engineer-rule

Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).

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

71%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 highly actionable, well-sequenced skill body with concrete templates and a validation step, but it is longer than necessary due to cross-IDE example duplication and fails to route the duplicated example library to references/examples.md, weakening both conciseness and progressive disclosure.

Suggestions

Move the per-IDE worked examples (Error Handling, React Patterns, Architecture) into references/examples.md and link to it from SKILL.md instead of inlining each variant, removing the duplication that inflates the body.

After relocating examples, trim the body toward the stated <50-line ideal by keeping only one representative frontmatter template per IDE and pointing to examples.md for the rest.

Add a brief inline note on what a passing vs. failing validate_rule.ts run looks like, so the verification checkpoint has a visible feedback loop rather than relying on the script alone.

Dimension	Reasoning	Score
Conciseness	Largely efficient and table-driven assuming Claude's competence, but the ~345-line body repeats the same Error Handling and React Patterns examples across Cursor and Claude Code variants and duplicates content also present in references/examples.md, adding padding that could be trimmed.	3 / 5
Actionability	Fully executable guidance: complete frontmatter templates, exact file paths per IDE, copy-paste code examples, and a concrete validation command (`deno run -A scripts/validate_rule.ts`) covering the common cases.	5 / 5
Workflow Clarity	Clear three-phase sequence (Discovery → Implementation → Verification) with an explicit validation step and a verification checklist; minor gap is that the checklist's validation step relies on the script rather than showing expected pass/fail handling inline.	4 / 5
Progressive Disclosure	Good internal structure with tables and sections, and the body's scripts/validate_rule.ts reference resolves to a real bundle file, but the worked examples are inlined in SKILL.md AND duplicated in references/examples.md which is never linked from the body — content that belongs in a separate file is inline and references are not clearly signaled.	3 / 5
	Total	15 / 20 Passed

Description

92%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, well-targeted description that names concrete actions, provides an explicit 'Use when' clause with natural trigger phrases, and carves out a distinct multi-IDE rule-creation niche. Only minor trigger-synonym gaps keep it from a perfect trigger-term score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating persistent AI rules', 'add coding standards', 'set up project conventions', 'configure file-specific patterns', 'ask about rules placement' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (guide for creating persistent AI rules) and when ('Use when users want to create a rule, add coding standards... or ask about rules placement') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('create a rule', 'add coding standards', 'set up project conventions', 'rules placement') with good synonym coverage; just shy of fully comprehensive because a few common phrasings (e.g. 'conventions', 'linting rules') are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche — persistent AI rules across named IDEs (Cursor, Claude Code, OpenCode) — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	19 / 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: korchasa/flowai-plugins
Path: plugins/flowai-devtools/skills/engineer-rule/SKILL.md
Commit: b4ba256

Reviewed: ~22 hours 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.