- Home
- Skills
- Productivity
- Workflow Inventory Pro
Works with the AI Agents you already use
Workflow Inventory Pro
**Workflow Inventory Pro** turns the map of what your AI agents actually do for you into a product line — safely.
$19
Workflow Inventory Pro
Example session with this skill installed
My bookkeeping agent sent its inventory, but it skipped the evidence classes, and one routine 'saves you 5 hours a week, probably.' Another 'runs every night' — it was built in June. A third we only discussed in April.
- Read your context and instructions
- Compiled the workflow inventory pro
Caveat check: present in spirit, non-compliant (no date; completeness half missing) — noted. Non-compliance loop: invented result struck → 'unknown' (results cannot be repaired, only struck); classes derived and marked (derived) with basis — invoice chasing: Reported (runs asserted, none exhibited); the nightly filer: Implemented, description locked to 'built, not yet run' — it may not be called an operating routine; birthday cards: Proposal, matching the definition word for word. Count: 3 routines, 0 Confirmed — so nothing here is a product candidate yet, and the report says exactly that, with the send-back prompt offered for a compliant re-issue.
Connects securely to your tools. The creator never sees your data.
About this skill
Workflow Inventory Pro turns the map of what your AI agents actually do for you into a product line — safely. It starts where the free version ends: a merged, evidence-classed inventory of your routines.
The core (from the free version)
- The inventory prompt — verbatim, with the records-relative caveat and no-credentials rules built in
- Evidence classes — Confirmed / Reported / Implemented / Proposal, applied to every routine and never upgraded by copying
- Non-compliance handling — agents skip fields and invent results; the system sends back a correction prompt, or repairs locally (classes derivable, invented results struck to "unknown")
What Pro adds
- Triage matrix — Repetition, Boundedness, Independence, Demand, Build cost — scored for Confirmed routines only; the rest go to a "prove it first" list
- The privacy scrub — names out, numbers out or generalized, niche rewritten to method, rule-bending steps cut or made compliant, and a final "read it as a stranger" pass
- Build-list sequencing — widest-and-most-wanted first, one product per build session
- Cross-agent production pattern — one agent inventories where the work happens; you courier the document; a second agent triages, scrubs and builds. (The pattern that produced a ten-product line in a day — stated as process, not promise.)
An inventory can only cover records the agent can reach — the caveat is structural, not a flaw to polish away. Demand scoring requires outside evidence the system asks for honestly (Unknown is an allowed score input). The scrub reduces identification risk; a determined reader who knows your public work may still guess — the system says so rather than promising anonymity.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 8 days ago
Requires
Permissions
No special permissions declared or detected