engineer-command

Guide for creating effective flowai commands. Use when users want to create a new command, or update an existing one, that extends flowai with specialized knowledge, workflows or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).

Quality

68%

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-command/SKILL.md

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 body is well-structured, actionable, and follows its own progressive-disclosure advice with concrete commands and a validated packaging workflow. Its weakest area is conciseness, with some conceptual padding and redundant benefit notes that could be cut.

Suggestions

Trim the 'About flowai Commands' conceptual intro and the per-resource 'Benefits'/'Note' lines, which restate what flowai already knows about scripts, references, and assets.

Add an explicit copy-paste invocation for scripts/validate_command.ts (and mention command_scripts_test.ts) so all bundle scripts are reachable from the body, closing the progressive-disclosure gap.

Collapse the duplicated guidance between the 'Progressive Disclosure Design Principle' section and the 'References' best-practice notes, which cover overlapping ground on keeping SKILL.md lean.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance, but the conceptual 'About flowai Commands' intro and the per-resource-type Benefits/Notes paragraphs explain things flowai already knows and could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready deno commands, a concrete IDE path table, detection markers, and worked examples (pdf-editor, webapp-builder, big-query); minor gaps such as the validate script not being given as an explicit invocation.	4 / 5
Workflow Clarity	A clear 6-step creation process with documented skip-conditions and an explicit validate->fix->retry feedback loop in the packaging step; planning steps lack explicit checkpoints, keeping it just below 5.	4 / 5
Progressive Disclosure	SKILL.md is an overview with well-signaled one-level-deep references (references/workflows.md, references/output-patterns.md) and a clear three-level loading rationale; minor gap: scripts/validate_command.ts and command_scripts_test.ts exist in the bundle but are not explicitly pointed to from the body.	4 / 5
	Total	15 / 20 Passed

Description

70%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 third-person, has an explicit 'Use when' trigger clause, and clearly distinguishes this as a command-authoring skill. It is strong on completeness and distinctiveness but the 'what' is slightly generic and trigger-term coverage lacks synonyms.

Suggestions

Make the 'what' more concrete by listing 1-2 specific authoring actions (e.g. 'scaffold, edit, validate, and package flowai commands') instead of the generic 'Guide for creating'.

Add natural synonym triggers users might say, such as 'build a command', 'add a new flowai skill', or 'scaffold a command', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('creating effective flowai commands') and two concrete actions ('create a new command, or update an existing one'), but the actions are high-level and coverage of what command creation entails is not comprehensive.	3 / 5
Completeness	Explicitly answers both 'what' ('Guide for creating effective flowai commands') and 'when' ('Use when users want to create a new command, or update an existing one...'); the 'what' is slightly generic which keeps it just below a 5.	4 / 5
Trigger Term Quality	Natural trigger phrases like 'create a new command' and 'update an existing one' align well with what a user would actually say, though a few synonymous phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The command-creator meta-niche is clearly distinct from domain skills, with only minor overlap risk against other tooling/authoring skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: korchasa/flowai-plugins
Path: plugins/flowai-devtools/skills/engineer-command/SKILL.md
Commit: ad81ae6

Reviewed: 6 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.