senior-engineering

Engineering principles for building software like a senior engineer. Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds. Covers planning, delivery, quality gates, and LLM-specific patterns.

Quality

81%

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

Quality

Content

82%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 tight, well-structured principles skill that respects token budget and provides concrete directives plus an explicit quality-gate checklist. As an instruction-only skill it lacks executable code and tightly coupled per-step validation feedback loops, which cap actionability and workflow_clarity just below the top.

Dimension	Reasoning	Score
Conciseness	Lean bullet-driven content with no padding of concepts Claude already knows; pithy lines like "Boring > Clever" and "Observability is a feature, not an afterthought" earn their place rather than inflate, matching the lean/efficient anchor.	5 / 5
Actionability	Concrete directives ("Never be more than 30 mins from something that compiles/runs", "Add logging/metrics while coding", "Single responsibility per agent") and an explicit Quality Gates checklist give mostly actionable guidance; it is principle-based rather than step-based, so it stops short of 5.	4 / 5
Workflow Clarity	A clear before/during/after progression (Before Writing Code → During Build → Quality Gates) with an explicit "Before Declaring Done" checklist and a "Verify, Don't Trust" section provides most checkpoints; validation is present but somewhat distributed rather than a tight per-step feedback loop, so not 5.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Safety Boundaries, Before Writing Code, During Build, Quality Gates, LLM Orchestration, Ownership) in a single appropriately-sized file with no need for external references; it is over 50 lines and lacks the one-level-deep reference splitting that would warrant a 5.	4 / 5
	Total	17 / 20 Passed

Description

80%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 both capability and explicit load triggers with natural phrasing. Its main weakness is breadth: the "senior engineering principles" niche overlaps with general coding skills and the listed actions are domains rather than concrete operations.

Suggestions

Sharpen the capability list from domains to concrete actions (e.g., "plans work into testable units, defines interface contracts before implementation, adds validation checkpoints") to lift specificity.

Narrow the trigger scope or add a distinguishing qualifier to reduce overlap with general development skills.

Add a couple of natural synonyms users might say (e.g., "refactoring", "designing systems", "code review") to round out trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several specific areas — "architecting systems, reviewing code, or orchestrating multi-agent builds" plus "planning, delivery, quality gates, and LLM-specific patterns" — going beyond 1-2 actions, though they are domains rather than concrete operations, so it stops short of 5.	4 / 5
Completeness	Explicitly answers both what ("Engineering principles for building software... Covers planning, delivery, quality gates, and LLM-specific patterns") and when ("Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would say ("non-trivial development work, architecting systems, reviewing code, orchestrating multi-agent builds") give good coverage; a few common synonyms are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	The "senior engineering" framing and multi-agent orchestration give it a partial niche, but it is broad enough to overlap with general development skills, so it is not clearly distinct (not a 4).	3 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jdrhyne/agent-skills
Path: prompts/senior-engineering/SKILL.md
Commit: 439cd3a

Reviewed: 17 days 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.