usage-report-v0
ARCHIVED - LLM-driven usage report generation (pre-deterministic refactor). Kept as a reference for comparing prose, structure, and content philosophy against the current /usage-report skill. NOT MEANT TO BE INVOKED.
npx skills add agentic-community/mcp-gateway-registry --skill usage-report-v0 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
It documents a comparison-mode workflow for generating a v0-style usage report side-by-side with the current deterministic report. It guides running the main /usage-report first, then invoking this archived skill to write a v0-style report from pre-populated data, generating a dated markdown output intended for side-by-side prose and structure comparison.
How it works
The skill’s instructions outline a two-step process: run /usage-report for a given date to create the deterministic report and populate .scratchpad/usage-reports/<DATE>/ with data files and charts; then invoke this archived skill in comparison mode to skip data exports and start at the step where the LLM writes the report from the existing files (Step 7). The output is saved as ai-registry-usage-report-<DATE>-v0.md in the same dated folder, alongside the deterministic ai-registry-usage-report-<DATE>.md. It references analysis scripts and chart generators located under .claude/skills/usage-report/, and notes this is LLM-driven in the past.
When to use it
Use this in a comparison context after a /usage-report run has populated the workspace, to produce a v0-style report for side-by-side evaluation against the current deterministic output.
What it can touch
- The workflow assumes presence of the following paths and files: .scratchpad/usage-reports/<DATE>/ (bastion export, analyzer JSON/CSV files, PNG charts), and the scripts under .claude/skills/usage-report/ (analyze_telemetry.py, analyze_liveness.py, chart generators).
- It expects to produce a file named ai-registry-usage-report-<DATE>-v0.md in the same dated folder as the deterministic report ai-registry-usage-report-<DATE>.md.
Caveats
- ARCHIVED, DOC-ONLY REFERENCE. Do not invoke this skill for production reports. Use
/usage-reportinstead. - The skill is intended for comparison, not for generating production reports. It describes a workflow that relies on pre-existing data exports and LLM-written narrative content rather than performing fresh data processing end-to-end.
> **ARCHIVED, DOC-ONLY REFERENCE.** Do not invoke this skill for production reports. Use `/usage-report` instead. > > **Comparison-mode usage:** This skill can be run AFTER `/usage-report` has already populated `.scratchpad/usage-reports/<DATE>/` with the bastion export, analyzer JSON/CSV files, and PNG charts. In comparison mode you skip Steps 1-6 (the bastion export and analyzer runs) and jump straight to Step 7 (LLM writes the report by reading the existing files). The output is a v0-style LLM-written report alongside the new deterministic + commentary report, useful for side-by-side prose voice / structure comparison. > > This SKILL.md captures the report-generation approach that was on `main` at commit `f1c0c14a` (2026-06-07), before the deterministic-render refactor. At that point the LLM did the report writing: it ran the analyzer scripts, then wrote the entire markdown by reading their outputs and synthesizing prose. The hallucination bug class we hit (Azure 28 vs 47, etc.) was the motivation to move to the template + augment-with-commentary architecture used in the current `/usage-report` skill. > > Kept here for: > - Side-by-side comparison runs against `/usage-report` ou
- Visualization Guidelines
- Prerequisites
- Input
- Workflow
- Step 1: Get Bastion IP
- Step 2: Copy Export Script to Bastion
- Step 3: Run Export on Bastion
- Step 4: Create Dated Subfolder and Download the CSV
- Step 5: Install Python Dependencies and Generate Charts
- Step 5b: Generate Timeseries Chart
- Step 5b2: Generate Compute Platform Timeseries Chart
- Step 5c: Generate Instance Lifetime Chart
- Step 5c-ts: Generate Lifetime-Bucket Retention Chart
- Step 5c2: Generate Customer-Active-Instances Chart
cd terraform/telemetry-collector && terraform output -raw bastion_public_ip scp -o StrictHostKeyChecking=no -i ~/.ssh/id_ed25519 \ terraform/telemetry-collector/bastion-scripts/telemetry_db.py \ ssh -o StrictHostKeyChecking=no -i ~/.ssh/id_ed25519 \ mkdir -p $DATE_DIR Cumulative -- all customers ever Active-yesterday -- only customers that reported on the last complete day. Pass YYYY-MM-DD - 1 (the previous day relative to report date) so today's partial-day undercount doesn't bias the picture. gh api repos/agentic-community/mcp-gateway-registry \
What does the usage-report-v0 skill do?
ARCHIVED - LLM-driven usage report generation (pre-deterministic refactor). Kept as a reference for comparing prose, structure, and content philosophy against the current /usage-report skill. NOT MEANT TO BE INVOKED.
How do I install it?
Run `npx skills add agentic-community/mcp-gateway-registry --skill usage-report-v0 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From agentic-community/mcp-gateway-registry, a repository with 845 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.