Ready to supercharge your AI agents?

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

Get Started Free →

Architecture Skill — measured AI agent skill | DecimalAI

davepoon/architecture

SkillScore100Maintained

Architecture design skill with ADR records, system design checklists, scalability assessment, and architecture patterns

by davepoon

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

Automatic

Coding pack

decimalai skills pull davepoon-architecture

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/davepoon-architecture/SKILL.md

Raw file: /s/davepoon-architecture/SKILL.md ↗ · machine-readable summary at /s/davepoon-architecture.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 5d ago

Yes — +9% lift-11% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-6%	0%
case-02	✗→✓	▲ Improved	-6%	0%
case-15	✓→✓	＝ Same ✓	-13%	0%
case-03	✓→✓	＝ Same ✓	3%	0%
case-04	✓→✓	＝ Same ✓	2%	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 — 8/3/2026

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

davepoon / buildwithclaude

plugins/cc-best/skills/architecture/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Architecture Skill

Provides architectural guidance for system design decisions, including:

ADR (Architecture Decision Records): Structured format for recording design decisions with context, options, and rationale
System Design Checklist: Scalability, reliability, observability, security considerations
Architecture Patterns: Microservices, event-driven, layered, hexagonal
API Design: RESTful conventions, versioning, pagination, error handling

When Loaded

This skill is automatically injected when working with:

/cc-best:lead — Technical design phase
architect agent — System architecture decisions
planner agent — Task breakdown and complexity analysis

Key Principles

Simplicity first — Choose the simplest architecture that meets requirements
Document decisions — Every significant choice gets an ADR
Separation of concerns — Clear boundaries between components
Design for failure — Graceful degradation and circuit breakers

Want to see if davepoon/architecture 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.