Ready to supercharge your AI agents?

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

A5c AI/Work Unit Decomposition — measured AI agent skill | DecimalAI

a5c-ai/work-unit-decomposition

SkillScore86Maintained

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Project Management pack

decimalai skills pull a5c-ai-work-unit-decomposition

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-work-unit-decomposition/SKILL.md

Raw file: /s/a5c-ai-work-unit-decomposition/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-work-unit-decomposition.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

Yes — +41% lift-10% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-52%	0%
case-05	✗→✓	▲ Improved	3%	0%
case-06	✗→✓	▲ Improved	9%	0%
case-11	✗→✓	▲ Improved	-70%	0%
case-12	✗→✓	▲ Improved	-40%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/metaswarm/skills/work-unit-decomposition/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

When decomposing a large feature into implementable chunks
When preparing for orchestrated execution

Work Unit Structure

Each work unit specifies:

ID - Unique identifier
Title - Human-readable description
Definition of Done - Enumerated checklist items
File Scope - Which files the unit may modify
Dependencies - Other work units this depends on
Human Checkpoint - Whether human approval is needed before execution
Parallel Safe - Whether it can execute alongside other units

Human Checkpoint Triggers

Mark human checkpoints for:

Schema or database changes
Security-sensitive code paths
New architectural patterns not seen in codebase
External API integrations
Breaking changes to public interfaces

Agents Used

agents/architect/ - Creates the decomposition
agents/cto/ - Validates TDD readiness per unit

Tool Use

Invoke as part of: methodologies/metaswarm/metaswarm-orchestrator (Phase 4)

Want to see if a5c-ai/work-unit-decomposition would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.