agentsclimarketplace
Sign in

Workflow policy layering

Skill markoblogo/abvx-agent-skills/skills/workflow-policy-layering

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.From its SKILL.md

Install
npx -y skills add markoblogo/abvx-agent-skills --skill workflow-policy-layering

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 352 tokens by cl100k_base, as published. Nobody here has run it

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.

What ships with it: 2 files

1.7 KB alongside SKILL.md

agents/

Gives 0 of the 12 instructions most automation workflows skills give in 352 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • extract workflow without policy noise
  • keep workflow in business or task language
  • extract what may be done directly
  • extract what requires confirmation
  • extract forbidden actions
  • extract escalation paths

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,645. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.