TH
thinkinglabs
Use when reading, querying, or integrating with the public thinkinglabs corpus through Markdown, JSON, feeds, or MCP.
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.117 chars✓ has a “when” trigger
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, detail routes, JSON APIs, feeds, and MCP endpoints from
/llms.txt. - Read clean page-shaped Markdown by appending
.mdto canonical public URLs. - Query public collections through
/api/<kind>.jsonor thequery_viewMCP tool. - Traverse public resources through the remote MCP endpoint at
https://mcp.thinkinglabs.run/mcp. - Precheck contact intent with
contact.precheckbefore preparing a human email handoff. - Submit structured answers to public questions with the
question.submitMCP tool.
Required Inputs
- A target task, topic, tag, object slug, or public view name.
- For MCP use, a client that supports Streamable HTTP MCP.
- 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: MCP resources, tools, JSON APIs, feeds, and connection examples./agent-permissions.json: Automated-access policy and preferred entrypoints.AGENTS.md: Repository operating instructions.docs/agents/mcp-http-server.md: Remote MCP transport contract.