Ready to supercharge your AI agents?

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

Engineering Runbook Skill — measured AI agent skill | DecimalAI

nexu-io/eng-runbook

NewSkillScoreMaintained

An engineering runbook — service overview, alerts table, dashboards links, common procedures with copy-pasteable commands, on-call rotation, and an incident-response checklist. Use when the brief mentions "runbook", "ops doc", "on-call guide", "SRE doc", or "运维手册".

by nexu-io

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

Automatic

DevOps & SRE pack

decimalai skills pull nexu-io-eng-runbook

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/nexu-io-eng-runbook/SKILL.md

Raw file: /s/nexu-io-eng-runbook/SKILL.md ↗ · machine-readable summary at /s/nexu-io-eng-runbook.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 7d ago

No — -9% lift+23% tokens0% turns5% of whole cases pass with skill (1/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	3%	0%
case-20	✓→✗	▼ Worse	107%	0%
case-21	✓→✗	▼ Worse	205%	0%
case-22	✓→✗	▼ Worse	51%	0%
case-01	✗→✗	＝ Same ✗	3%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

nexu-io / open-design

design-templates/eng-runbook/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

Engineering Runbook Skill

Produce a single-page engineering runbook.

Workflow

Read DESIGN.md.
Identify the service from the brief.
Layout:

Header: service name, owner team, severity tier, version.
Service summary paragraph + dependency list.
Alerts table: alert name / severity / what it means / first response.
Dashboards & links list.
Common procedures block (3–4) with code blocks (deploy, rollback, rotate keys).
On-call rotation table (week / primary / secondary / backup).
Incident response checklist (5 numbered steps).

One inline <style>, semantic HTML, monospace for code blocks.

Output contract

<artifact identifier="runbook-name" type="text/html" title="Service Runbook">
<!doctype html>...</artifact>

Want to see if nexu-io/eng-runbook 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.