Ready to supercharge your AI agents?

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

Flow-Next Setup (Optional) — measured AI agent skill | DecimalAI

gmickel/flow-next-setup

NewSkillScoreMaintained

Optional local install of flowctl CLI and CLAUDE.md/AGENTS.md instructions, plus an optional model-routing scaffold for the project instruction file. Use when user runs /flow-next:setup.

agent-toolingby gmickel

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/gmickel-flow-next-setup/SKILL.md

decimalai skills pull gmickel-flow-next-setup --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/gmickel-flow-next-setup/SKILL.md https://app.decimal.ai/s/gmickel-flow-next-setup/SKILL.md

Raw file: /s/gmickel-flow-next-setup/SKILL.md ↗ · machine-readable summary at /s/gmickel-flow-next-setup.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 5h ago

—-42% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-81%	0%
case-04	✗→✓	▲ Improved	-56%	0%
case-06	✗→✓	▲ Improved	-55%	0%
case-07	✗→✓	▲ Improved	-62%	0%
case-08	✗→✓	▲ Improved	-46%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

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

gmickel / flow-next

plugins/flow-next/skills/flow-next-setup/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v2Bundled 6 files

Skill contents

references/

templates/

SKILL.md

Flow-Next Setup (Optional)

Wire this repo to the plugin: the versioned docs snippet plus flow-next configuration. Fully optional - flow-next works without this via the plugin.

Benefits

Other AI agents (Codex, Cursor, etc.) can read instructions from CLAUDE.md/AGENTS.md

Workflow

Read workflow.md and follow each step in order.

workflow.md is the common router. Resolve each documented gate before reading its direct references/*.md target. When a branch says MUST read exactly one, read that complete reference before acting; never preload sibling host or Ralph references. Unknown/malformed routing state uses the safe/common fallback named at that gate.

Notes

Fully optional - standard plugin usage works without local setup
Copies nothing into the repo - plugin updates need no per-repo re-run, on any host
Safe to re-run - needed only when the snippet schema bumps or configuration/seeds change

Want to see if gmickel/flow-next-setup would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.