CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic-development-principles

Universal principles for agentic development when collaborating with AI agents. Defines divide-and-conquer, context management, abstraction level selection, and an automation philosophy. Applicable to all AI coding tools.

64

1.01x
Quality

47%

Does it follow best practices?

Impact

89%

1.01x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/agentic-development-principles/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

85%

-1%

Webhook Notification Service: Implementation Plan

Staged task decomposition

Criteria
Without context
With context

Multiple distinct steps

100%

100%

Stage 1: Design/schema

100%

100%

Stage 2: Core logic

87%

100%

Stage 3: API/interface connection

100%

100%

Stage 4: Tests

40%

20%

Stage 5: Integration/refactor

62%

25%

Independent validation

100%

100%

Scoped steps

80%

100%

Concrete deliverable per step

100%

100%

Fix-in-isolation design

80%

90%

Non-monolithic start

100%

100%

100%

Session Transition: Backend Authentication Work

Context handoff documentation

Criteria
Without context
With context

HANDOFF.md created

100%

100%

Completed work section

100%

100%

Current status section

100%

100%

Next tasks section

100%

100%

Tried but failed section

100%

100%

Cautions section

100%

100%

Single-topic focus

100%

100%

Concise essentials only

100%

100%

Failed attempts include reason

100%

100%

Current status specificity

100%

100%

83%

3%

Database Layer Refactor: Migrate from Raw SQL to Query Builder

Plan-first execution and verification

Criteria
Without context
With context

Plan document created

100%

100%

Risky operations identified

30%

30%

Backup strategy mentioned

0%

0%

Staged execution

70%

100%

Tests written

100%

100%

Edge cases in tests

100%

100%

Self-verification summary

100%

100%

Diff/change review

100%

100%

No dangerous commands unguarded

100%

100%

Behavior preservation check

100%

100%

Repository
supercent-io/skills-template
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.