Ready to supercharge your AI agents?

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

Get Started Free →

Plugin architect — measured AI agent skill | DecimalAI

kunanonj/cursor-plugin-create-agent-plugin-architect

SkillScore100Maintained

Plugin architecture specialist. Use when deciding the right component mix, structure, and metadata for a new Cursor plugin.

by kunanonj

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

Automatic

AI Engineer pack

decimalai skills pull kunanonj-cursor-plugin-create-agent-plugin-architect

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kunanonj-cursor-plugin-create-agent-plugin-architect/SKILL.md

Raw file: /s/kunanonj-cursor-plugin-create-agent-plugin-architect/SKILL.md ↗ · machine-readable summary at /s/kunanonj-cursor-plugin-create-agent-plugin-architect.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 40h ago

Yes — +68% lift-28% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-19%	0%
case-02	✗→✓	▲ Improved	-34%	0%
case-03	✗→✓	▲ Improved	-31%	0%
case-04	✗→✓	▲ Improved	-19%	0%
case-05	✗→✓	▲ Improved	-19%	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 — 8/2/2026

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

kunanonj / ai-skills-hub

skills/cursor-plugin-create-agent-plugin-architect/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Plugin architect

Design focused, maintainable Cursor plugins with the smallest viable component set.

Trigger

Use when planning a new plugin or refactoring an existing plugin's structure.

Workflow

Clarify plugin goal, users, and expected outcomes.
Recommend component mix (rules, skills, agents, commands, hooks, mcpServers) based on need.
Propose directory layout and manifest shape. The default output location for new plugins is ~/.cursor/plugins/local/<plugin-name>/.
Flag potential discoverability or metadata issues early.
Return a concrete implementation checklist.

Output

Recommended plugin architecture
Manifest and component decisions with rationale
Minimal implementation checklist

Want to see if kunanonj/cursor-plugin-create-agent-plugin-architect 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.