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 streamlit-to-sigmagit 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/streamlit-to-sigma)<a href="https://agentmods.dev/skills/twells89/sigma-migration-skills/streamlit-to-sigma"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/streamlit-to-sigma/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/streamlit-to-sigma"><img src="https://agentmods.dev/badge/skills/twells89/sigma-migration-skills/streamlit-to-sigma.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 | $0.00067 | $0.02745 |
| Opus 5.5 | $0.00027 | $0.01098 |
| Sonnet 5.5 | $0.00013 | $0.00549 |
| Haiku 4.5 | $0.00007 | $0.00275 |
Grade A, and why
streamlit-to-sigma 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 — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Streamlit → Sigma
Static analysis is the safety boundary: never import or execute the Streamlit
app during discovery. Translate only behavior whose source/dataframe lineage
is proven. Everything else stays visible in gaps.json.
This skill uses the companion sigma-authoring skills as the source of truth
for Sigma data-model/workbook shapes. Run commands from this skill directory.
Read before converting:
Inputs
Accept a project directory or a single main file. A complete Streamlit-in-Workspaces project usually contains:
snowflake.yml
pyproject.toml
streamlit_app.py
pages/*.py or app_pages/*.py
lib/*.py
.streamlit/config.toml
The analyzer follows Python artifacts listed in snowflake.yml, local page
files, and helper modules. It reads configuration and source text only.
Quick offline conversion
python3 scripts/streamlit-convert.py /path/to/project \
--connection <sigma-connection-id> \
--folder <sigma-folder-id> \
--name "Project Name" \
--out-dir /tmp/project-migration
Outputs:
streamlit-ir.json— source/provenance-aware normalized contractsource-signature.json— reuse-check inputgaps.jsonandsecurity.jsondm-spec.json/dm-result.jsonwb-spec.json/workbook-result.jsonlayout.xmlparity-plan.json
The offline workbook defaults to custom-SQL sources because those preserve source semantics without guessing server-remapped DM ids.
One-command orchestrator
Dry-run is the default:
python3 scripts/migrate-streamlit.py /path/to/project \
--connection <sigma-connection-id> \
--out-dir /tmp/project-migration
Posting requires explicit gate decisions:
python3 scripts/migrate-streamlit.py /path/to/project \
--connection <sigma-connection-id> \
--name "Project Name" \
--reuse-decision custom-sql \
--ack-security \
--post
What ships with it
60 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.
- converter/__init__.py 1.1 KB runs code
- converter/analyzer.py 62 KB runs code
- converter/api_capabilities.py 8.2 KB runs code
- converter/data_model.py 2.6 KB runs code
- converter/model.py 2.1 KB runs code
- converter/workbook.py 73 KB runs code
- fixtures/retail-fulfillment-control-tower/.streamlit/config.toml 120 B
- fixtures/retail-fulfillment-control-tower/app_pages/exceptions.py 2.4 KB runs code
- fixtures/retail-fulfillment-control-tower/app_pages/executive.py 1.8 KB runs code
- fixtures/retail-fulfillment-control-tower/app_pages/fulfillment.py 2.0 KB runs code
- fixtures/retail-fulfillment-control-tower/app_pages/returns.py 2.8 KB runs code
- fixtures/retail-fulfillment-control-tower/EXPECTED.md 8.3 KB
- fixtures/retail-fulfillment-control-tower/INTERACTION-VALIDATION.md 5.9 KB
- fixtures/retail-fulfillment-control-tower/lib/data.py 492 B runs code
- fixtures/retail-fulfillment-control-tower/lib/filters.py 3.3 KB runs code
- fixtures/retail-fulfillment-control-tower/lib/metrics.py 1.2 KB runs code
- fixtures/retail-fulfillment-control-tower/pyproject.toml 885 B
- fixtures/retail-fulfillment-control-tower/snowflake.yml 733 B
- fixtures/retail-fulfillment-control-tower/source-validation.sql 1.7 KB
- fixtures/retail-fulfillment-control-tower/sql/orders.sql 1.3 KB
- fixtures/retail-fulfillment-control-tower/streamlit_app.py 1.0 KB runs code
- fixtures/simple-retail/.streamlit/config.toml 61 B
- fixtures/simple-retail/pyproject.toml 137 B
- fixtures/simple-retail/snowflake.yml 354 B
- fixtures/simple-retail/streamlit_app.py 1.1 KB runs code
- QUICKSTART.md 1.5 KB
- refs/layout-visual-qa.md 2.1 KB
- refs/live-api-capabilities.md 6.9 KB
- refs/schema-hints.md 1.1 KB
- refs/streamlit-ir.schema.json 6.5 KB
- refs/supported-patterns.md 5.8 KB
- scripts/assert-phase6-ran.rb 256 KB runs code
- scripts/browser-login.sh 17 KB runs code
- scripts/cleanup-orphan-workbooks.rb 11 KB runs code
- scripts/escalate-gap.py 9.8 KB runs code
- scripts/find-or-pick-dm.rb 30 KB runs code
- scripts/get_token.py 20 KB runs code
- scripts/get-token.sh 4.4 KB runs code
- scripts/lib/anchor_values.rb 5.6 KB runs code
- scripts/lib/blind_grade.rb 9.3 KB runs code
- scripts/lib/browser-login-platform.sh 2.9 KB runs code
- scripts/lib/cli_encoding.rb 1.8 KB runs code
- scripts/lib/code_rep.py 9.6 KB runs code
- scripts/lib/code_rep.rb 12 KB runs code
- scripts/lib/control_lint.rb 22 KB runs code
- scripts/lib/degradation_ledger.rb 20 KB runs code
- scripts/lib/evidence_ledger.rb 6.9 KB runs code
- scripts/lib/flip_gate.rb 4.2 KB runs code
- scripts/lib/layout_lint.rb 15 KB runs code
- scripts/lib/preflight_lint.rb 30 KB runs code
- scripts/lib/ruby_compat.rb 2.9 KB runs code
- scripts/lib/sigma_rest.py 17 KB runs code
- scripts/lib/sigma_rest.rb 15 KB runs code
- scripts/lint-render-integrity.rb 11 KB runs code
- scripts/migrate-streamlit.py 13 KB runs code
- scripts/probe-controls.rb 23 KB runs code
- scripts/record-visual-check.rb 23 KB runs code
- scripts/refresh-token.sh 6.1 KB runs code
- scripts/sigma-export-png.py 6.2 KB runs code
- scripts/streamlit-convert.py 4.3 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 Changed · +17 lines 762e91e28e46
- 1mo ago First seen · 326 lines · 67 tokens per session scan A 4045d0b51109
streamlit-to-sigma is a skill published in the GitHub repository twells89/sigma-migration-skills (17 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,745 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…