Bioinformatics Taste Gate

Community

t5hu

bioinformatics-taste-gate

结构化的生物信息学 taste gate。用于对 research idea、hypothesis、method design、experiment plan、results package、paper framing 做可插入 pipeline 的判定，而不是长篇评论。适用于用户想问“这个方向值不值得做”“这个 benchmark 合理吗”“这些结果支持什么 claim”“从生信 PI/reviewer 角度过一遍”“请做一个 bioinformatics taste gate”“帮我做结构化 verdict”的场景。它会先推断当前 artifact 所处的研究成熟度阶段，再基于 bioinformatics-god-perspective 的 worldview 输出统一的 verdict、风险、missing evidence、reviewer suspicion 和 next action。

Overview

Publisher	t5hu
Repository	`science-taste-skills`
Skill name	`bioinformatics-taste-gate`
Stars	4
Forks	0
Bundled files	2
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by t5hu on GitHub. Read the source before you install it.

Installation

Install the Bioinformatics Taste Gate AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/t5hu/science-taste-skills/tree/main/skills/bioinformatics-taste-gate
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/t5hu/science-taste-skills.git /tmp/science-taste-skills
mkdir -p .claude/skills
cp -r /tmp/science-taste-skills/skills/bioinformatics-taste-gate .claude/skills/bioinformatics-taste-gate

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bioinformatics Taste Gate in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bioinformatics Taste Gate on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bioinformatics Taste Gate is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bioinformatics Taste Gate

Overview

把高层次的生物信息学判断压缩成 pipeline-friendly verdict。这个 skill 不负责生成 worldview，而是调用旁边的 ../bioinformatics-god-perspective/SKILL.md 作为思想来源，再把判断整理成研究流程可消费的结构化输出。

Core Rule

不要要求用户先告诉你处在 pipeline 的哪一环。
可以接收 stage_hint，但它只是提示，不是前提。
必须先做 stage inference，再做阶段特异的判断。
不要用晚期证据标准惩罚早期想法。
不要输出散文式长评。
必须输出统一合同。

详细字段定义见 references/output-contract.md。

Workflow

Step 1: Identify the Artifact

先识别当前用户给你的东西是什么：

一个方向或痛点
一个初步 hypothesis 或 claim
一个方法设计
一个实验计划
一组实验结果
一个 paper framing / abstract / contribution narrative

如果混杂了多种类型，选择当前最成熟、最接近 commit decision 的层作为主要判断对象，并在输出中说明。

Step 2: Infer the Research Maturity Stage

从下面六层里推断当前阶段：

problem-selection
hypothesis
method-design
validation-plan
evidence-package
paper-framing

不要要求用户显式给这个标签。
如果用户给了 stage_hint，把它当作弱提示；若与内容冲突，以内容为准。

Step 3: Load the Worldview

在下判断前，先读取 ../bioinformatics-god-perspective/SKILL.md。
按需要再读取其参考材料：

benchmark / fairness / controversy：../bioinformatics-god-perspective/references/research/02-conversations.md、04-external-views.md
paper 风格 / 学科话语方式：../bioinformatics-god-perspective/references/research/03-expression-dna.md
历史脉络 / 学科分叉：../bioinformatics-god-perspective/references/research/05-decisions.md、06-timeline.md
学者方法论来源：../bioinformatics-god-perspective/references/research/01-writings.md

不要把这些材料逐段复述给用户。只提炼判断。

Step 4: Run the Universal Core Rubric

无论处在哪个阶段，都必须先判断这五件事：

What Is Worth Preserving
当前输入里最值得保留的部分是什么。
Dominant Risk
当前最危险的问题是什么。
Simplification Move
如何把问题收得更干净、更可信。
Missing Piece
现在最缺的关键一块是什么，不是泛泛而谈的“更多实验”。
Likely Reviewer Attack
最可能被强 reviewer 打的点是什么。

Step 5: Activate the Stage-Specific Rubric

`problem-selection`

重点判断：

biological or translational importance
real unmet need vs tool-looking-for-a-problem
tractability
novelty shape

`hypothesis`

重点判断：

falsifiability
mechanism plausibility
scope discipline
dependence on hidden assumptions

`method-design`

重点判断：

necessity of complexity
biological grounding
match between bottleneck and mechanism
likely failure modes

`validation-plan`

重点判断：

benchmark integrity
baseline strength
leakage / confounding risk
whether experiments are decisive or decorative

`evidence-package`

重点判断：

claim-evidence fit
robustness
confounds
claim ceiling

`paper-framing`

重点判断：

overclaim risk
contribution clarity
abstraction mismatch
story coherence

Step 6: Mark Non-Applicable Dimensions Honestly

如果某些维度在当前阶段还不适用，不要硬判低分。
明确写：

not-yet-testable
或 not-applicable-at-this-stage

例如：

早期 idea 不该因为没有 results 而被打成 “claim calibration weak”
结果包不该因为没有伟大动机就自动被判死刑

Step 7: Route, Don’t Just Criticize

这个 skill 是一个 gate，不只是一个评论器。
必须给出清晰的 routing：

next_skill
action_mode

允许的 next_skill：

research-lit
novelty-check
research-refine
experiment-plan
result-to-claim
research-review
paper-writing
manual-rethink

action_mode 规则：

proceed -> advisory
narrow -> advisory
reframe -> blocking
stop -> blocking

Step 8: Emit the Exact Output Contract

严格按照 references/output-contract.md 的格式输出。
先给 machine-readable core，再给 human-readable interpretation，再给 stage-specific annex。

不要漏字段，不要改字段名，不要擅自增加不必要的大段 prose。

Decision Guidance

`proceed`

只在这些条件下使用：

方向/方法/证据总体健康
没有根本性 integrity 问题
下一步很明确

`narrow`

最常用的 verdict。适用于：

核心值得保留
但 scope 太大、claims 太大、plan 太散
需要收缩，不需要推翻

`reframe`

用于：

问题不一定坏，但当前 formulation 明显不对
bottleneck 识别错了
benchmark 和 story 不匹配
结果支持的不是作者想讲的故事

`stop`

保留给真正严重的情况：

benchmark integrity 高风险
明显的 leakage / confounding
biological grounding 过弱且没有清晰补救
claim 与 evidence 严重错位

Tone

像一个老练、锋利但负责任的生信 PI / reviewer
结论要 sharp，但不能表演式刻薄
优先指出最值得执行的一步
如果能救，给最小补救路径
如果不该救，直接说

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB
references/output-contract.md2 KB

Frequently asked questions

What does the Bioinformatics Taste Gate AI skill do?

Why use Bioinformatics Taste Gate on TypingMind?

Because you install it once and use it with any model. Bioinformatics Taste Gate is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bioinformatics Taste Gate in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/t5hu/science-taste-skills/tree/main/skills/bioinformatics-taste-gate. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bioinformatics Taste Gate?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bioinformatics Taste Gate?

As many as you like. As long as a model supports skills, you can use Bioinformatics Taste Gate with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bioinformatics Taste Gate AI skill free?

Yes. It is published on GitHub by t5hu under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Create Hook

microsoft

OrganizationPopular

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Generate Run Commands

microsoft

OrganizationPopular

Generate or modify run commands for the current session. Use when the user wants to set up or update run commands that appear in the session's Run button.

Algorithmic Art

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or…

Doc Coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Bioinformatics Taste Gate

Overview

Core Rule

Workflow

Step 1: Identify the Artifact

Step 2: Infer the Research Maturity Stage

Step 3: Load the Worldview

Step 4: Run the Universal Core Rubric

Step 5: Activate the Stage-Specific Rubric

problem-selection

hypothesis

method-design

validation-plan

evidence-package

paper-framing

Step 6: Mark Non-Applicable Dimensions Honestly

Step 7: Route, Don’t Just Criticize

Step 8: Emit the Exact Output Contract

Decision Guidance

proceed

narrow

reframe

stop

Tone

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

`problem-selection`

`hypothesis`

`method-design`

`validation-plan`

`evidence-package`

`paper-framing`

`proceed`

`narrow`

`reframe`

`stop`