Use when the user asks how hiring is going, wants funnel numbers per role, or needs a hiring report for the team.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Run this when the user asks how hiring is going, wants funnel numbers, or needs a hiring report for the team. This is also the pass behind an on-demand weekly pipeline review.
The tracker — roles, candidates, loops — the shortlist, and the outreach log. Name the window up front and compare it against the prior window, never against vibes.
Counts per role and stage: sourced, screened, in loop, offer, closed. Add conversion between stages and flag the stage losing the most candidates, with the top two reasons in plain words.
Time to fill, from req posted to offer accepted, and time to hire, from applied or sourced to accepted. Plus time to slate, days in stage per candidate, and reqs aging past the stalled bar. Name the oldest five stuck items with owner and days.
Source mix — sourced, inbound, referral — plus source of hire: the channel that produced each signed hire. Offer acceptance rate. Decline reasons grouped. Quality of hire as 90-day attrition with exit-survey notes where you have them. Under 30 candidates in the window, say the sample is small and read it as directional, not truth.
Rows missing stage or owner, scorecards overdue, loops with no next step, outreach past three touches with no reply. Every item gets the one action that fixes it.
What changed, by how much, and the driver. Label each line FACT — from the tracker — INFERENCE, with your math and assumptions shown, or UNKNOWN for missing data, never estimated silently.
List, a line apiece, the calls that need the user or a hiring manager, plus next week's interview load by day with any day too heavy for the panel.
The funnel read in chat, under 300 words unless they asked for the full table, saved with the date to the hiring folder.
With a thin or stale tracker, report what is there, name the gaps, and ask for the one export that fills them. Never invent a stage change, a number, or a commitment.
Post it to a channel or mail it to the team only when they ask for that specific send. Reports carry role-level numbers; candidate details stay out of anything shared.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when a support account wobbles or a quarterly business review looms: read the health signals, run the success plan, and prep the review from evidence.
The English summary is being prepared. Showing the original description.
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.
The English summary is being prepared. Showing the original description.
Review open receivables and draft factual, staged payment follow-ups without inventing status or contacting a customer.
The English summary is being prepared. Showing the original description.
Write ad variants that each test one idea, within platform limits and supported claims.
The English summary is being prepared. Showing the original description.
Use on the first conversation with Alex, or whenever their memory has no product preferences yet: learn what the user is building and who for, where specs, roadmap and numbers live, who decides dates and scope, and get them to a first real product deliverable.
The English summary is being prepared. Showing the original description.
Use when a strategic alliance needs joint selling governance: operating model, joint targeting, steering prep, and milestone accountability.
The English summary is being prepared. Showing the original description.