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 twells89/sigma-migration-skills --skill quicksight-assessmentgit clone --depth 1 https://github.com/twells89/sigma-migration-skillsWrote 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/twells89/sigma-migration-skills/quicksight-assessment)<a href="https://agentmods.dev/skills/twells89/sigma-migration-skills/quicksight-assessment"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/quicksight-assessment/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/twells89/sigma-migration-skills/quicksight-assessment"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/quicksight-assessment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00150 | $0.03153 |
| Opus 5 | $0.00075 | $0.01577 |
| Sonnet 5 | $0.00030 | $0.00631 |
| Haiku 4.5 | $0.00015 | $0.00315 |
Grade A, and why
quicksight-assessment 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Amazon QuickSight Assessment
Surveys an Amazon QuickSight account — what the configured AWS credentials can
reach — via the AWS CLI (aws quicksight ..., shelled out via subprocess; no
boto3). Emits a markdown readout + JSON inventory + a value/cost-ranked migration
shortlist the user can hand to a Sigma rep or directly to the
quicksight-to-sigma conversion skill.
This is the QuickSight sibling of powerbi-assessment and tableau-assessment —
same file layout, same readout sections, same privacy discipline, same
value/cost shortlist scoring — adapted to QuickSight's two-artifact world
(analysis + datasets).
READ-ONLY. Every call is a
list-*ordescribe-*GET-equivalent. The skill never writes to QuickSight and never posts to Sigma. It does not edit anything outside its output directory.
Enterprise edition required for complexity. The
describe-analysis-definition,describe-dashboard-definition, anddescribe-data-setAPIs are Enterprise-only — a Standard-edition account rejects them. The skill detects that, flags the account as Standard, and degrades to a counts-only readout (it never crashes on a Standard account, but it also can't score complexity there).
Warehouse-agnostic. QuickSight datasets source from many places (Snowflake, Redshift, Athena, BigQuery, Databricks, Postgres, S3, SaaS). The skill reports each dataset's physical source kind; the downstream
quicksight-to-sigmaconverter re-points Sigma at the same tables (S3/SaaS are a known gap). Worked examples use Snowflake because that's where the dev fixtures live.
Privacy posture (READ FIRST, surface to the customer)
This skill reads analysis / dataset metadata, not warehouse data. What crosses Anthropic's API on its way through Claude:
| Crosses Anthropic API | Stays local |
|---|---|
| Aggregate counts (analysis / dataset / data-source counts) | Warehouse / SPICE rows (never queried) |
| Analysis, dataset, data-source names | AWS credentials |
| Analysis definitions — visual config + calc-field expressions | Actual visual cell values |
| Dataset metadata — physical source kinds, custom-sql, RLS/CLS flags |
What ships with it
24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fixtures/sample-readout/complexity.json 4.1 KB
- fixtures/sample-readout/inventory.json 2.9 KB
- fixtures/sample-readout/migration-plan.json 2.8 KB
- fixtures/sample-readout/README.md 2.0 KB
- fixtures/sample-readout/readout.md 7.2 KB
- fixtures/sample-readout/shortlist.json 1.5 KB
- PRIVACY.md 4.9 KB
- README.md 6.2 KB
- refs/environment.md 5.7 KB
- refs/output-shapes.md 5.5 KB
- refs/readout-template.md 7.1 KB
- refs/token-model.json 3.6 KB
- scripts/bootstrap.ps1 41 KB runs code
- scripts/bootstrap.sh 44 KB runs code
- scripts/build-shortlist.rb 4.0 KB runs code
- scripts/doctor.ps1 24 KB runs code
- scripts/doctor.sh 34 KB runs code
- scripts/dup-dashboards.py 13 KB runs code
- scripts/migration-plan.rb 6.5 KB runs code
- scripts/quicksight-inventory.py 14 KB runs code
- scripts/render-readout-html.rb 47 KB runs code
- scripts/render-readout.rb 9.7 KB runs code
- scripts/requirements.txt 499 B
- scripts/score-quicksight-complexity.rb 6.2 KB runs code
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.
- 11d ago First seen · 262 lines · 150 tokens per session scan A 91f6cf9fc0f5
quicksight-assessment is a skill published in the GitHub repository twells89/sigma-migration-skills (16 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 3,153 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…