agentsclimarketplace
Sign in

Plan to issues

Skill markoblogo/abvx-agent-skills/skills/plan-to-issues

Break a PRD, plan, or spec into independently executable vertical slices. Use when a product artifact needs to become agent-ready or human-ready implementation tickets, especially for client, product, and multi-track project workflows. Prefer thin end-to-end slices, explicit blockers, and issue-tracker-neutral output.From its SKILL.md

Install
npx -y skills add markoblogo/abvx-agent-skills --skill plan-to-issues

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

1.8 KB, 309 tokens by cl100k_base, as published. Nobody here has run it

Plan To Issues

Turn a plan into vertical slices that can actually be picked up and shipped.

Workflow

  1. Gather the parent artifact: PRD, plan, or spec.
  2. Explore the repo only enough to understand the real seams.
  3. Break the work into thin vertical slices:
    • end-to-end;
    • verifiable on their own;
    • blocker-aware;
    • small enough to review.
  4. Classify slices:
    • agent-ready;
    • human-required;
    • blocked by decision or external dependency.
  5. Show the proposed breakdown and adjust granularity before publishing or writing it down.

Slice Rules

  • Prefer many thin slices over a few thick ones.
  • Each slice should cut through the relevant layers, not isolate one layer.
  • A completed slice should be demoable, testable, or reviewable on its own.

Output

For each slice include:

  • title;
  • type;
  • what to build;
  • acceptance criteria;
  • blockers;
  • parent reference when relevant.

Rules

  • Do not output horizontal slices like "DB layer", "API layer", "UI layer" unless the parent work truly is infrastructure-only.
  • Keep issue-tracker-neutral language; publish to a tracker only if the workflow calls for it.
  • If the plan is still fuzzy, route back to spec-to-prd or grilling first.

Final Report

Summarize the slice graph, identify the first executable slice, and note what still needs a human decision.

What ships with it: 2 files

1.4 KB alongside SKILL.md

agents/

Gives 1 of the 12 instructions most plan spec skills give in 309 tokens

Counted across 1,099 of the 1,860 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 51 of 1099
  • Break plans into vertical sliceshere, and in 29 of 1099, across 11 files
  • Publish issues in dependency orderin 27 of 1099, across 9 files
  • Iterate until user approves the breakdownin 25 of 1099, across 7 files
  • Explore the repository to understand the codebase statein 24 of 1099, across 7 files
  • Use domain glossary vocabularyin 23 of 1099, across 5 files
  • Apply correct triage labels to published issuesin 23 of 1099, across 5 files
  • Prefer AFK slices over HITLin 22 of 1099, across 7 files
  • Write a specification before writing any codein 22 of 1099, across 14 files
  • Write failing tests before implementation codein 22 of 1099, across 20 files
  • Ask clarifying questions until requirements are concretein 21 of 1099, across 13 files
  • Respect existing architecture decision recordsin 20 of 1099, across 5 files

Said here and by no other author read

  • gather the parent artifact
  • explore the repo to understand the real seams
  • make each slice end-to-end and verifiable
  • classify each slice by readiness
  • show the proposed breakdown and adjust granularity
  • include title type build criteria and blockers for each slice

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 326,861. 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.