Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Turbo Pipeline Architecture · goldsky-io | DecimalAI

databy goldsky-io

Turbo Pipeline Architecture

goldsky-io/turbo-architecture

Source goldsky-io/agent-skills ↗License Not recorded

Design and architect Turbo pipelines.

SkillScore91Maintained

Automatic

Data Engineer pack

Last verified 8/6/2026

What it changes

Passed 19 of 21 test cases with the skill, and 10 of 21 without it.

Without skill45%

With skill91%

Checks it passed that the model alone missed

Recommends kafka as the source type.
Directs handoff to /turbo-pipelines.
Directs handoff to /goldsky-secrets.

and 16 more in the full report

10 fixed10 passed either way2 still failing0 broke

Pass-rate lift: +45 pp
Tokens: +90%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 8/6/2026v120 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/goldsky-io-turbo-architecture/SKILL.md https://app.decimal.ai/s/goldsky-io-turbo-architecture/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add goldsky-io-turbo-architecture, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/goldsky-io-turbo-architecture/ and pins it in .decimal/skills.lock

decimalai skills add goldsky-io-turbo-architecture

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/goldsky-io-turbo-architecture/SKILL.md https://app.decimal.ai/s/goldsky-io-turbo-architecture/SKILL.md

Raw file: /s/goldsky-io-turbo-architecture/SKILL.md ↗ · machine-readable summary at /s/goldsky-io-turbo-architecture.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Once the pipeline architecture, source selection, and worker sizing decisions are finalized, which downstream execution skills should be referenced to write the YAML, draft SQL transforms, and configure keys?

What was checked, without and with the skill
Checked	Without skill	With skill
Directs handoff to /turbo-pipelines.	Missed	Passed
Directs handoff to /turbo-transforms.	Missed	Passed
Directs handoff to /goldsky-secrets.	Missed	Passed

case-21 · gemini-3.6-flash · 8/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md349 lines5 files

Turbo Pipeline Architecture

Help users make architecture decisions for Turbo pipelines — source types, data flow patterns, resource sizing, sink strategies, and multi-chain deployment.

Triggers

Invoke this skill when the user:

Asks "how should I structure my pipeline" or "what's the best approach for..."
Needs to choose between dataset and kafka source types
Wants to send data to multiple destinations
Is planning a multi-chain deployment
Asks about resource sizing (s, m, l)
Wants to split or combine pipelines
Asks about parallelism, sink performance, or throughput
Needs to decide between one big pipeline vs several smaller ones
Mentions /turbo-architecture

Agent Instructions

Step 1: Understand the Requirements

Ask the user about:

What data? — Which chain(s), which events/datasets, historical or real-time only?
Where does it go? — Database, webhook, streaming topic, multiple destinations?
How much volume? — Single contract or all chain activity? How many events/sec?
Latency needs? — Real-time dashboards (sub-second) or analytics (minutes OK)?

Step 2: Recommend an Architecture

Use the patterns and decision guides below to recommend a pipeline architecture. Reference the templates in templates/ as starting points:

templates/linear-pipeline.yaml — Simple decode → filter → sink
templates/fan-out-pipeline.yaml — One source → multiple sinks
templates/fan-in-pipeline.yaml — Multiple events → UNION ALL → sink
templates/multi-chain-templated.yaml — Per-chain pipeline pattern

Step 3: Hand Off to Implementation Skills

Track record

Benchmark

19 / 21

test cases passed, vs 10 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

goldsky-io / agent-skills

skills/turbo-architecture/SKILL.md

View on GitHub ↗

Imported 8/2/2026Version v1Bundled 4 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Turbo Pipeline Architecture

Triggers

Agent Instructions

Step 1: Understand the Requirements

Step 2: Recommend an Architecture

Step 3: Hand Off to Implementation Skills

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills