workflow-guardrailslisted
Install: claude install-skill bayeslearner/bayeslearner-skills
# Workflow Guardrails
Use this skill for agent operating discipline on real development, analysis,
and hybrid projects.
The point is simple: keep the project's durable artifacts current, use sound
engineering judgment, and do not fake progress.
## First Actions
Before substantive changes:
1. Inspect the repo, key docs, and current conventions.
2. Determine the mode: development, analysis, or hybrid.
3. Identify what must be maintained:
- specs, requirements, designs
- tasks, milestones, workstreams
- project-level feature inventory or status ledger
- feature status or verification status
- project knowledge or documentation
- analysis runs, assumptions, or result summaries
4. Classify what is stable vs live:
- repo knowledge vs agent memory
- frozen inputs vs live pulls
- durable workflow code vs one-off exploration
- current repo state vs stale notes or stale runtime state
5. Read the canonical steering file, usually `CLAUDE.md`, if it exists.
6. State the first boundary-sensitive change before making it.
## Core Rules
### 1. Repo First
- Prefer repo truth over memory or habit.
- Reuse the repo's structure before inventing a new one.
- If you change a weak convention, explain the delta first.
### 2. Maintain the Real Artifacts
- Keep the project's planning and status artifacts current as part of the work.
- Do not leave specs, tasks, milestones, feature status, or analysis records
behind while code moves ahead.
- If the user names ma