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 agentmods add skills/cafe3310/public-agent-skills/interview-processornpx skills add cafe3310/public-agent-skills --skill interview-processorgit clone --depth 1 https://github.com/cafe3310/public-agent-skillsWrote 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/cafe3310/public-agent-skills/interview-processor)<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/interview-processor"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/interview-processor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.01478 |
| Opus 5 | $0.00016 | $0.00739 |
| Sonnet 5 | $0.00006 | $0.00296 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
interview-processor 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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill: interview-processor (面试记录处理技能)
本技能用于辅助面试官在面试前后进行高效的结构化处理,沉淀招聘成果并客观自评提问水平。它可以配合 memories-off 技能的 memocli 将生成数据安全写入本地知识图谱。
1. 依赖工具与规范声明 (Dependencies)
本技能依赖本地优先的知识库管理工具 memocli。
外部依赖与规范说明
本 Skill 依赖 memories-off 库进行实体管理与长期记忆。在执行任何任务前,您必须先查阅并完整遵循当前目录下的 memories-off-declare.md 声明文档,以获取其定义的实体类型规范及封装的子过程操作细节。
同时,为了简化指令的输入长度,建议您在 ~/.config/memocli/config.yaml 中配置全局路径别名,并使用简写别名(如 -p work 或 -p life)来运行本技能涉及的所有 memocli 指令。
2. 动态上下文加载机制 (Interviewer Persona)
为了保证面试总结中“团队介绍”以及对面试官表现的自评贴合面试官当前的最新岗位和团队,本技能采用知识图谱优先的动态画像加载机制:
- 第一步:在执行任何子任务前,Agent 必须运行:
memocli search-entities "我自己的面试官画像" -p <path> - 第二步:
- 若实体存在,Agent 应读取其正文(通常包含
## 当前岗位与团队和## 个人面试偏好),以其内容作为当前的背景上下文。 - 若实体不存在,Agent 应友好提醒面试官,并引导其使用以下命令初始化该画像:
echo "## 当前岗位与团队 [在此写明您当前的岗位、所负责团队及核心业务介绍] ## 个人面试偏好 [在此写明您的面试风格、提问原则和关注特质]" | memocli create-entity -p <path> -e "我自己的面试官画像" -t "个人画像" --content-stdin --reason "初始化面试官个人画像"
- 若实体存在,Agent 应读取其正文(通常包含
3. 数据实体建模方案 (KG Entity Models)
本技能在本地知识库中管理四类实体。为符合 memories-off 规范,所有实体必须遵循严格的 H1 (# 实体名) 与 H2 (## 章节名) 标题层级,禁止使用 H3 及以下标题。
3.1 个人画像 (Interviewer Persona)
- 命名规范:
我自己的面试官画像 - 实体类型 (type):
个人画像 - 核心章节:
## 当前岗位与团队## 个人面试偏好
3.2 面试方法论 (Interview Methodology)
- 命名规范:
[领域/岗位]专家面试风格-YYYYMMDD(例如:iOS专家面试风格-20250718) - 实体类型 (type):
面试方法论 - 核心章节:
## 面试风格与偏好(列出面试官在该领域的提问原则、风格和追问逻辑)
3.3 面试问题集 (Interview Question Set)
- 命名规范:
[领域/岗位]面试问题集-YYYYMMDD(例如:大模型产品面试问题集-20250729) - 实体类型 (type):
面试问题集 - 核心章节:根据面试的方向或技术模块划分的多个 H2 章节。
## 核心认知与边界理解## 系统设计与成本控制- ... (根据实际方向动态创建)
- 出站关系:
target_methodology指向其对应的[领域/岗位]专家面试风格-YYYYMMDD实体。
3.4 面试记录 (Interview Record)
- 命名规范:
对[候选人姓名]的面试总结 (YYYY-MM-DD) - 实体类型 (type):
面试记录 - 核心章节:
## 基本信息(候选人姓名、招聘类型 [校招/社招/数字马力]、岗位名称、面试日期)## 面试反馈(建议层级、优势、不足、结论)## 沟通记录与评价(核心讨论话题列表与候选人回答情况评估)## 面试官表现自评(以专家级别对面试官提问、追问、得体度做出的客观改进要求)
- 出站关系:
use_style指向对应面试方法论实体。use_question_set指向对应面试问题集实体。candidate指向候选人个人实体(若有)。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 97 lines · 32 tokens per session scan A 3631021f9a75
interview-processor is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,478 once invoked, about $0.0002 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
experts
Assemble a panel of experts to assess a problem from multiple professional perspectives, surface agreement and disagreement, and deliver a chaired recommendation with clear tradeoffs. Use when the user wants multi-expert judgment, a second opinion, design critique, option comparison, or a recommendation backed by…
create-plan
Create and maintain repository-aware technical plans, implementation plans, refactor proposals, design drafts, and migration plans. Use when Codex is asked to investigate a codebase and propose a solution before implementation; write or update a durable plan file; produce a 方案、实施计划或重构计划; split engineering work into…
google-fonts-curator
Recommend high-taste Google Fonts for websites based on brand tone, page type, and visual direction. Use when the user needs font selection, font pairing, or aesthetic judgment within the Google Fonts ecosystem for landing pages, brand sites, editorial pages, portfolios, or digital products.
programmer-motivator
Give calm, technically grounded encouragement to programmers when the user is stuck on a bug, frustrated by debugging, tired, discouraged, blaming themselves after a mistake, asking for motivation or emotional support while coding, wanting someone to stay with them through a hard problem, celebrating a breakthrough…
subagent-orchestrator
Orchestrate subagent workflows for complex tasks that benefit from decomposition, role-based delegation, and parallel execution. Use when Codex should assemble a temporary team of subagents, choose roles from a reusable role library, create a controlled fallback role when no preset role fits, coordinate read-heavy…
async
Launch and coordinate Codex subagents as deferred tasks. Use when the user wants to start bounded subagent work now, keep the main thread moving without waiting by default, then later join, collect, or redirect that work through a stable task reference.