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

76%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./prompts/senior-engineering/SKILL.md

Quality

Content

85%

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

The body is a well-structured, token-efficient set of senior-engineering principles with a clear phased workflow and explicit quality-gate validation checkpoints. Its main weakness is that much of the guidance is abstract principle rather than concrete executable instruction, capping actionability.

Suggestions

Convert the most-used abstract principles into concrete, checkable steps (e.g., under "Always Have a Runnable State" add an explicit commit-cadence command or checkpoint trigger).

Add one concrete worked micro-example for the highest-value sections (e.g., a tiny "Define Done" acceptance-criteria template or a sample Quality Gates command sequence) to lift actionability without much length.

Pair each LLM-orchestration principle with a specific handoff contract snippet (inputs/outputs/success criteria) so the guidance is copy-paste ready rather than aphoristic.

Dimension	Reasoning	Score
Conciseness	The body is lean bullet-pointed principles with no padding and no explanation of concepts Claude already knows ("Context window is your RAM", "Boring > Clever", "Optimize for Delete"), assuming competence and earning every token, matching the lean-and-efficient anchor.	3 / 3
Actionability	Concrete guidance exists in places (the Quality Gates checkbox checklist, the "30 mins from runnable" threshold, the Define-Done prompts), but many sections are abstract aphorisms ("Leave It Better", "Strong Opinions, Weakly Held") with no executable steps, fitting the some-concrete-guidance-but-incomplete anchor.	2 / 3
Workflow Clarity	A clear phased sequence (Before Writing Code -> During Build -> Quality Gates) with an explicit validation checklist ("Linter passes", "Type checker passes", "Tests pass") and recovery guidance ("Fail Fast, Surface Early"; "Read Errors Carefully") matches the clear-sequence-with-validation-and-checklists anchor.	3 / 3
Progressive Disclosure	A single well-organized SKILL.md with clean section navigation and no reference material that needs splitting out; per the under-50-line / no-external-references guidance, well-organized sections with no needed references satisfy the top anchor.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 cleanly answers both what the skill does and when to load it with an explicit trigger clause, but its capabilities read as abstract domains rather than concrete actions and lean on some jargon, limiting specificity and trigger naturalness. It is competent but could be sharpened with more concrete verbs and plainer trigger language.

Suggestions

Replace abstract domain labels ("quality gates", "LLM-specific patterns") with concrete actions a user would name, e.g. "run lint/type/test checks before declaring done" and "delegate work across subagents with clear handoffs".

Soften jargon in the trigger clause by adding natural phrasings users actually say (e.g. "planning a feature", "reviewing a PR", "coordinating multiple agents") alongside the existing terms.

Tighten distinctiveness by foregrounding the senior-judgment + LLM-orchestration niche early so it is less likely to collide with generic coding skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several activity categories ("planning, delivery, quality gates, and LLM-specific patterns"; "architecting systems, reviewing code, orchestrating multi-agent builds") but these are abstract domains rather than the concrete discrete actions the score-3 anchor requires.	2 / 3
Completeness	Explicitly states both what it does ("Engineering principles for building software... Covers planning, delivery, quality gates, and LLM-specific patterns") and when to load it ("Load when tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds"), satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Includes natural terms users would say ("reviewing code", "architecting systems") but mixes in jargon ("quality gates", "LLM-specific patterns", "orchestrating multi-agent builds") and misses common phrasing variations, matching the some-relevant-keywords anchor rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The "senior engineering" framing is somewhat specific and the LLM-orchestration angle narrows it, but the broad software-building scope could still overlap with general coding or architecture skills, fitting the somewhat-specific-but-overlapping anchor.	2 / 3
	Total	9 / 12 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
Commit: a4d31ad

Reviewed: 11 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.