engineer-rule

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

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/flowai-devtools/skills/engineer-rule/SKILL.md

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.

The content is highly actionable with concrete templates, paths, and a validation command, and the workflow is clearly phased. Its main weaknesses are verbosity from duplicated examples and a missed progressive-disclosure link to the existing references/examples.md file.

Suggestions

Replace the inlined 'Example Rules' section with a brief pointer to references/examples.md to remove ~110 lines of duplication and improve token efficiency.

Add an explicit feedback loop to Phase 3: 'If validation fails, review the error, fix the rule, and re-run validation before proceeding.'

Consolidate the per-IDE format examples so each rule shape appears once with IDE-specific field differences noted inline, rather than repeating whole blocks for Cursor and Claude Code.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient reference material that assumes Claude's competence, but the 'Example Rules' section (~lines 229-345) duplicates near-identical rules already shown in 'Rule Format by IDE' and in references/examples.md, adding notable padding that could be tightened.	3 / 5
Actionability	Provides copy-paste-ready frontmatter templates per IDE, concrete file paths, glob patterns, and an executable validation command ('deno run -A scripts/validate_rule.ts'), covering the common cases fully.	5 / 5
Workflow Clarity	A clear three-phase process (Discovery, Implementation, Verification) with a verification command and checklist is present, but the error-recovery feedback loop ('if validation fails, fix and re-validate') is only implicit rather than spelled out.	4 / 5
Progressive Disclosure	Sections are well organized and scripts/validate_rule.ts is correctly referenced, but the large inlined 'Example Rules' section duplicates references/examples.md (which exists) and is never linked from the body, so content that belongs in a separate file is inlined and the reference is not signaled.	3 / 5
	Total	15 / 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: third-person, concise, and it explicitly answers both what the skill does and when to use it with natural trigger phrases. Minor room for improvement lies in broader synonym/extension coverage for trigger terms.

Dimension	Reasoning	Score
Specificity	Names the domain ('persistent AI rules') and lists several concrete rule types ('coding standards, project conventions, file-specific patterns') with the action 'Guide for creating', but the listed items are categories of output rather than distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states what the skill does ('Guide for creating persistent AI rules ...') and explicitly states when to use it ('Use when users want to create a rule, set up conventions, or ask where rules go'), satisfying both halves with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases ('create a rule, set up conventions, or ask where rules go') plus IDE names, giving good keyword coverage, though it lacks broader synonyms or file extensions that would push it to comprehensive.	4 / 5
Distinctiveness Conflict Risk	The 'persistent AI rules' niche with explicit IDE scoping (Cursor, Claude Code, OpenCode) and rule-specific triggers is a clear, distinct niche with minimal conflict risk against 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: korchasa/flowai-plugins
Path: plugins/flowai-devtools/skills/engineer-rule/SKILL.md
Commit: 78c7f17

Reviewed: 2 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.