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.
Install with Tessl CLI
npx tessl i github:supercent-io/skills-template --skill agentic-development-principles64
Quality
47%
Does it follow best practices?
Impact
89%
1.01xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/agentic-development-principles/SKILL.mdDiscovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (agentic AI development principles) but relies on abstract concepts rather than concrete actions Claude would take. The complete absence of a 'Use when...' clause significantly weakens its utility for skill selection, and the terminology leans toward conceptual jargon rather than natural user language.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about AI agent workflows, pair programming with AI, or best practices for working with coding assistants like Cursor or Copilot.'
Replace abstract principles with concrete actions, e.g., 'Guides breaking complex tasks into subtasks, managing context windows, and choosing appropriate abstraction levels when working with AI coding agents.'
Include more natural user terms like 'AI pair programming', 'coding assistant', 'Cursor', 'Copilot', 'agent prompting' that users would actually say.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agentic development) and lists some concepts (divide-and-conquer, context management, abstraction level selection, automation philosophy), but these are abstract principles rather than concrete actions Claude would perform. | 2 / 3 |
Completeness | Describes what the skill covers conceptually but completely lacks a 'Use when...' clause or any explicit trigger guidance. The 'when' is entirely missing, which per rubric guidelines caps this at maximum 2, but the 'what' is also weak (principles vs actions). | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'AI agents', 'AI coding tools', 'agentic development', but misses common user phrases like 'working with Cursor', 'AI pair programming', 'agent workflow', or 'coding assistant'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'agentic development' and 'AI agents' provides some distinction, but 'universal principles' and 'applicable to all AI coding tools' is broad enough to potentially conflict with other coding or development skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive guidance on agentic development principles with good workflow structure and validation checkpoints. However, it's overly verbose for a skill file, explaining concepts Claude already understands, and lacks executable code examples. The content would benefit from being more concise and splitting detailed sections into separate reference files.
Suggestions
Reduce verbosity by removing explanations of concepts Claude knows (e.g., 'Context (the AI's working memory)', basic automation definitions) - trust Claude's intelligence
Add executable code examples where applicable, such as actual scripts for HANDOFF.md generation or automation templates
Split detailed content (like the full automation levels table or abstraction guide) into separate reference files and link to them from the main skill
Remove or condense the 'Core concept' explanations that restate obvious principles - the examples and tables already convey the meaning
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places, explaining concepts Claude likely knows (e.g., what context drift is, basic automation concepts). Tables and examples add value but some sections could be tightened significantly. | 2 / 3 |
Actionability | Provides concrete examples and checklists, but lacks executable code. The HANDOFF.md template is actionable, but most guidance is conceptual rather than copy-paste ready commands or scripts. | 2 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with validation checkpoints (e.g., staged implementation pattern, verification checklist). The plan/execute mode distinction provides clear decision points for different scenarios. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and a quick reference summary, but it's monolithic - all content is inline rather than appropriately split into separate reference files. External references are only to outside resources, not internal skill documentation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
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.