Ready to supercharge your AI agents?

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

Get Started Free →

A5c AI/Merge Queue — measured AI agent skill | DecimalAI

a5c-ai/merge-queue

SkillScore32Maintained

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.

by a5c-ai

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

Automatic

DevOps & SRE pack

decimalai skills pull a5c-ai-merge-queue

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-merge-queue/SKILL.md

Raw file: /s/a5c-ai-merge-queue/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-merge-queue.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 9d ago

—-40% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	575%	0%
case-02	✗→✓	▲ Improved	858%	0%
case-04	✗→✓	▲ Improved	-52%	0%
case-08	✗→✓	▲ Improved	-77%	0%
case-13	✗→✓	▲ Improved	-77%	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 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/gastown/skills/merge-queue/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

When multiple agents have worked on overlapping areas
When integration testing is needed before landing
When conflict resolution requires coordination

Process

Collect pending changes from all agent branches
Detect conflicts between branches and target
Resolve conflicts (auto-resolve where possible)
Merge in dependency order with attribution
Verify integration (tests, lint, build)

Conflict Strategies

auto: Attempt automatic resolution, escalate on failure
manual: Always require human review
theirs: Prefer incoming changes
ours: Prefer target branch changes

Tool Use

Invoke via babysitter process: methodologies/gastown/gastown-merge-queue

Want to see if a5c-ai/merge-queue 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.