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 dongshuyan/compass-skills --skill assess-interview-candidategit clone --depth 1 https://github.com/dongshuyan/compass-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/dongshuyan/compass-skills/assess-interview-candidate)<a href="https://agentmods.dev/skills/dongshuyan/compass-skills/assess-interview-candidate"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/assess-interview-candidate/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/dongshuyan/compass-skills/assess-interview-candidate"><img src="https://agentmods.dev/badge/skills/dongshuyan/compass-skills/assess-interview-candidate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00129 | $0.04546 |
| Opus 5 | $0.00064 | $0.02273 |
| Sonnet 5 | $0.00026 | $0.00909 |
| Haiku 4.5 | $0.00013 | $0.00455 |
Grade A, and why
assess-interview-candidate 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 11d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
候选人评估与面试报告
目标
把简历和岗位要求整理成两层材料：
- 后台保留完整岗位模型、证据账本、来源、假设和评分数据，便于复核。
- 给面试官的 HTML 只保留“候选人简介、简历疑点与水分排查、面试提问”三个模块，使用通俗中文。
始终区分候选人明确提供的事实、外部佐证、推断和未知。最终招聘决定由具备权限的人作出。
可移植运行约定
本 Skill 不依赖某个特定 Agent、Skill 安装根目录或命令行外壳。任何能够读取本地文件并运行 Python 3.10 及以上版本的 Agent 都可以使用；PDF 处理、联网核验和浏览器检查按当前宿主实际具备的能力执行。
- 先把
<skill-dir>解析为本SKILL.md所在目录，不猜测固定安装路径。 <python>表示当前系统可用的 Python 3 启动方式。Windows 通常使用py -3或python，macOS 与 Linux 通常使用python3或python；先用版本命令确认实际可用项。<approved-root>、<output-dir>等是路径占位符，不代表固定路径分隔符。通过宿主文件 API 或pathlib组合路径，并把含空格或非 ASCII 字符的路径作为一个完整参数传入。- 命令示例使用单行、外壳无关的参数形式。不要依赖 Bash 续行符、环境变量展开、当前用户主目录结构或某个 Agent 的专用工具名。
agents/中的文件只是特定宿主可选的界面元数据；核心工作流以本文件、references/、scripts/、assets/和evals/为准。
遇到能力差异时按 agent-portability.md 处理。缺少必要能力时明确报告未完成的核验，不得把未执行的步骤写成已完成。
结果契约
每次完整运行在新的案件目录中生成：
input/ 原始简历、岗位要求和用户提供的链接
normalized/ 经文字提取与视觉核对的文本及案件清单
research/ 查询和来源记录
models/ 岗位模型、证据账本、行为假设和面试蓝图
interview/ 初始评分状态
output/ 完整后台数据、精简报告数据和离线 HTML
audit/ 运行、校验和隐私排除记录
关键输出：
output/assessment-data.json
output/interviewer-report-data.json
output/<候选人姓名>-候选人评估与面试报告.html
HTML 文件名、浏览器标题和页面最上方标题都必须包含候选人姓名。不要覆盖既有案件或报告。
开始前读取
先把 <skill-dir> 解析为本文件所在目录。
- 每次读取 workflow-contract.md、evidence-and-inference-policy.md 和 privacy-and-fairness-cn.md。
- 建立岗位模型前读取 job-modeling.md。
- 联网核验候选人职业证据前读取 research-and-identity-policy.md。
- 生成题目时读取 structured-interview-methods.md 和 scoring-and-coverage.md。
- AI、LLM、Agent 或工程岗位读取 role-adapter-ai-llm-engineering.md。
- 写 JSON 前读取对应 Schema；面试官报告必须读取 schema-interviewer-report.json。
What ships with it
31 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.
- agents/openai.yaml 329 B
- assets/candidate-assessment-template.html 35 KB
- evals/evals.json 9.9 KB
- references/agent-portability.md 3.5 KB
- references/evidence-and-inference-policy.md 7.5 KB
- references/job-modeling.md 3.8 KB
- references/privacy-and-fairness-cn.md 7.1 KB
- references/research-and-identity-policy.md 4.0 KB
- references/role-adapter-ai-llm-engineering.md 5.7 KB
- references/schema-evidence-ledger.json 6.2 KB
- references/schema-interview-blueprint.json 5.6 KB
- references/schema-interviewer-report.json 14 KB
- references/schema-job-model.json 4.5 KB
- references/schema-source-record.json 9.5 KB
- references/scoring-and-coverage.md 9.5 KB
- references/structured-interview-methods.md 4.8 KB
- references/workflow-contract.md 14 KB
- scripts/calculate_interview_score.py 15 KB runs code
- scripts/create_candidate_case.py 3.6 KB runs code
- scripts/derive_timeline_age.py 9.6 KB runs code
- scripts/normalize_inputs.py 9.0 KB runs code
- scripts/prepare_candidate_photo.py 12 KB runs code
- scripts/render_candidate_report.py 5.3 KB runs code
- scripts/validate_candidate_report.py 10 KB runs code
- scripts/validate_case_contract.py 28 KB runs code
- scripts/validate_evidence_ledger.py 15 KB runs code
- scripts/validate_interviewer_report_data.py 33 KB runs code
- scripts/validate_source_log.py 21 KB runs code
- tests/test_candidate_profile_enrichment.py 39 KB runs code
- tests/test_interviewer_report.py 29 KB runs code
- tests/test_public_package.py 7.0 KB runs code
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.
- 11d ago First seen · 236 lines · 129 tokens per session scan A 45aadc03fc07
assess-interview-candidate is a skill published in the GitHub repository dongshuyan/compass-skills (724 stars, last pushed 16d ago), licensed MIT. It adds 129 tokens to every session and 4,546 once invoked, about $0.0006 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
fiscaliste
Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…
fedramp
Expert guidance for FedRAMP certification and compliance under CR26 (FedRAMP Consolidated Rules for 2026). Use this skill whenever a user asks about FedRAMP authorization, ATO (Authority to Operate), cloud security for federal government, NIST SP 800-53 controls, CSP compliance, or any of the core FedRAMP document…
eu-cra
Expert EU Cyber Resilience Act (CRA) advisor for Regulation (EU) 2024/2847 — mandatory cybersecurity and vulnerability handling requirements for all products with digital elements (PDEs) sold in the EU. Use this skill for gap analysis, product classification (Default / Class I / Class II), conformity assessment route…
aenderungsvorbehalt-308
Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.
agb-rechtswahl-schweizer-recht-rom-i
Für AGB Rechtswahl Schweizer Recht Rom I: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-rechtswahl-schweizer-recht-rom-i.