Ready to supercharge your AI agents?

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

Get Started Free →

Python Architecture Skill · microsoft | DecimalAI

codingby microsoft

Python Architecture Skill

python-architecture

Source microsoft/apm ↗License MIT

[Python architect persona](../../../.apm/agents/python-architect.agent.md)

SkillScore95Maintained

Automatic

Coding pack

Last verified 8/2/2026

What it changes

Passed 21 of 22 test cases with the skill, and 6 of 22 without it.

Without skill27%

With skill95%

Checks it passed that the model alone missed

Prohibits leaving duplicated logic within sibling classes
Specifies using CommandLogger for contextual subcommand logging
Directs target lookups to target_catalog as the single canonical owner

and 25 more in the full report

15 fixed6 passed either way1 still failing0 broke

Pass-rate lift: +68 pp
Tokens: -25%
Agent turns: 0%
Response time: -37%

Model gemini-3.6-flashMeasured 8/2/2026v221 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/python-architecture/SKILL.md https://app.decimal.ai/s/python-architecture/SKILL.md

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

decimalai skills add python-architecture

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

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

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

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

What specific dual guardrail mechanism must be established whenever centralizing cross-cutting logic across `src/apm_cli/` modules?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies automated regression testing as the first guardrail component	Missed	Passed
Identifies static validation in scripts/lint-architecture-boundaries.sh as the second guardrail component	Missed	Passed

case-22 · gemini-3.6-flash · 8/2/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md20 linessingle file

Python Architecture Skill

Python architect persona

When to activate

Creating new Python modules or packages under src/apm_cli/
Refactoring class hierarchies or introducing base classes
Changes that touch 3+ files with shared logic patterns
Introducing new design patterns (Strategy, Observer, etc.)
Cross-cutting concerns (logging, auth, error handling)
Performance-sensitive paths (parallel downloads, large manifests)

Key rules

Follow existing patterns (BaseIntegrator, CommandLogger, AuthResolver) before inventing new ones
Prefer composition over deep inheritance
Push shared logic into base classes, not duplicated across siblings
One canonical owner per decision: route through the existing authority (target_catalog, AuthResolver/host_providers, runtime registry, CommandLogger, CompiledOutputWriter, deployment_ledger, install-outcome, neutral hook IR, BaseIntegrator); extend it, never fork it. Full rule: .apm/instructions/architecture.instructions.md
Lock every centralization with a dual guardrail: a regression test plus a static check in scripts/lint-architecture-boundaries.sh

Track record

Benchmark

21 / 22

test cases passed, vs 6 / 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 — 8/2/2026

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

microsoft / apm

.agents/skills/python-architecture/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v2

Other skills for the same job

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

microsoft/python-architectureActivate when creating new modules, refactoring class hierarchies, introducing design patterns, or making changes spanning 3+ files in the APM CLI codebase.Near-identical description+64 pp pass-rate lift

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

Python Architecture Skill

When to activate

Key rules

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills