Ready to supercharge your AI agents?

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

Get Started Free →

Agentic Engineering · loulanyue | DecimalAI

agent toolingby loulanyue

Agentic Engineering

loulanyue/agentic-engineering

Source loulanyue/awesome-claude-notes ↗License MIT

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/22/2026

What it changes

Passed 22 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill100%

Checks it passed that the model alone missed

Decomposes the feature into 15-minute work units
Re-runs evaluations and compares delta metrics against baseline signatures
Escalates to a higher model tier only when lower tiers exhibit a clear reasoning gap

and 10 more in the full report

7 fixed15 passed either way0 still failing0 broke

Pass-rate lift: +32 pp
Tokens: -30%
Agent turns: 0%
Response time: -50%

Model gemini-3.6-flashMeasured 8/22/2026v622 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/loulanyue-agentic-engineering/SKILL.md https://app.decimal.ai/s/loulanyue-agentic-engineering/SKILL.md

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

decimalai skills add loulanyue-agentic-engineering

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

curl -fsSL --create-dirs -o .claude/skills/loulanyue-agentic-engineering/SKILL.md https://app.decimal.ai/s/loulanyue-agentic-engineering/SKILL.md

Raw file: /s/loulanyue-agentic-engineering/SKILL.md ↗ · machine-readable summary at /s/loulanyue-agentic-engineering.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Before letting an AI coding agent modify a complex legacy codebase to add a feature, what is the initial step required to establish a measurement baseline?

What was checked, without and with the skill
Checked	Without skill	With skill
Runs baseline capability and regression evaluations to capture failure signatures prior to execution	Missed	Passed

case-09 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md64 linessingle file

Agentic Engineering

Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.

Operating Principles

Define completion criteria before execution.
Decompose work into agent-sized units.
Route model tiers by task complexity.
Measure with evals and regression checks.

Eval-First Loop

Define capability eval and regression eval.
Run baseline and capture failure signatures.
Execute implementation.
Re-run evals and compare deltas.

Task Decomposition

Apply the 15-minute unit rule:

each unit should be independently verifiable
each unit should have a single dominant risk
each unit should expose a clear done condition

Model Routing

Haiku: classification, boilerplate transforms, narrow edits
Sonnet: implementation and refactors
Opus: architecture, root-cause analysis, multi-file invariants

Session Strategy

Continue session for closely-coupled units.
Start fresh session after major phase transitions.
Compact after milestone completion, not during active debugging.

Review Focus for AI-Generated Code

Prioritize:

Track record

Benchmark

22 / 22

test cases passed, vs 15 / 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

loulanyue / awesome-claude-notes

docs/ja-JP/skills/agentic-engineering/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v6

Other skills for the same job

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

Agentic Engineering

Operating Principles

Eval-First Loop

Task Decomposition

Model Routing

Session Strategy

Review Focus for AI-Generated Code

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills