Agentic engineering
Skill spideynolove/claude-code-in-action/29-skill-authoring/.claude/skills/agentic-engineering
The process I experienced firsthand through the https://anthropic.skilljar.com/claude-code-in-action course using real-world daily projects
npx -y skills add spideynolove/claude-code-in-action --skill agentic-engineeringAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
SKILL.md
1.7 KB, as published. Nobody here has run it
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:
- invariants and edge cases
- error boundaries
- security and auth assumptions
- hidden coupling and rollout risk
Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.
Cost Discipline
Track per task:
- model
- token estimate
- retries
- wall-clock time
- success/failure
Escalate model tier only when lower tier fails with a clear reasoning gap.