quay/ai-helpers/work
- community
- ext:[{"type":"hook","description":"Pre/post lifecycle hooks"}]
Checking that the SKILL.md file is still in the repository.
Ralph Loop tick-loop for single-ticket development. Replaces the /start -> /code -> /pr -> /poll skill chain with one continuous state machine. Each tick: read state, do one thing, write state, continue.
Install
npx vskill@latest install quay/ai-helpers/workSemi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard
SKILL.md
Ralph Loop — Single-Ticket Workflow
Implement JIRA ticket $ARGUMENTS from assignment to merge-ready PR in one continuous loop.
Parse $ARGUMENTS: first token is the ticket key, --manual (if present) sets manual stepping mode.
Initialize
The Tick Loop
CRITICAL: Do NOT stop between ticks. The only valid exit points are:
- State reaches COMPLETE
- Manual mode and user chooses [a]bort
- triage_attempts >= 3 (ask user for guidance)
State Handlers
ASSIGN
View the JIRA ticket, assign it, transition to ASSIGNED.
-> advance to BRANCH
BRANCH
Check backport requirement, create feature branch, load area docs.
-> advance to IMPLEMENT
IMPLEMENT
Read AGENTS.md plus area docs. Write code, create tests, handle edge cases. -> advance to TEST
TEST
Run quality checks and tests:
If tests fail: fix and re-run. Stay in TEST until all pass. -> advance to COMMIT
COMMIT
Stage and commit:
If pre-commit hooks fail: fix, re-stage, new commit. Stay in COMMIT until success. -> advance to PR_CREATE
PR_CREATE
Validate PR title, fill description template, create PR:
-> advance to DORMANT_CI
DORMANT_CI
Poll script blocks internally — zero tokens consumed:
| Exit | Meaning | Next State | |
|---|---|---|---|
| 0 | All pass | COMPLETE | |
| 1 | CI fail | ADDRESS_FEEDBACK | |
| 2 | Pending | DORMANT_CI | |
| 3 | Comments | ADDRESS_FEEDBACK | |
| 4 | Awaiting review | DORMANT_REVIEW |
ADDRESS_FEEDBACK
Fix CI failures or address review comments. Increment triage_attempts. If triage_attempts >= 3: stop and ask user. After pushing fixes -> advance to DORMANT_CI
DORMANT_REVIEW
Awaiting human review approval. Re-poll:
| Exit | Next State | |
|---|---|---|
| 0 | COMPLETE | |
| 3 | ADDRESS_FEEDBACK | |
| 4 | DORMANT_REVIEW |
COMPLETE
Report summary and exit. If backport_required, suggest /backport <PR#>.
Manual Mode
When mode is "manual", pause after each tick and present:
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/dev/skills/work/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Extension points
hookPre/post lifecycle hooks
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/quay/ai-helpers/work)