Ready to supercharge your AI agents?

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

GitHub Automation Skill — measured AI agent skill | DecimalAI

ruvnet/github-automation

SkillScore74Maintained

GitHub workflow automation for issues, pull requests, CI, and releases. Use when: repository hosting actions are explicitly requested. Skip when: local git operations are sufficient or publishing is unauthorized.

by ruvnet

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

Automatic

DevOps & SRE pack

decimalai skills pull ruvnet-github-automation

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ruvnet-github-automation/SKILL.md

Raw file: /s/ruvnet-github-automation/SKILL.md ↗ · machine-readable summary at /s/ruvnet-github-automation.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 33h ago

—-28% tokens0% turns74% of whole cases pass with skill (17/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-31%	0%
case-05	✗→✓	▲ Improved	25%	0%
case-07	✗→✓	▲ Improved	-57%	0%
case-16	✗→✓	▲ Improved	50%	0%
case-06	✓→✗	▼ Worse	-54%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

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

ruvnet / ruflo

v3/@claude-flow/codex/.agents/skills/github-automation/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

GitHub Automation Skill

Purpose

Automate GitHub workflows while keeping external writes explicit and scoped.

Commands

Create Pull Request

bash
gh pr create --draft

Inspect Checks

bash
gh pr checks

Best Practices

Confirm repository and branch before external writes
Inspect CI evidence before changing workflows
Never publish, merge, or close without authorization
Report the exact resulting URL or identifier

Want to see if ruvnet/github-automation 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.