Ready to supercharge your AI agents?

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

Get Started Free →

Deep Agents Architecture Decisions · majiayu000 | DecimalAI

agent toolingby majiayu000

Deep Agents Architecture Decisions

majiayu000/deepagents-architecture

Source majiayu000/claude-skill-registry ↗License MIT

Guides architectural decisions for Deep Agents applications.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/19/2026

What it changes

Passed 22 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill100%

Checks it passed that the model alone missed

Selects FilesystemBackend.
Recommends CompositeBackend.
Recommends create_react_agent.

and 15 more in the full report

12 fixed10 passed either way0 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +20%
Agent turns: 0%
Response time: -56%

Model gemini-3.6-flashMeasured 8/19/2026v122 of 22 cases passed with skill

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/majiayu000-deepagents-architecture/SKILL.md https://app.decimal.ai/s/majiayu000-deepagents-architecture/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-deepagents-architecture, 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/majiayu000-deepagents-architecture/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-deepagents-architecture

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-deepagents-architecture/SKILL.md https://app.decimal.ai/s/majiayu000-deepagents-architecture/SKILL.md

Raw file: /s/majiayu000-deepagents-architecture/SKILL.md ↗ · machine-readable summary at /s/majiayu000-deepagents-architecture.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

Which middleware handles task planning and file operations in the built-in stack?

What was checked, without and with the skill
Checked	Without skill	With skill
Names TodoListMiddleware for task planning.	Missed	Passed
Names FilesystemMiddleware for file operations.	Missed	Passed

case-16 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md223 linessingle file

Deep Agents Architecture Decisions

When to Use Deep Agents

Use Deep Agents When You Need:

Long-horizon tasks - Complex workflows spanning dozens of tool calls
Planning capabilities - Task decomposition before execution
Filesystem operations - Reading, writing, and editing files
Subagent delegation - Isolated task execution with separate context windows
Persistent memory - Long-term storage across conversations
Human-in-the-loop - Approval gates for sensitive operations
Context management - Auto-summarization for long conversations

Consider Alternatives When:

Scenario	Alternative	Why
Single LLM call	Direct API call	Deep Agents overhead not justified
Simple RAG pipeline	LangChain LCEL	Simpler abstraction
Custom graph control flow	LangGraph directly	More flexibility
No file operations needed	`create_react_agent`	Lighter weight
Stateless tool use	Function calling	No middleware needed

Backend Selection

Backend Comparison

Backend	Persistence	Use Case	Requires
`StateBackend`	Ephemeral (per-thread)	Working files, temp data	Nothing (default)
`FilesystemBackend`	Disk	Local development, real files	`root_dir` path
`StoreBackend`	Cross-thread	User preferences, knowledge bases	LangGraph `store`
`CompositeBackend`	Mixed	Hybrid memory patterns	Multiple backends

Backend Decision Tree

Need real disk access?
├─ Yes → FilesystemBackend(root_dir="/path")

Track record

Benchmark

22 / 22

test cases passed, vs 10 / 22 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 v4 — 8/3/2026

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

majiayu000 / claude-skill-registry

skills/agent/deepagents-architecture/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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

Ready to supercharge your AI agents?

See it in action

What's inside

Deep Agents Architecture Decisions

When to Use Deep Agents

Use Deep Agents When You Need:

Consider Alternatives When:

Backend Selection

Backend Comparison

Backend Decision Tree

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills