New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Autoresearch Feishu Three Table

by bosprimigenious in bosprimigenious/autoresearch-skills

在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。

MITAuto-check passedAgent Workflows

Install Autoresearch Feishu Three Table

skills CLI
$ npx skills add bosprimigenious/autoresearch-skills --skill autoresearch-feishu-three-table -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bosprimigenious/autoresearch-skills autoresearch-feishu-three-table --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bosprimigenious/autoresearch-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/autoresearch-feishu-three-table .claude/skills/autoresearch-feishu-three-table && rm -rf skills-src

Use ~/.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/

Facts

Skill name
autoresearch-feishu-three-table
GitHub stars
153
Token cost
~413 tokens
SKILL.md length
57 words
Files
8 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。

  • Works in 7 steps: 确认授权边界。 只使用用户当前可访问的… → 解析真实 schema。… → 建立跨表身份。… → …
  • Tasks that involve Autonomous loops
  • SKILL.md covers 先识别当前动作, 共同执行顺序, 权限失败 and 完成条件
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Autoresearch Feishu Three Table is an agent skill from bosprimigenious/autoresearch-skills. 在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。

Its SKILL.md is about 410 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including reference files (for example `AGENTS.md`, `CLAUDE.md` and `agents/openai.yaml`).

It sits in Agent Workflows, covering Autonomous loops and Messaging and chat bots. It works with Feishu (Lark). The repository describes itself as: Reusable skills for AutoResearch task design, isolation, QA, and handoff. The licence is MIT.

When your agent uses it

  • Tasks that involve Autonomous loops
  • Tasks that involve Messaging and chat bots

Example prompts

  • “/autoresearch-feishu-three-table”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 确认授权边界。 只使用用户当前可访问的 tenant、文档和连接器。先做只读探测，记录资源类型、当前期次、表/视图、字段 schema、记录主键和读写能力。页面可见不等于表可写，能写记录不等于能改 schema 或验收字段。
  2. 解析真实 schema。 通过当前资源的元数据、字段列表和状态枚举匹配语义字段；不硬编码列序号、视图位置或旧字段名。无法列字段时停止，不通过猜测构造请求。
  3. 建立跨表身份。 以当前期次的权威题号为主键，同时核对规范论文标识、精确标题和交付摘要。只按项目展示名或模糊搜索命中不能写入。
  4. 预演最小变更。 写出目标记录、拟改字段、旧值摘要、新值摘要和证据引用。除用户明确要求外，不新增字段、改状态枚举、覆盖他人、删除记录或批量更新。
  5. 按职责写入。 领取人只填领取范围，提交人只填材料与自检，验收人或组长才填其受保护结论。用户要求提交材料不等于授权代替审核者判定。
  6. 写后回读。 重新读取目标记录，逐字段比较规范化值，并确认关联记录仍指向同一期次和题号。接口成功但回读不一致时记 CONFLICT，不得报告完成。
  7. 保存私有操作账本。 记录时间、资源逻辑名、记录主键的本地别名、字段变化、回执、证据哈希和未完成项。真实 URL、base/table token、record ID、用户 ID、姓名、邮箱和附件 capability URL 不得进入公开仓库、公开日志或 skill 示例。

What it can do on your machine

Read from SKILL.md and the folder at commit d8ff7e2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Autoresearch Feishu Three Table loads about 413 tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 57 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~413
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.2k

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.

Safety

Auto-check passed

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from bosprimigenious/autoresearch-skills at commit d8ff7e2, republished under its MIT licence (© bosprimigenious). 57 words, ~413 tokens.

Download SKILL.mdSave it as .claude/skills/autoresearch-feishu-three-table/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
autoresearch-feishu-three-table
description
在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。

AutoResearch 飞书三表流转

把三张表视为有顺序的外部状态机，而不是三份可凭记忆填写的表单：当期领题表提供权威题号，完成提交/验收表绑定交付物，组长初检表记录复核结论。任何写入都只能使用当前已授权身份和当前期次的实时 schema；旧期导出、文件夹名、历史题号和聊天记录都不是权威源。

先识别当前动作

共同执行顺序

  1. 确认授权边界。 只使用用户当前可访问的 tenant、文档和连接器。先做只读探测，记录资源类型、当前期次、表/视图、字段 schema、记录主键和读写能力。页面可见不等于表可写，能写记录不等于能改 schema 或验收字段。
  2. 解析真实 schema。 通过当前资源的元数据、字段列表和状态枚举匹配语义字段；不硬编码列序号、视图位置或旧字段名。无法列字段时停止，不通过猜测构造请求。
  3. 建立跨表身份。 以当前期次的权威题号为主键，同时核对规范论文标识、精确标题和交付摘要。只按项目展示名或模糊搜索命中不能写入。
  4. 预演最小变更。 写出目标记录、拟改字段、旧值摘要、新值摘要和证据引用。除用户明确要求外，不新增字段、改状态枚举、覆盖他人、删除记录或批量更新。
  5. 按职责写入。 领取人只填领取范围，提交人只填材料与自检，验收人或组长才填其受保护结论。用户要求提交材料不等于授权代替审核者判定。
  6. 写后回读。 重新读取目标记录，逐字段比较规范化值，并确认关联记录仍指向同一期次和题号。接口成功但回读不一致时记 CONFLICT，不得报告完成。
  7. 保存私有操作账本。 记录时间、资源逻辑名、记录主键的本地别名、字段变化、回执、证据哈希和未完成项。真实 URL、base/table token、record ID、用户 ID、姓名、邮箱和附件 capability URL 不得进入公开仓库、公开日志或 skill 示例。

权限失败

权限不足、账号失效、资源已转移或用户已经离开原组织时，不循环登录、不复用旧凭据、不请求扩大权限，也不尝试通过旧分享链接绕过访问控制。保留脱敏错误类别和请求阶段，结论写 INCOMPLETE_PERMISSION。替代路径只能是：由当前资源所有者授权新身份、由仍有权限的负责人代填经过复核的字段草稿，或迁移到用户当前控制且被流程认可的新表。

如果旧表不可访问，新表尚未被明确指定为权威源，则只能生成待填草稿和证据清单，不能宣称“已领取”“已提交”“验收通过”或“初检完成”。

完成条件

仅当目标记录唯一、题号来自当期权威表、字段与角色权限匹配、写入有成功回执且写后回读一致时，才能报告对应动作完成。三表是独立门禁：领题成功不证明提交成功，提交成功不证明验收通过，QA 通过也不自动等于组长已回填。

© bosprimigenious, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in skills/autoresearch-feishu-three-table of bosprimigenious/autoresearch-skills.

  • SKILL.md
  • AGENTS.md
  • CLAUDE.md
  • agents/openai.yaml
  • references/lead-review-table.md
  • references/state-and-evidence.md
  • references/submission-acceptance-table.md
  • references/topic-claim-table.md

Open the folder on GitHubat commit d8ff7e2

Compare with similar skills

Autoresearch Feishu Three Table 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.

Autoresearch Feishu Three Table compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autoresearch Feishu Three Table this skillbosprimigenious/autoresearch-skills153—~413Automated safety check: PassMIT
Feishu Multi Agenthyperlist/feishu-multi-agent273—~419Automated safety check: PassNone
Tinyplacetinyhumansai/tiny.place138—~5.1kAutomated safety check: PassGPL-3.0-or-later
Incremental Implementationskuramatata/my-pi-agent114—~869Automated safety check: NotesNone
Feishu Doc Writerhyperlist/feishu-multi-agent273—~505Automated safety check: PassNone
Openlark Code Standardsfoxzool/openlark106—~1.8kAutomated safety check: NotesApache-2.0

Similar skills

  • Feishu Multi Agent

    hyperlist/feishu-multi-agent

    飞书多 Agent 系统搭建指南。当用户要求创建新的功能 Agent、配置飞书群聊绑定、 搭建多 Agent 协作系统时激活此 skill。

    273 GitHub stars~419 tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed

  • Tinyplace

    tinyhumansai/tiny.place

    Live on tiny.place (the agent-to-agent social network) like a person lives on a social app — entirely through the tinyplace CLI.

    138 GitHub stars~5.1k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Incremental Implementation

    skuramatata/my-pi-agent

    A skill your agent uses when implementing my-pi-agent changes that touch multiple files, shared runtime behavior, prompt/skill logic, Feishu channel flow, verifier behavior, or coding workflow lanes.

    114 GitHub stars~869 tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check: notes

  • Feishu Doc Writer

    hyperlist/feishu-multi-agent

    Feishu document writing skill. An agent skill from hyperlist/feishu-multi-agent.

    273 GitHub stars~505 tokensUpdated 7 mo ago
    Productivity & AutomationAuto-check passed

  • Openlark Code Standards

    foxzool/openlark

    OpenLark 项目代码规范检查技能。用于快速审查仓库内的架构一致性、API 实现套路、参数校验、命名与导出规范，并输出可执行检查清单与证据路径。Triggers: code review / consistency check / architecture audit / 规范检查 / 风格一致性 / 体检 / 对齐约定。项目锚点见 AGENTS.mdCONVENTIONS 与…

    106 GitHub stars~1.8k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

  • Sync Specs

    nexu-io/nexu

    A skill your agent uses when code changes may have made documentation outdated, when reviewing docs for consistency, or when the user asks to sync or audit documentation.

    3.3k GitHub stars~1.2k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed

More from bosprimigenious/autoresearch-skills

All 8 skills in this repo

  • Autoresearch Baseline Quality

    bosprimigenious/autoresearch-skills

    对 AutoResearch 的正式 Baseline 做只读合理性审查，检查训练不足、实现故障、预算或 seed 不公平及缺乏代表性的弱对照，区分合理 naive Starter 与评分锚点。适用于专家提交包和 Baseline/Reference 证据复核，不用于求解任务或要求 Baseline 达到 SOTA。

    153 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed

  • Autoresearch Paper Discovery

    bosprimigenious/autoresearch-skills

    自主检索、去重并筛选可转化为 AutoResearch 优化任务的论文，核查论文与源码许可、优化面、评测、资源、效应噪声和目标 Harness 可交付性。用于从零找论文、维护候选池或在投入实现前做选题预检；不用于已经确定论文后的实验执行。

    153 GitHub stars~506 tokensUpdated 6 days ago
    Auto-check passed

  • Autoresearch Task QA

    bosprimigenious/autoresearch-skills

    对 AutoResearch 目录或 ZIP 做只读质检；先审优化面是否仅调参、Baseline 是否合理、Reference 提升是否充分，再查 21 项实现、严格 Docker 路径、Harbor 接口与成对训练证据。输出方法介绍、完整跑分、专家退回说明及 TXT/Markdown/JSON 报告；不用于求解任务。

    153 GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed

  • Autoresearch Run Isolation

    bosprimigenious/autoresearch-skills

    为 AutoResearch 的双 Agent 轨迹、付费 GPU 长跑、Docker 执行、可信评测与恢复建立共享协议、成本决策和隔离边界。用于小时/包日选择、启动或恢复 campaign、设计证据与防止题目或轨迹串用；不替代具体任务算法或最终平台 QA。

    153 GitHub stars~553 tokensUpdated 6 days ago
    Auto-check passed

  • Autoresearch Task Authoring

    bosprimigenious/autoresearch-skills

    从论文与代码仓设计可交付的 AutoResearch 工程题，确定 Starter、Baseline、Reference、评分器、Harbor 结构和证据契约。用于出题、改题或审题；不替代提交包最终 QA。

    153 GitHub stars~390 tokensUpdated 6 days ago
    Auto-check passed

  • Autoresearch Conversation Handoff

    bosprimigenious/autoresearch-skills

    将 AutoResearch 的 Claude、Codex、Cursor 对话、命令输出和外部提交状态整理为可执行交接，区分事实、失败、待办和证据边界。用于总结长会话、换 agent 或收尾归档；不把对话陈述当作已验证事实。

    153 GitHub stars~183 tokensUpdated 6 days ago
    Auto-check passed

Works with

Categories

Questions about Autoresearch Feishu Three Table

What does Autoresearch Feishu Three Table do?

在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转，核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论；不用于绕过组织权限、恢复离职账号或替代任务 QA。. Autoresearch Feishu Three Table is an agent skill from bosprimigenious/autoresearch-skills.

When should I use Autoresearch Feishu Three Table?

Autoresearch Feishu Three Table fits situations like: tasks that involve Autonomous loops; tasks that involve Messaging and chat bots.

How do I install Autoresearch Feishu Three Table in Claude Code?

Run `npx skills add bosprimigenious/autoresearch-skills --skill autoresearch-feishu-three-table -a claude-code`. Or copy the skill folder (skills/autoresearch-feishu-three-table in bosprimigenious/autoresearch-skills) into .claude/skills/autoresearch-feishu-three-table in your project. Claude Code loads it when a task matches its description.

How do I install Autoresearch Feishu Three Table in Codex?

Run `npx skills add bosprimigenious/autoresearch-skills --skill autoresearch-feishu-three-table -a codex`. Or copy the skill folder (skills/autoresearch-feishu-three-table in bosprimigenious/autoresearch-skills) into .agents/skills/autoresearch-feishu-three-table in your project. Codex loads it when a task matches its description.

Can I use Autoresearch Feishu Three Table in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bosprimigenious/autoresearch-skills --skill autoresearch-feishu-three-table -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autoresearch-feishu-three-table, .gemini/skills/autoresearch-feishu-three-table, .github/skills/autoresearch-feishu-three-table and .opencode/skills/autoresearch-feishu-three-table in your project.

What does Autoresearch Feishu Three Table need to run?

SKILL.md names no scripts, command-line tools or credentials: Autoresearch Feishu Three Table is instructions for the agent only.

Does Autoresearch Feishu Three Table access the network?

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.

Is Autoresearch Feishu Three Table safe to install?

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. Review the folder before installing.

What licence does Autoresearch Feishu Three Table use?

Autoresearch Feishu Three Table is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Autoresearch Feishu Three Table use?

About 413 tokens (SKILL.md is roughly 1.7k 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 3.8k tokens, read only when the agent opens those files.

What are the alternatives to Autoresearch Feishu Three Table?

Skills that share tags, products or a category with Autoresearch Feishu Three Table: Feishu Multi Agent (hyperlist/feishu-multi-agent, 273 stars), Tinyplace (tinyhumansai/tiny.place, 138 stars), Incremental Implementation (skuramatata/my-pi-agent, 114 stars) and Feishu Doc Writer (hyperlist/feishu-multi-agent, 273 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autoresearch Feishu Three Table?

bosprimigenious (a GitHub user) maintains it in bosprimigenious/autoresearch-skills, which has 153 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 4, 2026.

Source: bosprimigenious/autoresearch-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.