measure
Skill1 starsChanged 3 months agoMITView on GitHub
Produce the honest numbers — weekly scorecard, campaign performance, funnel conversion, spend efficiency — translated into three plain lines and next actions. Run weekly, and on demand for "is it working?
5 other projects use a version of this.
Adopted by
Most recently taken up by
- BSSE23047/nauraiz-devtheir own version, first seen Nov 8, 2026
- ZoolCoder/findabletheir own version, first seen Nov 1, 2026
- synaptiai/agent-capability-standardtheir own version, first seen Nov 1, 2026
- dososo/blcaptain-measure-cjktheir own version, first seen Nov 1, 2026
- vivekschaudhary/compasstheir own version, first seen Oct 25, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- dososo/blcaptain-measure-cjk★ 18same name
- synaptiai/agent-capability-standard★ 7same name
- BSSE23047/nauraiz-dev★ 2same name
- vivekschaudhary/compass★ 2same name
- ZoolCoder/findable★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- build-funnelSkill
- close-dealSkill
- connect-toolsSkill
- create-contentSkill
- define-positioningSkill
- design-offerSkill
- experimentSkill
- grow-referralsSkill
- grow-seoSkill
- health-checkSkill
- launch-campaignSkill
- launch-productSkill
- manage-pipelineSkill
- plan-strategySkill
- research-marketSkill
- review-monthlySkill
- run-adsSkill
- run-outboundSkill
- run-partnershipsSkill
- setup-teamSkill
- tune-revopsSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
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
- Very specific: line 34
No strategy exists yet → don't fake a scorecard.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/measure — Honest Numbers, Plain Words
Inputs: knowledge/strategy.md (targets), active briefs in knowledge/campaigns/, knowledge/pipeline.md, connected tool dashboards via knowledge/tool-registry.md, knowledge/results-history.md.
Agents: growth-analyst leads; tools-operator pulls data.
Method: knowledge/methods/funnel-and-measurement.md.
Steps
- Pull the week. From each connected source: funnel-stage numbers (visits/reach → clicks/opens → leads/conversations → sales), spend, per-campaign performance. Note retrieval dates; missing data is reported missing, never interpolated.
- Fill the scorecard.
templates/weekly-scorecard.md— this week, last week, target. Absolute counts beside rates (small-sample honesty). - Judge against the plan. Each active campaign vs its brief's success metric and kill threshold. Anything past its threshold gets flagged with the pre-committed action — kill, adjust, or extend with reason.
- Attribute what's knowable. UTM data, marketplace stats, and the "how did you hear about us?" answers. State confidence; "can't tell yet" is a valid finding.
- Reconcile the money. Update
knowledge/budget.md: approved vs actually spent per channel this week, and return where attributable (revenue, or pipeline value at honest stage-weighted odds). Flag any channel spending ahead of its approval or pacing past its monthly cap. Cost-per-sale per channel is the number the operator most needs and least often sees. - Track the keep-rate. Where the model supports it: repeat purchase rate (B2C), churn/renewal and expansion (B2B recurring), refund rate. A leaky bucket makes every acquisition number a lie.
- Write the three lines. What worked / what didn't / what changes next week — in words the operator needs no glossary for.
- Bank the learnings. Each finding that changes how we operate becomes one dated line in the relevant method file's "What we've learned here" section (cite the scorecard week). No essays — one line, one source.
- Queue next week. Approval batch needed (spend, outbound, publishing), experiments ready to call (route to
/experiment), and recommended actions ranked by expected impact.
Before you start
- Required inputs:
knowledge/strategy.mdapproved (targets to judge against);knowledge/results-history.mdandknowledge/budget.mdas they exist. This skill runs on the weekly schedule — verify the scheduled task fired it or run manually. - Scan
knowledge/decision-log.mdfor tagsbudget,channel— pre-committed kill thresholds are decisions, not suggestions. - Gate check: none to execute — but this skill queues next week's approval batch.
If things go wrong
- A data source is unreachable this week → report the number as missing (never interpolate), note the source and retry path; if it recurs, route to
/connect-tools. - Numbers contradict each other across sources → report both with the discrepancy flagged; pick the more conservative for decisions.
- No strategy exists yet → don't fake a scorecard; report activity honestly and recommend
/plan-strategy.
Outputs
The weekly scorecard appended to knowledge/results-history.md; updated knowledge/budget.md; the three-line summary; a ranked action list. Close with the report per templates/skill-report.md.
Writeback
knowledge/results-history.md; knowledge/budget.md; kill/adjust decisions (tags: budget, channel) to knowledge/decision-log.md; campaign briefs' results sections; learning lines to the relevant knowledge/methods/*.md.
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.

