Ready to supercharge your AI agents?

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

CI Loop (moai-workflow-ci-loop) · modu-ai | DecimalAI

devopsby modu-ai

CI Loop (moai-workflow-ci-loop)

modu-ai/moai-workflow-ci-loop

Source modu-ai/moai-adk ↗License Apache-2.0

Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user.

SkillScore82Maintained

Automatic

DevOps & SRE pack

Last verified 8/15/2026

What it changes

Passed 16 of 19 test cases with the skill, and 6 of 19 without it.

Without skill32%

With skill82%

Checks it passed that the model alone missed

Returns control without auto-restarting the watch loop
Prohibits subagents from calling AskUserQuestion directly
Exits with code 3 upon exceeding the 30-minute timeout limit

and 14 more in the full report

12 fixed6 passed either way3 still failing1 broke

Pass-rate lift: +50 pp
Tokens: +133%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/15/2026v118 of 22 cases passed with skill · 19 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/modu-ai-moai-workflow-ci-loop/SKILL.md https://app.decimal.ai/s/modu-ai-moai-workflow-ci-loop/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add modu-ai-moai-workflow-ci-loop, 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/modu-ai-moai-workflow-ci-loop/ and pins it in .decimal/skills.lock

decimalai skills add modu-ai-moai-workflow-ci-loop

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

curl -fsSL --create-dirs -o .claude/skills/modu-ai-moai-workflow-ci-loop/SKILL.md https://app.decimal.ai/s/modu-ai-moai-workflow-ci-loop/SKILL.md

Raw file: /s/modu-ai-moai-workflow-ci-loop/SKILL.md ↗ · machine-readable summary at /s/modu-ai-moai-workflow-ci-loop.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

What git commit message pattern should be used when pushing an auto-fix patch for an import-order failure on iteration 2 of PR #63?

What was checked, without and with the skill
Checked	Without skill	With skill
Formats commit message as fix(ci): auto-fix <classification> failure (iter <N>)	Missed	Passed

case-15 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md167 linessingle file

CI Loop (`moai-workflow-ci-loop`)

Unified CI watch + auto-fix loop. The orchestrator invokes this skill after /moai sync Phase 4 (gh pr create) returns a PR number. The skill polls required checks, classifies failures into mechanical vs semantic, attempts safe patches up to 3 iterations, and escalates semantic failures via AskUserQuestion.

Quick Reference

Trigger: /moai sync Phase 4 PR-create returns a PR number, or an existing PR needs CI monitoring.

Two phases, one skill:

Watch — Poll gh pr checks every 30s, classify required vs auxiliary via .github/required-checks.yml SSoT; exit on green/fail/timeout.
Auto-fix — On required-fail (exit 2), receive JSON handoff, run up to 3 patch iterations, escalate semantic failures immediately.

One-liner:

MOAI_CIWATCH_GH=gh sh scripts/ci-watch/run.sh <PR_NUMBER> <BRANCH>

Exit codes:

0 — all required passed → ready-to-merge AskUserQuestion
1 — fatal error → surface remediation
2 — required failure → JSON handoff → auto-fix phase
3 — 30-min hard timeout → blocker message, return control

HARD invariants:

AskUserQuestion is orchestrator-only — CLI, shell scripts, and the manager-develop (cycle_type=autofix) subagent MUST NOT call it.
Force-push is absolutely prohibited (--force, -f, --force-with-lease all banned).
Max 3 auto-fix iterations; iteration 4+ triggers mandatory blocking AskUserQuestion.
Semantic failures (race, deadlock, panic, assertion) are never auto-patched.
Protected files: .env*, credentials, .claude/settings*.json, .github/required-checks.yml, scripts/ci-watch/run.sh.

Implementation Guide

Phase 1 — Watch Loop

Track record

Benchmark

16 / 19

test cases passed, vs 6 / 19 without

Adoption

Users: 1
Times used: 19

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

modu-ai / moai-adk

.claude/skills/moai-workflow-ci-loop/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.