Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Decompose Into Slices · gsd-build | DecimalAI

productivityby gsd-build

Decompose Into Slices

gsd-build/decompose-into-slices

Source gsd-build/gsd-2 ↗License MIT

Break a plan or milestone brief into independently-grabbable vertical slices (tracer bullets). Produces slices in `M###-ROADMAP.md` by default, or GitHub issues only with explicit user confirmation.

SkillScore61Maintained

Automatic

Project Management pack

Last verified 9/28/2026

What it changes

Passed 9 of 14 test cases with the skill, and 4 of 14 without it.

Without skill26%

With skill61%

Checks it passed that the model alone missed

Both parallel slices explicitly declare `depends:[S01]`.
The issue body references `.gsd/milestones/M010/M010-CONTEXT.md`.
The response advises against manually editing checkbox state in the roadmap file.

and 5 more in the full report

8 fixed6 passed either way9 still failing0 broke

Pass-rate lift: +35 pp
Tokens: +80%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 9/28/2026v114 of 23 cases passed with skill · 14 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gsd-build-decompose-into-slices/SKILL.md https://app.decimal.ai/s/gsd-build-decompose-into-slices/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gsd-build-decompose-into-slices, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gsd-build-decompose-into-slices/ and pins it in .decimal/skills.lock

decimalai skills add gsd-build-decompose-into-slices

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gsd-build-decompose-into-slices/SKILL.md https://app.decimal.ai/s/gsd-build-decompose-into-slices/SKILL.md

Raw file: /s/gsd-build-decompose-into-slices/SKILL.md ↗ · machine-readable summary at /s/gsd-build-decompose-into-slices.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Where exactly on disk should the finalized milestone roadmap file be written for milestone M017?

What was checked, without and with the skill
Checked	Without skill	With skill
The response specifies writing the file to `.gsd/milestones/M017/M017-ROADMAP.md`.	Missed	Passed

case-17 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md134 linessingle file

Typical invocation points:

After write-milestone-brief (or after a discuss phase that produced a brief)
When a roadmap exists but slices are too thick, too few, or poorly ordered
When exporting the plan for external collaborators (GitHub issues)

<core_principle> VERTICAL, NOT HORIZONTAL. A slice that adds "schema + API + UI + tests for feature X on one narrow path" is vertical. A slice that adds "all schemas for all features" is horizontal and is wrong. Horizontal slices destroy the demoability property that makes slice completion meaningful.

MANY THIN, NOT FEW THICK. If a slice could be split into two demoable pieces, split it. Thin slices retire risk earlier, parallelize better, and give the user faster feedback on whether the direction is right.

DEPENDENCY GRAPH, NOT LINEAR LIST. Slices that don't depend on each other should be marked that way — depends:[] means the slice can start immediately. The GSD engine uses this to parallelize. </core_principle>

Step 1: Load context

Read M###-CONTEXT.md for the active milestone — the brief is the source of truth for scope.
Read M###-ROADMAP.md if one exists — you may be refining rather than creating from scratch.
Read src/resources/extensions/gsd/templates/roadmap.md for the exact slice format. The parser depends on it.
If the plan came from a GitHub issue (user passed a URL or number), fetch it with mcp__github__issue_read.

Step 2: Explore the codebase briefly

If you haven't yet, spawn Agent(subagent_type=Explore) to map the modules the milestone touches. This is fast and prevents proposing slices that don't align with the codebase's seams.

Step 3: Draft vertical slices

Produce a draft list of slices. For each slice, capture:

ID: S01, S02, ... — assigned in dependency order (earliest first).
Title: short, descriptive, says what the slice delivers.

Track record

Benchmark

9 / 14

test cases passed, vs 4 / 14 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gsd-build / gsd-2

src/resources/skills/decompose-into-slices/SKILL.md

View on GitHub ↗

License MITImported 8/31/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

open-gsd/decompose-into-slicesBreak a plan or milestone brief into independently-grabbable vertical slices (tracer bullets), written to `M###-ROADMAP.md` by default (GitHub issues only on explicit confirmation). Prefers many thin slices over few thick ones and marks dependency order. Use when asked to "break this into slices", "decompose the plan", "vertical slices", "break into issues", or when a plan needs task-level decomposition.Near-identical description+18 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.