galley
SolidAuthors and validates Galley task YAML, profiles, daemon handoff, run evidence, and queueing. Use when the user asks to create/repair/queue a Galley task, configure profiles/daemon/PR automation, or diagnose a Galley run.
AI & Automation 16 stars
1 forks Updated 2 days ago MIT
Install
Quality Score: 80/100
Stars 20%
Recency 20%
Frontmatter 20%
Documentation 15%
Issue Health 10%
License 10%
Description 5%
Skill Content
# Galley
Use this skill to turn a user's development intent into a valid Galley task, prepare a repository for Galley execution, or diagnose a Galley run.
## Context
Galley executes task YAML files through a file-backed queue. Task authoring is conversational; execution is AFK after queueing, meaning away-from-keyboard execution without further user interaction until completion, retry exhaustion, or supervisor escalation.
Supervisor = LLM-based review gate that returns acceptance or revision verdicts. Executor = the LLM that performs implementation work inside the task worktree. Claim TTL and heartbeat are daemon liveness signals for running tasks.
## Flow Catalog
Use this table to choose the active flow. Load every required file for that flow before acting. SKILL.md selects the route; the routed references own step-by-step procedure and output format.
| Flow | Use when | Required files | Core invariant |
| --- | --- | --- | --- |
| Task authoring | User wants a Galley task YAML, ACs, scope, queueing, or task repair. | `references/task-authoring.md`, `references/authoring-quality.md`, `references/task.schema.json`, `scripts/create_task_skeleton.py` | User approves task direction, execution settings, and queueing; task YAML is generated from the skill skeleton and validates before queueing. |
| Profile authoring | User wants `quality.yaml` or `environment.yaml`, or setup finds missing profiles. | `references/profile-authoring.md`, `references/authoring-quality.md`, `ref...
Details
- Author
- shinpr
- Repository
- shinpr/galley
- Created
- 2 months ago
- Last Updated
- 2 days ago
- Language
- Go
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
Code & Development Listed
aitask-qa
Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks
6 Updated today
beyondeye Code & Development Listed
aitask-review
Review code using configurable review guides, then create tasks from findings.
6 Updated today
beyondeye Code & Development Listed
gsd-eval-review
Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan
1 Updated 6 days ago
hoanganhduc