Clawhard Studio

Shrinks a prompt, chat, log, stack trace, JSON dump or code paste so it uses fewer tokens: removes base64 and data blobs, minifies JSON, shortens stack traces, squashes repeated log lines, strips code comments and link tracking parameters, and collapses whitespace. Optionally drops pleasantries and markdown. Returns the trimmed text and how much was saved. Token numbers here are rough estimates (about 4 characters per token); the website shows exact counts.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to trim (up to 200,000 characters)."
    },
    "rules": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "blobs",
          "json",
          "traces",
          "repeats",
          "comments",
          "urls",
          "space",
          "polite",
          "markdown"
        ]
      },
      "description": "Rules to apply. Default: blobs, json, traces, repeats, comments, urls, space. Also available: polite, markdown."
    }
  },
  "required": [
    "text"
  ]
}

Fetches a public web page and its main stylesheets and scripts once, then scores it from 0 (hand-made feel) to 100 (certified slop) against 19 design and copy habits that make a site look AI-made (purple gradients, gradient headlines, glow blobs, glassmorphism, default fonts, untouched component kits, icon card grids, buzzwords, template headlines, vague social proof, placeholder testimonials, app-builder leftovers, em dashes and more). Returns each tell found with how to fix it.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public website address, for example example.com or https://example.com/pricing"
    }
  },
  "required": [
    "url"
  ]
}

Lists the AI subscription plans AI Tab knows (chat assistants, coding tools, image and video, voice and music, work) with their USD list prices and the plan keys to pass to the total tool.

{
  "type": "object",
  "properties": {}
}

Adds up a list of AI subscriptions and returns the monthly, yearly and daily total, where the user is paying twice for the same thing (overlaps), what could be cut and how much that saves, plus a link that opens the shareable receipt. Use plan keys from the plans tool, for example chatgpt.plus, claude.pro, cursor.pro. Append ":y" to a key for yearly billing.

{
  "type": "object",
  "properties": {
    "plans": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Plan keys, e.g. [\"chatgpt.plus\",\"claude.pro\",\"cursor.pro\"]. In a GET query use a comma-separated list."
    },
    "billing": {
      "type": "string",
      "enum": [
        "monthly",
        "yearly"
      ],
      "description": "Which total the shared receipt shows first. Default monthly."
    }
  },
  "required": [
    "plans"
  ]
}

Checks a piece of writing for the habits that make people think a chatbot wrote it (em dashes, words like "delve", assistant filler like "I hope this helps", "it's not X, it's Y", fake suspense, stiff transitions, markdown leftovers, emoji bullets, rule of three, same-length sentences). Returns a 0-100 bot-o-meter score, a verdict and the tells found. Style habits only. Not an AI detector and not proof of who wrote the text.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The writing to check (up to 60,000 characters)."
    }
  },
  "required": [
    "text"
  ]
}

Rewrites the easy tells: swaps em dashes for commas, chatbot words for plain ones, strips assistant filler, markdown stars and emoji bullets, fixes stiff transitions. Habits that need a human rewrite ("it's not X, it's Y", fake suspense, rule of three) are listed but left alone. Returns the fixed text, the before and after score and what remains.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The writing to clean up (up to 60,000 characters)."
    },
    "categories": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "dash",
          "buzz",
          "filler",
          "frame",
          "reveal",
          "trans",
          "md",
          "emoji",
          "three",
          "rhythm"
        ]
      },
      "description": "Optional: only fix these categories. Default: every auto-fixable category."
    }
  },
  "required": [
    "text"
  ]
}

Lists the starter run sheets (wedding, conference, photo shoot, blank) with their default times, so you can pick one or adapt it before creating a run sheet.

{
  "type": "object",
  "properties": {}
}

Creates a Runsheet: a live, shareable schedule for an event day (wedding, shoot, conference, any timed run of show). Start from a template or send your own items. Returns a view-only link for guests and vendors and a private edit link for the planner. Keep the edit link secret: anyone with it can change the schedule.

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Event name."
    },
    "date": {
      "type": "string",
      "description": "YYYY-MM-DD"
    },
    "timezone": {
      "type": "string",
      "description": "IANA time zone, e.g. America/New_York. Default UTC."
    },
    "template": {
      "type": "string",
      "enum": [
        "wedding",
        "conf",
        "shoot",
        "blank"
      ],
      "description": "Starter schedule. Ignored if items are given."
    },
    "items": {
      "type": "array",
      "maxItems": 200,
      "description": "Schedule slots.",
      "items": {
        "type": "object",
        "properties": {
          "time": {
            "type": "string",
            "description": "Start, 24-hour HH:MM"
          },
          "duration_minutes": {
            "type": "integer"
          },
          "title": {
            "type": "string"
          },
          "where": {
            "type": "string"
          },
          "who": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Vendors or roles on this slot"
          }
        },
        "required": [
          "time",
          "title"
        ]
      }
    }
  }
}

Given a group of people and the expenses (who paid, how much, who shared it), returns each person's net balance and the smallest set of payments that squares everyone up. Splits equally by default, or by exact amounts. Stateless: nothing is saved. Use create_group instead to make a shared link people can keep adding to.

{
  "type": "object",
  "properties": {
    "currency": {
      "type": "string",
      "description": "ISO currency code, default USD."
    },
    "people": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Names of everyone in the group (2 to 40, unique)."
    },
    "expenses": {
      "type": "array",
      "description": "What was paid.",
      "items": {
        "type": "object",
        "properties": {
          "what": {
            "type": "string"
          },
          "amount": {
            "type": "number",
            "description": "Total in normal units, e.g. 45.50"
          },
          "paid_by": {
            "type": "string"
          },
          "split_between": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Who shared it. Default: everyone, equally."
          },
          "exact": {
            "type": "object",
            "additionalProperties": {
              "type": "number"
            },
            "description": "Optional exact amount per person (must add up to amount). Overrides split_between."
          }
        },
        "required": [
          "amount",
          "paid_by"
        ]
      }
    },
    "payments": {
      "type": "array",
      "description": "Payments already made between people to settle up.",
      "items": {
        "type": "object",
        "properties": {
          "from": {
            "type": "string"
          },
          "to": {
            "type": "string"
          },
          "amount": {
            "type": "number"
          }
        },
        "required": [
          "from",
          "to",
          "amount"
        ]
      }
    }
  },
  "required": [
    "people",
    "expenses"
  ]
}

Creates a Halves group and returns a link anyone can open (no sign-up) to add and fix expenses and see who owes whom. Optionally pre-loads expenses. Anyone who has the link can edit the group, so share it only with the people in it. Groups are kept for about 400 days after the last change.

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Group name, e.g. \"Lisbon trip\"."
    },
    "currency": {
      "type": "string",
      "description": "Main currency, default USD."
    },
    "people": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Names (2 to 40)."
    },
    "expenses": {
      "type": "array",
      "description": "Optional starting expenses (up to 50), same shape as the settle tool.",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "people"
  ]
}

Lists the design vocabulary Lingo knows: 36 named looks in six groups (layout, type, color, shape, motion, style), each with a plain-English meaning and the exact wording and values to give an AI coding agent, plus the vague phrases Lingo can decode (like "make it pop").

{
  "type": "object",
  "properties": {}
}

Turns a vague design request ("make it pop", "it looks cheap", "too busy", "less AI-looking") into what designers usually mean by it and the specific design terms and values to use instead. Returns a ready-to-paste design brief and a link that opens it in Lingo.

{
  "type": "object",
  "properties": {
    "phrase": {
      "type": "string",
      "description": "The vague request in plain words, e.g. \"it feels cheap and too busy\"."
    },
    "avoid_ai_look": {
      "type": "boolean",
      "description": "Add rules that steer away from the generic AI-made look. Default true."
    }
  },
  "required": [
    "phrase"
  ]
}

Builds a precise design brief (markdown) from Lingo term ids and/or vague phrases, ready to paste into an AI coding agent or a project rules file. Conflicting picks (for example sharp and soft corners) keep the last one. Includes optional "don't look AI-made" rules and a link that opens the brief in Lingo.

{
  "type": "object",
  "properties": {
    "terms": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Term ids from the terms tool, e.g. [\"airy\",\"display\",\"accent\",\"soft\"]. In a GET query use a comma-separated list."
    },
    "say": {
      "type": "string",
      "description": "Optional vague request to decode and include, e.g. \"more premium\"."
    },
    "avoid_ai_look": {
      "type": "boolean",
      "description": "Add rules that steer away from the generic AI-made look. Default true."
    }
  }
}

Checks a memo, email, post, report or AI-written draft for fluff: pleasantries and throat-clearing, stock openers ("in today's fast-paced world"), padding ("it's important to note that"), buzzwords (leverage, synergy, robust), hedges, vague claims and sentences that repeat an earlier one. Returns a 0-100 fluff percentage, a verdict, every flagged sentence with the reason, the most used filler phrases, and the gist (only the lines that say something, with padding phrases trimmed). Rule-based wording check, not a fact check; it never invents text.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to check (up to 60,000 characters)."
    }
  },
  "required": [
    "text"
  ]
}

Returns the gist of a text: drops sentences that are pure filler, buzzwords, pleasantries or repeats, and trims padding phrases ("in order to" becomes "to", "it's important to note that" is removed) from the rest. Keeps the author's own words and order, invents nothing. Also returns the fluff percentage and how many words were cut.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to cut down (up to 60,000 characters)."
    }
  },
  "required": [
    "text"
  ]
}