Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gulmezeren2-byte/erp-report-engine --skill explain-kpi-movegit clone --depth 1 https://github.com/gulmezeren2-byte/erp-report-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gulmezeren2-byte/erp-report-engine/explain-kpi-move)<a href="https://agentmods.dev/skills/gulmezeren2-byte/erp-report-engine/explain-kpi-move"><img src="https://agentmods.dev/badge/skills/gulmezeren2-byte/erp-report-engine/explain-kpi-move/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gulmezeren2-byte/erp-report-engine/explain-kpi-move"><img src="https://agentmods.dev/badge/skills/gulmezeren2-byte/erp-report-engine/explain-kpi-move.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00536 |
| Opus 5 | $0.00022 | $0.00268 |
| Sonnet 5 | $0.00009 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
explain-kpi-move scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Explain a KPI move
Use this when someone asks "why did revenue / on-time / cover change this week?"
The honest answer uses what erp-report-engine already derived — not a guess.
Steps
- Get the briefing. Call
weekly_report. It returns the KPIs (this week vs previous vs 8-week baseline), thefindings, thereconciliation, and the SQLaudit_trail. - Lead with the finding. The engine's
findingsalready name the driver (e.g. "Revenue +26.7% WoW — main driver: region 'Ege' (157% of the move)") and any SPC signal ("148,291 is ABOVE the control limits … a real shift beyond week-to-week noise"). Quote that; it is deterministic and audited. - Signal vs noise. If the finding says a move is within control limits, say so plainly — "this week's dip is inside normal week-to-week variation, not a real change." Don't manufacture a story for noise.
- Confirm the driver if asked. To go deeper, run one aggregate query
(see
erp-safe-query):SELECT region, SUM(net_total) …for this week vs last. Report the split; don't speculate beyond it. - Name the caveats. If
data_quality_issuesflags unscored on-time orders, duplicates, or a reconciliation mismatch, surface it — a KPI built on shaky inputs deserves the asterisk.
Guardrails
- No invented causes. "Revenue rose because of a marketing campaign" is not in the data. Attribute only to what the driver split and findings support (a region, a customer, a status).
- Correlation ≠ cause. The engine attributes where a move concentrated, not why it happened in the real world. Frame it as "the move concentrates in X — confirm whether that's demand or a one-off," exactly as the finding does.
- Percentages need a base. A "+400%" on a tiny customer is smaller than a "+5%" on the biggest one; report the absolute change alongside the percent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 40 lines · 44 tokens per session scan A 8ff093e3501d
explain-kpi-move is a skill published in the GitHub repository gulmezeren2-byte/erp-report-engine (1 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 536 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
performance-report
Generate affiliate performance reports with KPIs and recommendations. Triggers on: "show my affiliate report", "how are my programs doing", "performance review", "earnings report", "monthly affiliate report", "weekly report", "analyze my affiliate earnings", "which program is best", "EPC report", "conversion rate…
building-soc-metrics-and-kpi-tracking
Builds SOC performance metrics and KPI tracking dashboards measuring Mean Time to Detect (MTTD), Mean Time to Respond (MTTR), alert quality ratios, analyst productivity, and detection coverage using SIEM data. Use when SOC leadership needs operational visibility, continuous improvement tracking, or executive-level…
google-analytics
Skill "google-analytics" from VKirill/claude-lane-stack, covering version requirements (may 2026), usage, use this skill when, do not use this skill when and purpose.
sheets-automation
Google Sheets automation workflows - data sync, task management, reporting dashboards, and multi-platform integrations.
monitoring-weekly
Use when: kullanıcı "weekly check", "haftalık monitoring", "drift check GSC anomaly + budget burn", "weekly health report", "haftalık sağlık raporu", "haftalık monitoring özeti" der ya da /pseo-monitoring-weekly çağırır; week range filter events.jsonl + drift-check output reuse + GSC week-over-week delta + budget burn…
monthly-close
Repeatable month-end close checklist for small businesses — lock the period, process outstanding receipts, categorize remaining items, reconcile all accounts, review large transactions, check contractor 1099 thresholds, generate monthly P&L summary. Trigger on "close the month", "month-end close", "monthly…