engineering-cost-review

Use when reviewing a blueprint (PRD, spec, implementation plan, design/architecture doc, or product scope and technical decisions from the current session) right after it is written or before implementation, to check whether its implementation cost is economical and rational. Not for reviewing already-implemented code.

Quality

84%

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

81%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 body is a highly actionable, well-sequenced review methodology with explicit validation gates, a triage framework, and worked examples. Its main weakness is conciseness: the core cost-minimization thesis is repeated across several sections and the motivational framing could be tightened.

Suggestions

Consolidate the repeated "does this minimize implementation cost in this stack" framing — keep it once in "Core lens" and trim the restatements in the intro bullets and "Why this skill exists".

Tighten "Why this skill exists" to the essential paradox without the discursive lead-in about user intuition, since the procedure already enforces the read-the-stack discipline.

Consider moving the four worked Examples into a separate REFERENCES file referenced from the body, which would both improve progressive_disclosure and reduce body length.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic-concept padding, but the central thesis ("does this minimize implementation cost in this stack") is restated across the intro bullets, "Why this skill exists", "Core lens", and the procedure, and the "Why" section is discursive; not a 4 because the repetition is noticeable rather than minor.	3 / 5
Actionability	For an instruction-only skill it gives fully actionable guidance: a 5-step review procedure, three per-decision sub-questions, four priority-ordered flag categories with explicit criteria, a copy-paste output template, and four worked examples covering common cases.	5 / 5
Workflow Clarity	Clear 5-step sequence with explicit validation gates ("Verify the stack — read, don't reason", "Don't flag without evidence") and a flag/pass/undecidable triage; no error-recovery feedback loop is needed because the skill is non-destructive and explicitly defers execution to the user.	5 / 5
Progressive Disclosure	A single self-contained file with no bundle references and clean section headers that make navigation easy; not a 5 because the skill exceeds 50 lines and the lengthy inline Examples section could arguably live in a separate file, so the "sections-only" exception does not fully apply.	4 / 5
	Total	17 / 20 Passed

Description

87%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 is well-crafted: it states a concrete purpose, fires on natural trigger terms covering multiple blueprint synonyms, explicitly defines when to use it, and draws a clear boundary against post-implementation review. Minor synonym gaps keep trigger term quality and specificity just below maximum.

Dimension	Reasoning	Score
Specificity	Names the concrete action ("check whether its implementation cost is economical and rational") with a comprehensive enumeration of blueprint artifact types and an explicit negative boundary; not a 5 because the action set is essentially review-plus-cost-check rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both what (check whether implementation cost is economical and rational) and when ("Use when reviewing a blueprint... right after it is written or before implementation") with concrete trigger phrases, plus a clear exclusion.	5 / 5
Trigger Term Quality	Strong natural-term coverage with synonyms ("blueprint", "PRD", "spec", "implementation plan", "design/architecture doc", "product scope"); not a 5 because common variants like "RFC", "tech spec", or "design doc" are absent and no file extensions apply.	4 / 5
Distinctiveness Conflict Risk	Clear niche (pre-implementation blueprint cost review) with distinct triggers and an explicit "Not for reviewing already-implemented code" boundary, giving minimal conflict risk with other skills.	5 / 5
	Total	18 / 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: choegyumin/agent-skills
Path: skills/engineering-cost-review/SKILL.md
Commit: a6a5aba

Reviewed: 4 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.