agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents perform most implementation work and humans enforce quality and risk controls.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.kiro/skills/agentic-engineering/SKILL.md

Quality

Content

75%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.

The content is actionable, well-sequenced, and efficiently organized with concrete examples and an embedded eval-first feedback loop. The main improvements are removing the description-redundant opening and "When to Use" restatement, and adding one concrete eval example to the otherwise generic loop.

Suggestions

Remove the opening "Use this skill for..." sentence and the "When to Use This Skill" section since both restate the frontmatter description, recovering token budget.

Add one concrete eval example (e.g., a small test snippet and its baseline-vs-after delta) to the Eval-First Loop so the workflow is copy-paste ready rather than generic steps.

Add an explicit per-unit validation checkpoint to the Task Decomposition workflow (e.g., "verify Unit N passes its done-condition before starting Unit N+1") to close the workflow-clarity gap.

Dimension	Reasoning	Score
Conciseness	The body is well-organized with bullets and examples rather than padded prose, but the opening line duplicates the description and the "When to Use This Skill" section restates points already covered, leaving minor trim opportunities.	4 / 5
Actionability	Concrete guidance is present throughout—the 15-minute unit rule, model-tier examples (Haiku/Sonnet/Opus with specific use cases), a review checklist, and a cost-tracking template—though the eval-first loop example stays at generic steps without a concrete eval snippet.	4 / 5
Workflow Clarity	The eval-first loop is a clear sequenced workflow with an embedded validation/feedback loop (re-run evals, compare deltas, check regressions) plus a review checklist, but decomposition lacks per-unit validation checkpoints, leaving a minor gap.	4 / 5
Progressive Disclosure	The single-file skill is well-structured into clearly headed sections with an "Integration with Other Skills" pointer block; no bundle files exist, and the content is appropriately self-contained, with only minor organization refinement possible.	4 / 5
	Total	16 / 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.

The description clearly states both what the skill does and when to use it with concrete, distinct triggers, placing it in the strong range. Minor gains are possible by adding natural synonyms and tightening the conceptual capability language into more granular actions.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities—"eval-first execution", "decomposition", and "cost-aware model routing"—matching the anchor for several specific actions with minor coverage gaps, though the phrasing stays somewhat conceptual rather than fully granular.	4 / 5
Completeness	It explicitly answers both what ("Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing") and when ("Use when AI agents perform most implementation work...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The "Use when AI agents perform most implementation work and humans enforce quality and risk controls" clause surfaces natural phrases a user might say, but lacks common synonyms (e.g., "agent workflows", "model tier selection") that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	The agentic-engineering niche with eval-first and model-routing triggers is mostly distinct, but the broad engineering framing has minor overlap risk with related dev-workflow skills like tdd-workflow and coding-standards.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: .kiro/skills/agentic-engineering/SKILL.md
Commit: d8409a4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.