Not is this broken. Where specifically is this leaking.
The tool that maps a working process as it actually runs, times each step, and finds the specific handoff or rework loop quietly costing the most time, money, or quality.
A process that's obviously broken gets fixed quickly. A process that mostly works is more dangerous, because the inefficiency is diffuse enough that everyone's quietly adapted to the friction as normal.
This tool maps the process as it's actually run, including the workarounds nobody's written down, times each step, and traces any rework loop to its actual root cause instead of just flagging the symptom.
The leak, found and quantified.
Same process, same complaint, run two ways.
A 25-person agency's monthly client reporting process is taking noticeably longer each month even though the underlying work hasn't obviously grown.
You ask Claude how to make the process more efficient. You get sensible general suggestions: automate the data pulls, use a template, reduce back-and-forth.
All reasonable, and none of it tells you the back-and-forth is actually costing as much time as the entire deck build, or why it's happening in the first place.
It maps the process as it actually runs and times each step:
- →Four handoffs found for a single monthly deliverable, most with uncounted wait time
- →The discrepancy back-and-forth traced to a labeling problem in the spreadsheet, not a data-quality issue
- →Roughly 25-35 hours a month quantified as the single largest addressable leak
The recommendation fixes the actual root cause, standardizing the spreadsheet's labeling, rather than adding another review step to catch a problem that a labeling fix would prevent from happening at all.
The cold version suggested automating things. This found the specific leak and traced it to its actual cause.
- ✦Operators with a process that works but feels inefficient in a way nobody's pinned down
- ✦Teams whose processes have grown by accretion as they scaled
- ✦Anyone about to propose a fix without having actually diagnosed the leak first
- →process-audit.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →process-audit-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, Gemini, and the API
What it does with a real question.
Our customer onboarding takes about 19 days from signed contract to first use. It involves sales handoff, a kickoff call, account setup by support, data import by a technical lead and a training session. Customers complain about delays, and my team feels overworked. I want to find where the time and quality actually leak.
Where I'd bet the leak is. Nineteen days across five stages almost certainly means most of the clock is waiting, not working. Your team feels overworked and customers feel delayed because both are true at once: people are busy, yet the contract sits idle between them. Four handoffs sit inside this process (sales to kickoff, kickoff to support setup, setup to the technical lead, import to training), and each one is a place where work waits for someone to notice it, have capacity, or get missing information.
My position: the data import is the likely biggest leak, and it is probably fed by an upstream gap. A single technical lead is a natural queue. If customers' data arrives incomplete or in the wrong format, the import stalls and gets sent back, and that rework lands on your most expensive person. I'd trace that back to what sales captures and what the kickoff call collects, not treat the import itself as the problem. Training likely can't be scheduled until import finishes, so the delay compounds.
Don't redesign anything yet. Next move: pull timestamps for your last ten onboardings at each stage transition and split every st
The full Tool runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Tool loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude suggests generic efficiency improvements, automate this, template that, without measuring anything specific. This maps the process as it actually runs, times each step, finds the handoffs and rework loops, and traces the biggest one to its actual root cause with a rough number attached.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Tool itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.
Process Audit is a diagnostic tool. It identifies where a process is leaking; implementing a fix, especially one involving new tools or automation, should be scoped and tested separately.