Ready to supercharge your AI agents?

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

Create Custom Routine · evolution-foundation | DecimalAI

agent toolingby evolution-foundation

Create Custom Routine

evolution-foundation/create-routine

Source evolution-foundation/evo-nexus ↗License NOASSERTION

Create a new automated routine (ADW) for the scheduler. Guides the user through defining what the routine does, the type (AI or systematic), the schedule, and generates the Python script + Makefile target.

SkillScore86Maintained

Automatic

DevOps & SRE pack

Last verified 8/19/2026

What it changes

Passed 18 of 21 test cases with the skill, and 4 of 21 without it.

Without skill18%

With skill86%

Checks it passed that the model alone missed

Records cost equal to 0.
Executes make run R=log-cleanup.
Calls run_claude from runner.py.

and 19 more in the full report

15 fixed4 passed either way3 still failing0 broke

Pass-rate lift: +68 pp
Tokens: +55%
Agent turns: 0%
Response time: -58%

Model gemini-3.6-flashMeasured 8/19/2026v119 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/evolution-foundation-create-routine/SKILL.md https://app.decimal.ai/s/evolution-foundation-create-routine/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add evolution-foundation-create-routine, 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/evolution-foundation-create-routine/ and pins it in .decimal/skills.lock

decimalai skills add evolution-foundation-create-routine

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

curl -fsSL --create-dirs -o .claude/skills/evolution-foundation-create-routine/SKILL.md https://app.decimal.ai/s/evolution-foundation-create-routine/SKILL.md

Raw file: /s/evolution-foundation-create-routine/SKILL.md ↗ · machine-readable summary at /s/evolution-foundation-create-routine.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

I just finished writing a custom routine with script identifier `log-cleanup`. What command line call runs this specific routine manually using the project automation helper?

What was checked, without and with the skill
Checked	Without skill	With skill
Executes make run R=log-cleanup.	Missed	Passed

case-13 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md209 linessingle file

Create Custom Routine

Guide the user through creating a new automated routine that runs on schedule via the EvoNexus scheduler.

What You're Building

A routine is a Python script in ADWs/routines/custom/ that runs on a schedule (daily, weekly, monthly, or interval). There are two types:

AI routines — invoke Claude Code CLI with an agent to perform reasoning tasks (reports, analysis, decisions). Cost tokens and ~30-120s per run.
Systematic routines — pure Python scripts that perform deterministic operations (API calls, file ops, data transforms). No AI, no tokens, no cost, ~1-5s per run.

Step 1: Understand the Task

Ask the user:

What should this routine do? (e.g., "check my GitHub repos every morning", "ping API endpoints every 5 minutes")
AI or systematic? Help the user decide:
- Use AI when: the task needs reasoning, analysis, writing, or decisions (generate a report, analyze sentiment, summarize data, make recommendations)
- Use systematic when: the task is deterministic and repeatable (HTTP health checks, file cleanup, data snapshots, metric logging, backups, CSV exports)
When should it run? (daily at X, every N minutes, weekly on day, monthly on day 1)
What output? (HTML report, markdown file, CSV, JSON, Telegram notification, log entry, or just action)

If AI routine, also ask:

Which agent should run it?
- clawdia-assistant — ops, daily tasks, email, meetings
- flux-finance — financial reports, Stripe, ERP
- atlas-project — GitHub, Linear, project tracking
- pulse-community — Discord, WhatsApp, community
- pixel-social-media — social media, content, analytics
- sage-strategy — OKRs, strategy, competitive analysis
- nex-sales — pipeline, proposals, leads
- mentor-courses — courses, learning paths
- kai-personal-assistant — health, habits, personal

Step 2: Generate the Script

AI routine

Create the routine script at ADWs/routines/custom/{name}.py:

Track record

Benchmark

18 / 21

test cases passed, vs 4 / 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 — 8/3/2026

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

evolution-foundation / evo-nexus

.claude/skills/create-routine/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

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

Create Custom Routine

What You're Building

Step 1: Understand the Task

Step 2: Generate the Script

AI routine

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills