Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Automation discovery audit skill. Walks through a 5-question workflow intake, then audits Gmail/Calendar/Slack/task trackers to identify automation opportunities. Use when a user wants to discover what processes in their business can be automated.
.claude/skills/flowhunt-skill/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-20 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-02 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
FlowHunt is an automation discovery audit skill. It guides agents through a structured 5-question intake to understand the user's business context, then systematically audits connected tools (Gmail, Google Calendar, Slack, task trackers, and more) to surface concrete automation opportunities ranked by impact and effort.
The skill is cross-agent: it works with Claude Code, Codex CLI, Gemini CLI, OpenCode, and any agent that accepts markdown skill files.
Install: npx skills add heyneuron/flowhunt-skill
Ask the user exactly these five questions, one at a time:
Wait for answers before moving to the audit.
For each tool the user mentioned, surface automation patterns:
Gmail
Google Calendar
Slack
Task trackers (Asana, Jira, Notion, Linear)
CRMs (HubSpot, Salesforce, Pipedrive)
Rank each identified opportunity on a 2x2:
| | Low effort | High effort | |---|---|---| | High impact | Do first (quick wins) | Plan carefully | | Low impact | Nice to have | Skip for now |
Present the top 3 quick-win automations with:
Deliver a structured Automation Opportunity Report in markdown:
# Automation Opportunity Report
## Business Context
[Summary from intake]
## Top 3 Quick Wins
1. [Name] — [What it does] — [Tools] — [~X hrs/week saved]
2. ...
3. ...
## Full Opportunity List
[All identified automations, ranked]
## Recommended Next Step
[Single clearest action the user can take today]| Excuse | Why it's wrong | |--------|----------------| | "I'll skip the intake and guess their stack" | Intake prevents wasted recommendations on tools they don't use | | "I'll list every possible automation" | Overwhelming output kills adoption — prioritize ruthlessly | | "I'll recommend complex custom code first" | Start with no-code/low-code quick wins; earn the right to build |
The skill is complete when the user has:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.