thinkinglabs
Interface for interacting with the Thinkinglabs public corpus.
Install
mkdir -p .claude/skills/thinkinglabs && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15844" && unzip -o skill.zip -d .claude/skills/thinkinglabs && rm skill.zipInstalls to .claude/skills/thinkinglabs
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when reading, querying, or integrating with the public thinkinglabs corpus through Markdown, JSON, feeds, or MCP.Key capabilities
- →Discover public pages, JSON APIs, and MCP endpoints
- →Read clean page-shaped Markdown from canonical URLs
- →Query public collections via JSON APIs or MCP tool
- →Traverse public resources through the remote MCP endpoint
- →Submit structured answers to public questions with an MCP tool
How it works
This skill allows agents to interact with the public thinkinglabs corpus by discovering content, querying public objects, and inspecting source-backed pages. It uses `/llms.txt` as an index for public surfaces.
Inputs & outputs
When to use thinkinglabs
- →Query thinkinglabs data
- →Read public documentation
- →Integrate with public mcp
About this skill
Thinkinglabs
Thinkinglabs is a public markdown-canonical thinking surface. Use this skill when an agent needs to discover content, query public objects, inspect source-backed pages, or submit an answer to an open question.
What I Can Accomplish
- Discover public pages, Markdown, JSON APIs, feeds, and local MCP setup from
/llms.txt. - Read clean page-shaped Markdown by appending
.mdto canonical public URLs with Markdown variants. Use/index.mdfor the homepage. - Query public collections through
/api/<kind>.jsonor thequery_viewtool on a local MCP installation. - Run the local MCP server from an installed checkout with
pnpm mcp:thinkinglabs. - Precheck contact intent with
contact.precheckbefore preparing a human email handoff. - Submit structured answers to public questions through a local MCP installation with
question.submit.
Required Inputs
- A target task, topic, tag, object slug, or public view name.
- For MCP use, an installed checkout and a client that supports stdio or local Streamable HTTP.
- For question submissions, the question slug and a substantive answer body.
Constraints
- The canonical source is
content/<kind>/*.md; generated artifacts are projections. - Public JSON APIs and Markdown variants are read-only.
- The MCP server is public-only; provenance and private local state are not exposed.
contact.sendprepares a handoff and does not send mail.- Token counts are approximate and use the
chars/4estimate exposed asagent_metadata.approx_token_count. - Prefer
/llms.txt,.mdvariants, JSON APIs, feeds, or MCP over crawling rendered HTML.
Key Documentation
/llms.txt: Agent-readable public surface index./agents: When to use the public corpus and an overview of its machine-readable surfaces./docs/apiand/docs/mcp: JSON API reference and MCP connection guide./agent-permissions.json: Automated-access policy and preferred entrypoints.AGENTS.md: Repository operating instructions.docs/agents/mcp-http-server.md: Standalone MCP HTTP setup.
When not to use it
- →The task requires modifying private local state
- →The task involves database schema evolution without API surface impact
- →The task is about adding a new route file or domain decomposition
Prerequisites
Limitations
- →Public JSON APIs and Markdown variants are read-only
- →The MCP server is public-only; provenance and private local state are not exposed
- →`contact.send` prepares a handoff and does not send mail
How it compares
This workflow provides structured access to public content through defined APIs and MCP tools, offering a programmatic alternative to manual web browsing for data discovery and interaction.
Compared to similar skills
thinkinglabs side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| thinkinglabs (this skill) | 0 | 5mo | No flags | Beginner |
| qmd | 26 | 5mo | Review | Intermediate |
| biorxiv-database | 7 | 1y | Review | Beginner |
| read-arxiv-paper | 16 | 8mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
qmd
tobi
Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search markdown files", "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".
biorxiv-database
lifangda
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
read-arxiv-paper
karpathy
Use this skill when when asked to read an arxiv paper given an arxiv URL
twitter-reader
daymade
Fetch Twitter/X post content by URL using jina.ai API to bypass JavaScript restrictions. Use when Claude needs to retrieve tweet content including author, timestamp, post text, images, and thread replies. Supports individual posts or batch fetching from x.com or twitter.com URLs.
notion-research-documentation
openai
Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.
arxiv-to-md
solatis
Convert arXiv papers to LLM-consumable markdown. Invoke when user provides an arXiv ID or URL, or when syncing academic papers from a PDF folder to a markdown destination.