Process Inbox
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dongshuyan/compass-skills assess-interview-candidate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/assess-interview-candidate .claude/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .claude/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dongshuyan/compass-skills assess-interview-candidate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/assess-interview-candidate .agents/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .agents/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dongshuyan/compass-skills assess-interview-candidate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/assess-interview-candidate .cursor/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .cursor/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/dongshuyan/compass-skills.git --path skills/assess-interview-candidate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dongshuyan/compass-skills assess-interview-candidate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/assess-interview-candidate .gemini/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .gemini/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install dongshuyan/compass-skills assess-interview-candidateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/assess-interview-candidate .github/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .github/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dongshuyan/compass-skills assess-interview-candidate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dongshuyan/compass-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/assess-interview-candidate .opencode/skills/assess-interview-candidate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "assess-interview-candidate" agent skill from https://github.com/dongshuyan/compass-skills/tree/master/skills/assess-interview-candidate into .opencode/skills/assess-interview-candidate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "assess-interview-candidate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
assess-interview-candidate根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。
Assess Interview Candidate is an agent skill from dongshuyan/compass-skills. 根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 37 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `evals/evals.json` and `references/agent-portability.md`).
It sits in Productivity & Automation. It works with Python. The repository describes itself as: 司南:个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 1b2e556. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Assess Interview Candidate loads about 2.2k tokens when it runs, and up to ~28k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 298 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from dongshuyan/compass-skills at commit 1b2e556, republished under its MIT licence (© dongshuyan). 298 words, ~2,218 tokens.
.claude/skills/assess-interview-candidate/SKILL.md (or your agent's skills folder). This skill also uses 33 other files; get the full folder from GitHub.把简历和岗位要求整理成两层材料:
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。
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。
<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。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。
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.htmlHTML 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。
先把 <skill-dir> 解析为本文件所在目录。
必需输入:
candidate-cases/。尽可能取得:
缺少简历或岗位要求时以 REQUIRED_INPUT_MISSING 停止,不创建案件。缺少公司地点时继续生成,但写明“距离无法计算,待补充公司地址”。缺少候选人联网核验权限时关闭该分支,不影响本地简历分析。
<python> "<skill-dir>/scripts/create_candidate_case.py" --root "<approved-root>" --role-slug "<role-slug>"复制原始输入并记录哈希,不移动或删除用户文件。PDF 简历在案件目录中使用固定受限副本 input/resume-original.pdf,同时在案件清单保留原文件名和哈希。PDF 必须同时使用当前宿主可用的文字提取能力和逐页视觉检查能力,核对页数、姓名、时间线、表格、图片文字及提取遗漏。为保证完整核对,原件和逐页提取文本可能保留电话、邮箱、证件号或精确住址,因此 input/ 与 normalized/ 都按受限候选人资料处理;这些内容不得进入联网查询、面试官数据或 HTML。若无法完成逐页视觉检查,以 PDF_VISUAL_CHECK_UNAVAILABLE 停止生成最终报告,并说明缺少的能力。
逐页视觉检查时同时记录照片状态:
not_present;ambiguous;extraction_unavailable;included。先检查 PDF 的嵌入图片;若头像不是独立图片,再从对应页面裁切。所有提取结果统一转换为 PNG,并在转换后再次与 PDF 页面视觉比对;JPEG、PPM 等格式不能直接嵌入。不得从公开主页或其他文件补图,不得使用人脸识别、相似度匹配、照片年龄估计或外貌分析。选定图片后运行下列脚本;脚本要求来源为案件内的 input/resume-original.pdf,会在解压前检查尺寸、校验 PNG 结构和像素数据、移除非显示所需元数据和文件尾随内容,再以内嵌图片输出:
<python> "<skill-dir>/scripts/prepare_candidate_photo.py" --input "<visually-confirmed-image>" --resume-pdf "<original-resume-pdf>" --page <one-based-page> --extraction-method embedded_image --image-index <zero-based-image-index>页面裁切时把最后两个参数改为 --extraction-method page_crop --crop-box <x,y,width,height>。脚本只负责校验格式、尺寸、哈希和结构化来源,不能替代视觉身份确认。
按“工作产出 → 关键任务 → 能力 → 目标熟练度 → 可接受证据 → 验证方法”拆解岗位。记录重要性、频率、失败影响和是否入职即需具备。缺少招聘方确认时标为暂定,不把学历、年限或公司名气自动当作能力。
对快速变化岗位进行不含候选人身份信息的当前岗位研究;优先官方招聘页、一手技术资料、标准和职业框架。
逐条拆分与岗位重要能力有关的声明,记录原文位置、情境、任务、本人行动、结果、个人贡献边界、可验证材料和剩余缺口。简历没有写某项能力只表示“当前证据不足”,不能直接写成“不具备”。
疑点使用“描述不清”“可核验缺口”等中性语言。优先检查:
仅研究获得允许、公开可访问、身份确认且与岗位直接相关的职业资料。系统发现的页面至少需要两个一致职业锚点;同名不足以确认身份。不得搜索年龄、籍贯、婚姻、家庭或私人生活。没有公开主页、论文或代码仓库不得扣分。
继续生成岗位模型、证据账本、候选人视角、九类岗位行为假设、面试蓝图、评分状态、来源记录和 output/assessment-data.json。这些对象供审计与人工复核,不直接展示在面试官 HTML 中。
按 schema-interviewer-report.json 生成 output/interviewer-report-data.json。
personal_info 只保存候选人主动提供的出生信息、出生地、老家或籍贯、婚姻状况、现居城市;没有就显示“未提供”,不得搜索或补写。candidate_overview.candidate_photo,不得放进 personal_info。只有 status=included 时 HTML 才显示本地 data: 图片;其他状态不保留空白照片栏。candidate_overview.timeline_age_estimate:优先使用简历明确写出的最早本科入学时间;没有入学时间时,只有同时明确写出本科毕业时间和学制,才可反推入学年份。毕业月份或日期不能证明入学月份或日期,因此回推锚点一律降为年份精度。以本科入学年龄 18 岁为中心,固定使用 16–20 岁区间,并把锚点精度造成的日期不确定性计入上下界。只列与岗位核心能力直接相关的 0–8 项,按能力重要性降序。每项写清:对应能力、简历原话、哪里说不清、为什么要核实、怎么核实。不要在可见文案中输出内部状态码、能力编号或英文评估术语。
生成 12–18 道按优先级排列的问题。问题必须能让面试官直接照读。每道岗位题提供提问目的、回答好/一般/差的具体表现、加分点和减分点。
题库必须包含:
HTML 只嵌入 interviewer-report-data.json,不嵌入完整 assessment-data.json。页面恰好包含三个主模块:
头像只在 candidate_photo.status=included 时出现在候选人简介中,并注明来自简历 PDF、只展示、不参与评估或排序。履历年龄区间使用独立标签,明确它是推算而非候选人自述。每道题支持:单击“标记”默认设为黄色“可能要问”;下拉改为红色“一定要问”、蓝色“备选”或取消;记录“好/一般/差/未问”及备注。地点、到岗和其他自述类问题只记录“已记录/不便回答/未问”。重点标记和回答自动保存到当前浏览器本机,并可导出或清空。不得发送网络请求、加载外部资源或保存候选人资料到远程服务。
页面不显示简历证据分、综合分、权重、覆盖率、门槛、可比性、来源表、九类行为假设或内部英文状态。这些信息继续留在后台文件。
使用:
<python> "<skill-dir>/scripts/derive_timeline_age.py" --report-date "<YYYY-MM-DD>" --undergraduate-start "<YYYY-or-YYYY-MM-or-YYYY-MM-DD>" --source-locator "<resume-page-or-section>"
<python> "<skill-dir>/scripts/derive_timeline_age.py" --report-date "<YYYY-MM-DD>" --undergraduate-graduation "<YYYY-or-YYYY-MM-or-YYYY-MM-DD>" --degree-duration-years <explicit-duration> --source-locator "<resume-page-or-section>"
<python> "<skill-dir>/scripts/validate_interviewer_report_data.py" "<interviewer-report-data.json>"
<python> "<skill-dir>/scripts/render_candidate_report.py" --data "<interviewer-report-data.json>" --output "<candidate-report-file>"
<python> "<skill-dir>/scripts/validate_candidate_report.py" "<candidate-report-file>"如需核对后续时间线,可重复传入 --consistency-check-json。每个参数是一个含 event、date 和 source_locator 的 JSON 对象;脚本自动补出日期精度,并在明确矛盾时输出 timeline_conflict。
渲染器会拒绝文件名不含候选人姓名的输出。
继续校验后台对象:
<python> "<skill-dir>/scripts/validate_case_contract.py" --job-model "<job-model.json>" --sources "<sources.json>" --evidence-ledger "<evidence-ledger.json>" --blueprint "<interview-blueprint.json>" --score-state "<score-state.json>" --assessment-data "<assessment-data.json>"
<python> "<skill-dir>/scripts/validate_source_log.py" "<sources.json>"
<python> "<skill-dir>/scripts/validate_evidence_ledger.py" "<evidence-ledger.json>"
<python> "<skill-dir>/scripts/calculate_interview_score.py" --blueprint "<interview-blueprint.json>" --state "<score-state.json>"将命令、时间、退出码、错误和警告写入 audit/validation.json。交付时说明案件目录、HTML 文件、采用与拒绝的来源数量、关键未知项、校验结果和仍需人工确认的内容。
REQUIRED_INPUT_MISSING:缺少简历或岗位要求;PDF_VISUAL_CHECK_UNAVAILABLE:当前宿主无法完成 PDF 逐页视觉核对;AUTHORITY_UNCONFIRMED:无法确认有权处理简历;IDENTITY_UNRESOLVED:候选人职业页面身份不能确认;PRIVATE_ACCESS_REQUIRED:需要登录私人账号或绕过权限;SENSITIVE_DATA_HIT:联网结果出现不应处理的私人或敏感内容;CONTACT_DETAIL_LEAK:面试官数据或 HTML 中出现邮箱、手机号、证件号或其他不应展示的联系方式;JOB_RELEVANCE_MISSING:信息无法映射到岗位任务;AUTOMATED_ADVERSE_ACTION:要求自动拒绝、排序或触发不利决定;HUMAN_REVIEW_MISSING:拟把未经人工确认的结果用于招聘决定。停止一个联网分支不妨碍继续处理获准的本地材料。
© dongshuyan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 33 other files (scripts, references, assets) in skills/assess-interview-candidate of dongshuyan/compass-skills.
Open the folder on GitHubat commit 1b2e556
Assess Interview Candidate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Assess Interview Candidate this skilldongshuyan/compass-skills | 753 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Process Inboxtelegramdesktop/tdesktop | 33k | 1 repos | ~5.4k | Automated safety check: Pass | GPL-3.0 | |
| Process InboxTDesktop-x64/tdesktop | 3k | — | ~4.3k | Automated safety check: Pass | GPL-3.0 | |
| Telegrambubbuild/bub | 1.7k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Browser Use Terminalbrowser-use/terminal | 650 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Robocorp Automationrobocorp/robocorp | 653 | — | ~3.3k | Automated safety check: Pass | Apache-2.0 |
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
TDesktop-x64/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
bubbuild/bub
Telegram Bot skill for sending and editing Telegram messages via Bot API.
browser-use/terminal
Direct browser control via the Browser Use Terminal CLI. An agent skill from browser-use/terminal.
robocorp/robocorp
Bootstrap from an empty folder or build, debug, locally run, and validate Python automations built with Robocorp or Sema4.ai tooling, robocorp.tasks, rcc, robocorp-browser, and RPA Framework.
czl9707/build-your-own-openclaw
Create, list, and delete scheduled cron jobs. An agent skill from czl9707/build-your-own-openclaw.
dongshuyan/compass-skills
Maintains a repo-local task forest or task DAG for the current workspace.
dongshuyan/compass-skills
Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan.
dongshuyan/compass-skills
Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill.
dongshuyan/compass-skills
Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session.
dongshuyan/compass-skills
Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses.
dongshuyan/compass-skills
Draft, audit, or minimally revise English- or Chinese-language academic prose to reduce formulaic, vacuous, mechanically repetitive, or process-leaking language while preserving claims, evidence…
Works with
Categories
根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题,以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现,或自动录用、淘汰、排序候选人。. Assess Interview Candidate is an agent skill from dongshuyan/compass-skills.
Assess Interview Candidate fits situations like: productivity & Automation work in your project.
Run `npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a claude-code`. Or copy the skill folder (skills/assess-interview-candidate in dongshuyan/compass-skills) into .claude/skills/assess-interview-candidate in your project. Claude Code loads it when a task matches its description.
Run `npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a codex`. Or copy the skill folder (skills/assess-interview-candidate in dongshuyan/compass-skills) into .agents/skills/assess-interview-candidate in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dongshuyan/compass-skills --skill assess-interview-candidate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assess-interview-candidate, .gemini/skills/assess-interview-candidate, .github/skills/assess-interview-candidate and .opencode/skills/assess-interview-candidate in your project.
SKILL.md names no scripts, command-line tools or credentials: Assess Interview Candidate is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Assess Interview Candidate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 25k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Assess Interview Candidate: Process Inbox (telegramdesktop/tdesktop, 33k stars), Process Inbox (TDesktop-x64/tdesktop, 3k stars), Telegram (bubbuild/bub, 1.7k stars) and Browser Use Terminal (browser-use/terminal, 650 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
dongshuyan (a GitHub user) maintains it in dongshuyan/compass-skills, which has 753 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 26, 2026.
Source: dongshuyan/compass-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.