KunanonJ/superstacks / plugins/superstacks/skills/workflow-profile
workflow-profile
UnverifiedUse when starting a ticket or choosing merge, review, trust_level, and pipeline order. Generic ticket refs, merge owner, and skill sequence.
Workflow profile
Generic team conventions. Override with repo docs when they exist. safety-overrides still win.
Ticket references
- Cite tickets as
Refs #Nin commits and pull requests. - Never use
Closes,Fixes, orResolves. The human merge owner closes tickets.
Merge owner
The human who asked for the work (or the user on the ticket) is the merge owner unless trust_level says otherwise. The implementing agent opens a draft PR and stops.
Trust level
Set trust_level here or in repo docs. Default: 1. Merge and ready-for-review authority are read from the owner's decision record through owner-decisions. Only a recorded standing rule may raise the level, for the scope it states; nothing else raises it.
trust_level: 1
| Level | Merge |
|---|---|
| 1 | Humans merge everything. The agent never merges. |
| 2 | A designated merge bot may merge green two-way-door PRs. |
| 3 | Autopilot may merge two-way-door PRs that have verify-loop evidence (VERIFY_FAIL then VERIFY_PASS). |
One-way doors always need a human plus interrogate, at every level: money movement, schema or data migrations, auth, data deletion, infra or prod config, licences.
Pipeline order
how → writing-plans → verify-loop → test-driven-development → verification-before-completion → code-review → (interrogate on one-way doors) → pr.
Plans live in the pull request body. Run ticket-pipeline/scripts/pipeline_status.py instead of inferring which steps are done.
Optional model table
Used by how and interrogate when the Task tool accepts a model field. Omit model unless the user names a slug.
| Role | Model |
|---|---|
| how explorer | omit model (parent) |
| how explainer | omit model (parent) |
| interrogate reviewers | omit model (parent), one reviewer per row the user adds |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |