Separate workflow instructions from safety, authority, escalation, and validation rules. Use when an assistant, agent, or skill pack is getting muddled because process steps, permissions, forbidden actions, and review gates are mixed together.
Scanned 6/15/2026
Install via CLI
openskills install markoblogo/abvx-agent-skills---
name: workflow-policy-layering
description: Separate workflow instructions from safety, authority, escalation, and validation rules. Use when an assistant, agent, or skill pack is getting muddled because process steps, permissions, forbidden actions, and review gates are mixed together.
license: MIT
metadata:
abvx_status: experimental
abvx_origin: original
---
# Workflow Policy Layering
Separate operating workflow from policy and authority.
## Goal
Turn a messy assistant spec into clear layers:
- workflow;
- authority and boundaries;
- escalation;
- validation.
## Workflow
1. **Extract the workflow**
- write the actual operating sequence without policy noise;
- keep it in business or task language.
2. **Extract authority separately**
- list what the assistant may do directly;
- list what requires confirmation;
- list what is forbidden.
3. **Extract escalation paths**
- define what should be handed to a human, another role, or another system;
- make the next step concrete instead of vague refusal.
4. **Extract validation**
- define what should be checked before a response, mutation, recommendation, or delivery is considered complete;
- keep this as a short checklist or gate list.
5. **Rewrite the spec**
- keep workflow in the main skill body;
- keep detailed policy and validation in `references/` or clearly named sections;
- ensure the assistant does not confuse “can explain” with “can execute”.
6. **Run a conflict check**
- look for steps that assume authority the policy layer does not grant;
- look for policy text that silently changes the workflow;
- fix contradictions before release.
## Output Shape
Return:
- workflow layer;
- authority layer;
- escalation layer;
- validation layer;
- open contradictions, if any.
## Design Rules
- Do not hide forbidden actions inside workflow prose.
- Do not let validation sprawl into generic QA philosophy.
- Keep escalation concrete and actionable.
- Treat drafts, summaries, and recommendations as different from real execution authority.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.