yearly-kpi
Skill1 starsChanged 5 months agoMITView on GitHub
Build 3–5 yearly Product KPIs, each with measurable quarterly targets for the next 4 quarters.
In this repository7 other files it gives its agents.
- backlog-scrubSkill
- golden-testsSkill
- kpi-definitionSkill
- prd-writingSkill
- press-releaseSkill
- user-storiesSkill
- weekly-updateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 13
Use today's date (given in your instructions) to name the next 4 quarters.
- Distinctive: line 42
Every target is a number with a unit.
- Distinctive: line 44
Make sure each KPI is measurable now or includes a plan to instrument it.
- Very specific: line 46
When done, start_draft it as "<your name> Yearly Product KPIs" and log/attach a ledger item so it's tracked.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Yearly Product KPIs
Define the small set of Product KPIs you'll be held to this year, each with a clear title and a measurable goal for each of the next four quarters. Fewer, sharper KPIs beat a long vanity list.
Pick the quarters
Use today's date (given in your instructions) to name the next 4 quarters.
Calendar quarters: Q1 = Jan–Mar, Q2 = Apr–Jun, Q3 = Jul–Sep, Q4 = Oct–Dec. Start
from the quarter that contains today and list it plus the following three (label
them like Q3'26). If your org uses a fiscal year, ask your manager — otherwise use
calendar quarters.
Choose 3–5 KPIs
Tie them to your focus area and current projects (check your ledger with
list_items). For each KPI:
- Title — short and outcome-oriented (e.g. "Activation rate", "Weekly active teams", "p95 API latency", "Net revenue retention").
- Definition — precise: numerator / denominator / population / time window.
- Type — growth metric, quality/guardrail, or efficiency.
- Baseline — today's value (state "unknown — needs instrumentation" if you don't
have it, and log that as a
prove-stage item). - Quarterly targets — a measurable goal for each of the 4 quarters, showing a credible trajectory. State the key assumption behind the ramp.
Output
Produce a table, one row per KPI:
| KPI | Definition | Baseline | Q?'?? | Q?'?? | Q?'?? | Q?'?? |
| Activation rate | % of new signups completing setup in 7d | 38% | 42% | 47% | 52% | 55% |
Then a short paragraph per KPI: why it matters, the main lever you'll pull, and the biggest risk to hitting it.
Rules:
- Every target is a number with a unit. No "improve" / "increase" without a figure.
- Include at least one guardrail KPI that must not regress.
- Make sure each KPI is measurable now or includes a plan to instrument it.
When done, start_draft it as "<your name> Yearly Product KPIs" and log/attach a
ledger item so it's tracked. Tell your manager the headline targets and the one KPI
you're least confident about.
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
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.

