Standard operating procedure writer from a rough process description
Turns a rambling explanation, voice-note transcript or screen-share notes of how a task is done into a clear SOP with purpose, roles, prerequisites, numbered steps, decision points, checks and a list of questions for the process owner.
Prompt in Operations by AISkillHub Library
What it does
Processes usually live in one person's head until they go on holiday. This prompt takes however that person explained the process (a transcript of them talking through it, rough bullet notes, a long Slack message) and turns it into a standard operating procedure someone new could follow.
**Use it when** you are documenting recurring operational work such as month-end tasks, onboarding a new client, processing returns, publishing content, or running payroll inputs, and you want a consistent format across procedures.
**What you get** - Purpose and scope: what the procedure covers and does not cover. - Roles: who does what, and who approves. - Trigger and frequency: when the procedure starts and how often. - Prerequisites: access, tools and inputs needed before starting. - Numbered steps, one action each, with the expected result so the person knows a step worked. - Decision points written as "If ... then ..." branches. - Quality checks and common mistakes taken from what the expert mentioned. - What to do when something goes wrong, and who to contact. - A list of gaps and questions for the process owner, since spoken explanations always skip steps the expert finds obvious.
**What it will not do** - It will not invent steps, system names, thresholds or approvers. Gaps are marked `[confirm: ...]` and collected in the questions list. - It will not include passwords, API keys or other secrets even if they appear in the source; it replaces them with `[stored in: password manager entry name]` and flags them. - It does not make regulatory or safety judgements. For regulated processes, have the SOP reviewed by the accountable owner.
How to use it
## How to use
1. Open `prompts/sop-writer.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{process_description}}`: the raw explanation: transcript, notes or message. - `{{process_name}}`: a short name, e.g. `Monthly supplier invoice reconciliation`. - `{{audience}}`: who will follow it, e.g. `new finance assistant in their first month`. - `{{tools}}`: systems used in the process, with the names your team uses. Optional.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
Files
Save each file at the path shown, relative to your project root.