skills/flowhunt-skill/SKILL.md
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 wha
npx skillsauth add ranbot-ai/awesome-skills flowhunt-skillInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
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:
tools
Use when a user asks to mine or update a private, evidence-backed work profile from local Claude Code, Codex, Copilot CLI, or OpenCode sessions.
data-ai
Use when diagnosing Android overheating, idle heat, thermal throttling, charging or radio heat, or abnormal battery drain with read-only ADB evidence and approval gates.
research
Research public competitor ads, analyze creative patterns and landing pages, and produce an evidence-labeled strategic teardown.
tools
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.