scorecard
Skill4 starsChanged 7 days agoMITView on GitHub
Generate the weekly or monthly business performance scorecard — fixed KPI set with comparisons, status colours, and narrative explanations for every off-track metric. Usage - /scorecard weekly or /scorecard monthly.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- anthony-chaudhary/faktheir own version, first seen Nov 3, 2026
- mangollc/claude-SDR-Manager-plugintheir own version, first seen Nov 1, 2026
- lgtm-hq/ai-skillstheir own version, first seen Oct 13, 2026
- sparkline-ventures/product-evaltheir own version, first seen Jun 29, 2026
- tansuasici/claude-research-kittheir own version, first seen Jun 2, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- anthony-chaudhary/fak★ 49same name
- sparkline-ventures/product-eval★ 15same name
- tansuasici/claude-research-kit★ 4same name
- lgtm-hq/ai-skills★ 1same name
- mangollc/claude-SDR-Manager-plugin★ 1same 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 repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- build-dashboardSkill
- build-modelSkill
- build-pipelineSkill
- causal-analysisSkill
- connect-dataSkill
- define-kpisSkill
- evalSkill
- experimentSkill
- forecastSkill
- health-checkSkill
- investigate-metricSkill
- make-deliverableSkill
- powerbiSkill
- privacy-reviewSkill
- research-domainSkill
- setup-teamSkill
- tableauSkill
- triageSkill
- upgradeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Check data freshness first: Verify every source table is loaded through the period end.
- Distinctive: line 35
Monthly only: add a narrative section (what happened this month and why, ~half page) and a "watch next month" list.
- Very specific: line 37
Check before it leaves: Run python scripts/scan_outputs.py scorecards/ — a segment breakdown is where a cell under the minimum group size …
- Very specific: line 41
Maintain: If any metric was 🔴 two consecutive periods, recommend a full /investigate-metric.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Scorecard — Periodic Performance Report
Owner: performance-monitor, with insights-communicator for the monthly narrative. Argument: weekly (default) or monthly.
Procedure
- Determine the period. Weekly = most recent complete week ({{WEEK_DEFINITION e.g. Mon–Sun}}); monthly = most recent complete calendar/fiscal month per
knowledge/business-context.md. Never report a partial period without labelling it as such. - Load the KPI set from the scorecard section of
knowledge/metrics-catalog.md. The set is fixed between periods; if it's empty, run/define-kpisfirst. Checkscorecards/for prior editions — formats and metric set must stay comparable. - Check data freshness first. Verify every source table is loaded through the period end. A scorecard on stale data is worse than a late scorecard — if data is missing, say so per-metric rather than silently under-reporting.
- Compute each metric using catalog formulas (or the pre-built marts) — take the SQL from
python scripts/run_metric.py "<name>", never from last period's scorecard or from memory: current value, vs prior period (Δ and %), vs same period last year where history allows, vs target where set, and status:- 🟢 on track (within {{GREEN_THRESHOLD e.g. ±5% of target/trend}})
- 🟡 watch ({{YELLOW_THRESHOLD}})
- 🔴 off track ({{RED_THRESHOLD}}) Thresholds per metric live in the catalog; flag any metric without thresholds.
- Explain, don't just colour. For every 🔴 and 🟡, run a quick localisation (which segment/channel drives it) and attach a one-line cause or "under investigation — see /investigate-metric". Also call out notable 🟢 overperformance — wins matter too.
- Anomaly sweep. Beyond the fixed set, scan for trend breaks, paired-metric divergence, and segment-level moves hidden by stable toplines. Add an "Also noticed" section if anything qualifies.
- Write the scorecard to
scorecards/YYYY/weekly-YYYY-WW.mdormonthly-YYYY-MM.md:- Headline (2–3 sentences: overall state + the one thing to pay attention to)
- KPI table (metric, value, vs prior, vs LY, vs target, status, note)
- Off-track detail (one short paragraph each)
- Also noticed
- Data caveats (freshness gaps, definition changes this period)
- The provenance footer (
standards/reporting-standards.md): source tier, data-through date, owner, review status - Monthly only: add a narrative section (what happened this month and why, ~half page) and a "watch next month" list.
- Check before it leaves. Run
python scripts/scan_outputs.py scorecards/— a segment breakdown is where a cell under the minimum group size appears. The monthly scorecard, and any scorecard going to executives, is reviewed byanalysis-reviewerfirst; record the verdict in the footer. - Distribute per the standing cadence in
CLAUDE.md§6. Producing the file is autonomous; sending it anywhere external requires the user's standing authorisation. - Maintain. If any metric was 🔴 two consecutive periods, recommend a full
/investigate-metric. Log definition or threshold changes inknowledge/decision-log.md.
Created by Colin Beck — https://www.linkedin.com/in/beckcolin/
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.

