CtrlK
BlogDocsLog inGet started
Tessl Logo

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, execution, quality gates, and LLM-specific patterns.

79

0.95x
Quality

71%

Does it follow best practices?

Impact

87%

0.95x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is senior-engineering in jdrhyne/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 skill is a well-structured, concise principles document with a clear lifecycle and a validation checklist. Its weakness is actionability: many items are aphorisms or reflective prompts rather than concrete, executable senior-engineering procedures.

Suggestions

Convert reflective questions ('What does success look like?') into concrete directives or mini-procedures (e.g. 'Write a one-line acceptance criterion and a verification command before coding').

Add 1-2 concrete worked checkpoints to 'During Build' (e.g. an example commit cadence or a sample 'instrument as you build' log statement) to lift actionability.

DimensionReasoningScore

Conciseness

The body is lean bullet-form prose organized into tight sections, assuming Claude's competence; only minor aphoristic padding ('Maintainability beats elegance', 'Documentation is a gift to future-you') could be trimmed.

4 / 5

Actionability

Much of the guidance is high-level heuristics and reflective questions ('What does success look like?') rather than concrete, executable steps; for an instruction-only skill the directives lack specific actionable detail.

3 / 5

Workflow Clarity

A clear lifecycle sequence (Before Writing Code → During Build → Quality Gates) with an explicit validation gate (the 'Before Declaring Done' checklist) is present, with only minor validation gaps.

4 / 5

Progressive Disclosure

No bundle files exist; the ~140-line body is well-organized into clearly headed sections, but it exceeds the 50-line simple-skill threshold and inlines all content with no external references, so it falls just short of a 5.

4 / 5

Total

15

/

20

Passed

Description

75%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 purpose and trigger conditions with natural keywords, scoring well on completeness. Its main weakness is overlap risk with code-review and planning skills and somewhat abstract rather than concrete capability wording.

Suggestions

Narrow the trigger scope (e.g. 'Load when guiding multi-step engineering work that needs planning, quality gates, or LLM orchestration — not for routine edits') to reduce overlap with code-review/planning skills.

Replace abstract topic lists ('planning, execution, quality gates') with a concrete capability verb or two (e.g. 'plans work, sequences quality gates, orchestrates multi-agent builds').

DimensionReasoningScore

Specificity

Names the domain ('building software like a senior engineer') and lists covered areas ('planning, execution, quality gates, and LLM-specific patterns'), but these are abstract topics rather than concrete actions, fitting between the 'names domain and 1-2 concrete actions' and 'actions minimal/generic' anchors.

3 / 5

Completeness

Explicitly answers both what ('Engineering principles for building software like a senior engineer') 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

'tackling non-trivial development work, architecting systems, reviewing code, or orchestrating multi-agent builds' provides good natural keyword coverage a user would say, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The triggers are broad ('non-trivial development work' covers most dev) and 'reviewing code' / 'architecting systems' overlap with dedicated code-review and planning skills, so it could trigger for the wrong skill.

3 / 5

Total

15

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bap-jorkim/agent-skills-fork-feb-25
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.