CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is tdg-personal/ai-first-engineering

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-organized instruction skill that assumes Claude's competence and avoids padding. Its main weakness is the lack of a sequenced workflow with validation checkpoints, and some sections lean on abstract principles over concrete executable steps.

Suggestions

Convert the abstract 'Process Shifts' principles into concrete directives an engineer can apply (e.g. 'Require an eval plan before implementation begins').

Add an explicit ordered workflow for applying the operating model — e.g. define acceptance criteria -> design agent-friendly boundaries -> review for behavior regressions -> require regression coverage -> validate before rollout.

Where review and testing standards are listed, add a brief validation checkpoint (e.g. 'Block merge until regression coverage for touched domains is green') to raise workflow clarity.

DimensionReasoningScore

Conciseness

Lean bullet-driven guidance with no padding and no explanation of concepts Claude already knows ('Planning quality matters more than typing speed', 'Avoid implicit behavior spread across hidden conventions'); every line earns its place, matching the lean/efficient anchor.

5 / 5

Actionability

Most sections give concrete directives ('Review for: behavior regressions, security assumptions...', 'required regression coverage for touched domains'), but several lines are abstract principles ('Planning quality matters more than typing speed') rather than executable guidance, keeping it just below fully actionable.

4 / 5

Workflow Clarity

Content is organized into logical topic sections but there is no sequenced multi-step process or validation checkpoints; the skill covers multiple concerns rather than a single unambiguous task, so the simple-skill exception does not lift it above 3.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed and is organized into clear, well-labeled sections (Process Shifts, Architecture, Code Review, Hiring, Testing), satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill provides and when to use it, with concrete trigger areas and a distinctive AI-first niche. Minor improvements would come from adding more natural synonyms and a slightly more exhaustive action list.

DimensionReasoningScore

Specificity

Names the domain ('Engineering operating model for teams where AI agents generate a large share of implementation output') and several concrete action areas ('setting team process, review gates, or ownership rules'), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because the actions are process areas rather than a comprehensive enumerated set.

4 / 5

Completeness

Explicitly answers both what ('Engineering operating model for teams where AI agents generate a large share of implementation output') and when ('Use when setting team process, review gates, or ownership rules for a codebase largely written by agents'), with concrete trigger phrases matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user might say ('team process', 'review gates', 'ownership rules', 'codebase largely written by agents'); good coverage but a few common synonyms (e.g. 'AI-generated code', 'agent-written code') are absent, so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The AI-agent-generated-code framing carves a clear niche with distinct triggers, but it retains minor overlap risk with general engineering-process and code-review skills, placing it just below the minimal-conflict anchor.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
affaan-m/ECC
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.