未完成。
改期 / 取消
- 先
calendar +search-event --query "<候选人名>"定位 event_id。 - 改期：
calendar +update改时间（面试官会收到变更通知）；取消：删除日程。 - 同步三处：档案排期表该行状态、台账状态、候选人通知（新话术给用户发）。漏候选人通知 = 放鸽子。
无飞书降级（没装 lark-cli）
输出一份"手动操作包"，其余步骤照常：
- 给用户的建会清单：在你用的会议工具（飞书/腾讯会议/Zoom）建
<时间>会议、邀请<面试官名单>； - 给面试官的面前必读（候选人背景 + 待验证点）；
- 给候选人的邀约话术（留
<会议链接>占位，用户建完会填上）； - 档案排期表与台账照常更新，形式列注明"手动建会"。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 98 lines · 137 tokens per session scan A cdec0ed044a5
interview-schedule is a skill published in the GitHub repository Viy1204/recruiting-copilot (57 stars, last pushed 7d ago), licensed MIT. It adds 137 tokens to every session and 1,594 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
estimating-and-contingency
Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…