agentleFS
agiea-brainagiea-brain/agency-skills/skills/tony-dowling/activity-incentive-sprint/SKILL.md

activity-incentive-sprint

Skill1 starsChanged 17 days agoMITView on GitHub

Use this skill when a sales team's pattern needs interrupting for a few days: Call 1 bookings have dried up, presentations have stalled, a dormant list needs clearing, or the quarter needs a jolt. Produces an Executive Sprint Brief for a 1-day blitz, 3-day push or 2-week sprint, with targets worked from the team's real baseline, qualifying criteria, a scoreboard, a reward and three daily huddle prompts. Also use for "sales blitz", "sprint incentive", "spiff", "activity competition", "get the team booking meetings this week".

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do the workings. Baseline × reps × window gives the expected number.

    line 25
  2. Distinctive:

    Write three daily huddle prompts: a callout, a momentum nudge, a closing push.

    line 29
  3. Distinctive:

    Write it up as an Executive Sprint Brief using the section order in the reference, and create it as a shared document named for the sprint …

    line 30
  4. Distinctive:

    MUST ask for a baseline if none is given.

    line 42
  5. Distinctive:

    MUST use a leading indicator as the primary metric.

    line 43
  6. Distinctive:

    MUST show the target maths in the brief.

    line 44
  7. Distinctive:

    MUST define what counts precisely enough to settle an argument.

    line 45
  8. Distinctive:

    NEVER run longer than two weeks.

    line 46
  9. Distinctive:

    NEVER reward activity for its own sake: dials, emails sent, or tasks closed.

    line 47
  10. Distinctive:

    NEVER pay the reward through a delayed commission calculation.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Applies when a manager wants a short, tactical burst that drives one specific high-value behaviour, never dials for the sake of dials. Produces an Executive Sprint Brief the team can read in two minutes and run from Monday.

The play

  1. Gather inputs. Use what the manager has given and ask for the rest: the behaviour to drive, who is taking part, the window available, and the current baseline numbers (typical weekly Call 1s booked, presentations made, meetings held). A missing baseline is a blocker; targets are set off real numbers, not round ones.
  2. Pin the intent. Which behaviour: booking Call 1s (diagnostic briefs), making presentations (asking for cash), uncovering new C-suite decision makers, or clearing a dormant list. If unsaid, infer the most likely pain from what was shared and state the assumption at the top of the brief.
  3. Pick the format from the window: 1-day Blitz, 3-day Push, or 2-week Sprint at the longest. Shorter and tighter beats longer. Never past two weeks; energy does not survive it.
  4. Define the metrics from leading indicators only. Primary: Presentations Made or Call 1s Booked. Secondary: meaningful conversations held, or new decision-maker contacts identified. Revenue is not a sprint metric; it lags the window.
  5. Do the workings. Baseline × reps × window gives the expected number; set a stretch of roughly 40 to 60% over it, per rep and team total, and show the sum in one line. Worked example in references/sprint-brief-template.md.
  6. Design the incentive and mechanics. Rewards are fast, tangible and cultural: a team experience, peer recognition, spot prizes on the day, an early Friday finish. Nothing that pays out in a commission run weeks later. Daily rhythm: a 5-minute morning kick-off and an afternoon scoreboard check.
  7. Define qualifying criteria precisely so nothing can be gamed. A Call 1 counts only if booked and logged with a future date. A presentation counts only if a proposal or pricing was shared.
  8. Specify the scoreboard. Default: a simple shared tally in a team doc or channel. It can be wired to the CRM by mapping the metric to an activity or stage change, but do not assume it lives there.
  9. Write three daily huddle prompts: a callout, a momentum nudge, a closing push.
  10. Write it up as an Executive Sprint Brief using the section order in the reference, and create it as a shared document named for the sprint in the team's document store, ready to circulate.

What good looks like

  • First thing I check that most people skip: whether the primary metric is a leading indicator the rep controls this week. A revenue sprint rewards whoever had deals closing anyway.
  • Second tell: whether the qualifying criteria would survive a rep arguing their numbers on Friday afternoon. If "a conversation" is not defined, every voicemail becomes one.
  • The mediocre version: "most calls wins a bottle", a two-month window, a prize paid in the next commission run, and a leaderboard nobody updates after Tuesday.
  • I know the brief is right when a rep can read it in two minutes and say what counts, what the number is, and what they get, and the target makes them wince and then nod.
  • I know it worked when the behaviour persists in the week after the sprint at a level above the old baseline.

Rules

  • MUST ask for a baseline if none is given. No baseline, no target.
  • MUST use a leading indicator as the primary metric.
  • MUST show the target maths in the brief.
  • MUST define what counts precisely enough to settle an argument.
  • NEVER run longer than two weeks.
  • NEVER reward activity for its own sake: dials, emails sent, or tasks closed.
  • NEVER pay the reward through a delayed commission calculation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.