Categories › AI & Agents › Thinking, planning & prompt tools
669 work prompts, prompt and answer checks, a job planner, a prompt linter and AI prices.
Remote server: your requests and data go to thinkhard.si. Claude Code: claude mcp add --transport http thinkhard-si-prompt-tools https://thinkhard.si/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_prompts — Search the thinkhard.si repository of 1,024 tested prompt templates for work tasks: email, meetings, presentations, job search, marketing, sget_prompt — Get the full text of one prompt from the thinkhard.si repository by its slug, registry number (such as CAR-001) or exact title, with its {{blist_collections — List the collections in the thinkhard.si prompt repository, with how many prompts each has.grade_prompt — Score a prompt out of 10 on the ten checks thinkhard.si uses (what to make, who it is for, background facts, length, format, what to avoid, estimate_ai_cost — Estimate the monthly cost of running a prompt on current AI models (Claude, GPT, Gemini, DeepSeek, Qwen and others), from thinkhard.si's prifix_bad_answer — When an AI answer goes wrong (it made up a source or a number, ignored an instruction, came back too long or in the wrong shape, sounded robget_prompt_pattern — The 24 prompt patterns from thinkhard.si: small moves that change the answer, such as giving the facts, naming the reader, showing one exampdefine_ai_term — Plain-English definitions of 102 AI words from the thinkhard.si glossary (token, context window, hallucination, temperature, system prompt, check_answer — Did the AI do what the prompt asked? Give the prompt and the answer it got. Finds every rule in the prompt that can be checked by reading (lbuild_assistant — Write the instructions for an assistant that keeps its rules: a ChatGPT custom GPT, a Claude Project, a Gemini Gem, a Microsoft Copilot agenplan_workflow — Turn a job such as hiring for a role, launching a feature, closing the month or applying for a job into steps in the order the work happens,lint_prompts — Find the prompts in source files (Python, JavaScript, TypeScript, YAML, JSON and prompt files) and review each for what breaks AI features iaudit_library — Read many prompts at once, such as a team's shared prompt doc: each prompt's score on the ten checks, the task it does and how ready it is fcheck_agent_brief — Before a task goes to a coding agent (Claude Code, Codex, Cursor, GitHub Copilot or another), check the brief: what kind of task it is, whicNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.