engineer-skill

Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).

Quality

76%

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-skill/SKILL.md

Quality

Content

73%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 well-structured, actionable authoring guide with an exemplary gated workflow and clean progressive-disclosure references. Its main weakness is verbosity in a few explanatory sections that add token cost beyond what the concrete guidance requires.

Suggestions

Tighten or relocate the "Priming" section into a reference file; its multi-paragraph prose is the largest conciseness cost in the body.

Condense the token-budget blockquote under Constraints to the rule plus one example, moving the validator-context detail to references.

Move the repeated pattern code blocks (Template/Examples/Workflow/Conditional/Feedback Loop) into the existing references/output-patterns.md, keeping only a one-line pointer each in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tables, concrete commands, and compact examples, but extended prose sections ("Priming: Output Shape Teaches The Agent" and the long token-budget blockquote) explain reasoning at length that could be tightened without losing the point.	3 / 5
Actionability	Provides copy-paste-ready commands ("deno run -A scripts/validate_skill.ts", "deno run -A scripts/init_skill.ts", "wc -c <SKILL.md>"), concrete IDE path tables, and specific templates, with only minor gaps where illustrative pattern blocks are not executable code.	4 / 5
Workflow Clarity	A clear six-phase creation process (Discovery → Design → Implementation → Verification → Packaging → Iterate) with an explicit BLOCKING validation gate ("do NOT finish until it exits 0"), a fix-and-re-run feedback loop, and checklists, matching the anchor for explicit validation steps and feedback loops.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with well-signaled, verified one-level-deep references ("references/workflows.md", "references/output-patterns.md") and bundled scripts, but substantial inline sections (Priming, Common Patterns) that could arguably live in references keep it just short of the cleanly-split anchor.	4 / 5
	Total	16 / 20 Passed

Description

78%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 cleanly satisfies the mandatory WHAT + WHEN structure with explicit, natural trigger phrases and a well-scoped niche. It is slightly generic in enumerating concrete capability actions and has minor overlap risk from the broader "best practices" trigger.

Suggestions

Replace abstract items like "ask about best practices" with more concrete capability verbs (e.g., "scaffold, validate, and package Agent Skills") to lift specificity.

Add a distinguishing keyword such as the ".skill" distribution format to sharpen distinctiveness from generic engineering skills.

Dimension	Reasoning	Score
Specificity	Names the domain ("creating effective Agent Skills (SKILL.md packages)") with a few concrete actions ("create a new skill, write a skill, author a SKILL.md"), but coverage is not comprehensive and several listed items ("ask about best practices") are trigger scenarios rather than concrete capability actions.	3 / 5
Completeness	Explicitly answers both WHAT ("Guide for creating effective Agent Skills (SKILL.md packages)") and WHEN ("Use when users want to create a new skill, write a skill, author a SKILL.md...") with concrete trigger phrases, matching the anchor for clear and explicit what + when.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ("create a new skill, write a skill, author a SKILL.md, ask about skill structure, best practices, or skill file format") with good keyword coverage, though a few synonyms or the .skill extension are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (skill/SKILL.md authoring) with distinct triggers and IDE qualifiers, but "ask about best practices" and "skill structure" are somewhat broad and could overlap with adjacent meta/engineering skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-devtools/skills/engineer-skill/SKILL.md
Commit: b4ba256

Reviewed: ~20 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.