Ready to supercharge your AI agents?

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

Get Started Free →

BB workflows · get-bb | DecimalAI

agent toolingby get-bb

BB workflows

get-bb/workflows

Source get-bb/bb ↗License MIT

Execute a workflow script that orchestrates multiple subagents deterministically.

SkillScore82Maintained

Automatic

AI Engineer pack

Last verified 9/2/2026

What it changes

Passed 16 of 19 test cases with the skill, and 4 of 19 without it.

Without skill23%

With skill82%

Checks it passed that the model alone missed

The response specifies using bb workflows status.
The response specifies redirecting output into BB_THREAD_STORAGE.
The response identifies references/runs.md as the required document.

and 10 more in the full report

13 fixed5 passed either way4 still failing0 broke

Pass-rate lift: +59 pp
Tokens: -33%
Agent turns: 0%
Response time: -54%

Model gemini-3.6-flashMeasured 9/2/2026v218 of 22 cases passed with skill · 19 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/get-bb-workflows/SKILL.md https://app.decimal.ai/s/get-bb-workflows/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add get-bb-workflows, 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/get-bb-workflows/ and pins it in .decimal/skills.lock

decimalai skills add get-bb-workflows

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

curl -fsSL --create-dirs -o .claude/skills/get-bb-workflows/SKILL.md https://app.decimal.ai/s/get-bb-workflows/SKILL.md

Raw file: /s/get-bb-workflows/SKILL.md ↗ · machine-readable summary at /s/get-bb-workflows.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

I have created a workflow file at `.bb/workflows/lint-all.js`. What is the exact CLI command to validate this file before running it?

What was checked, without and with the skill
Checked	Without skill	With skill
The response outputs bb workflows validate --file .bb/workflows/lint-all.js.	Missed	Passed

case-11 · gemini-3.6-flash · 9/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md97 lines4 files

BB workflows

Use a workflow when the user explicitly asks for multi-agent orchestration. Ordinary tasks do not authorize a workflow run.

A workflow puts deterministic control flow around normal BB worker threads. The script can fan out work, pipeline stages, verify results, and return structured data. Worker threads retain normal workspace tools and permissions.

Start safely

Inspect the task and repository before you choose the work list.
Confirm the provider, model, and reasoning tuple from the live catalog.
Write the smallest workflow that gives the requested coverage.
Validate the exact source before execution.
Start the background run.
Emit the returned workflow preview directive exactly once.
Use compact status for progress and paged history for details.

Check an explicit model selection with:

bb provider list --environment "$BB_ENVIRONMENT_ID" --json
bb provider models <provider-id> --environment "$BB_ENVIRONMENT_ID" --json

Do not guess model identifiers or partial selection tuples.

Read only the required detail

Read references/authoring.md when you write or change workflow source, schemas, agent options, or nested workflows.
Read references/orchestration.md when you design pipelines, barriers, verification, panels, loops, or other quality controls.
Read references/runs.md when you validate, start, inspect, stop, or resume a workflow.

Minimal source

Every script starts with a literal meta object:

Track record

Benchmark

16 / 19

test cases passed, vs 4 / 19 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 v5 — 9/1/2026

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

get-bb / bb

plugins/workflows/skills/workflows/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2Bundled 3 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

vellum-ai/workflowsDelegate a big or high-stakes job to a fleet of parallel subagents, orchestrated deterministically; runs unattended and reports backClose match+44 pp pass-rate lift

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

BB workflows

Start safely

Read only the required detail

Minimal source

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills