engineer-hook

Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.

Quality

85%

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

86%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 strong, well-structured multi-IDE hooks skill with executable examples, clear cross-IDE mapping tables, and clean progressive disclosure into real reference files. The main improvement area is adding an explicit validation/feedback loop to the workflow for destructive command-blocking scenarios.

Suggestions

Add a validate-then-fix-then-retest feedback loop to the Main Workflow (e.g. after Test: "If the hook does not fire or misbehaves, inspect with --debug/Ctrl+O, fix config or script, and re-test until it fires correctly").

Trim the Overview paragraph that re-explains what hooks do, since Claude already understands hook semantics.

Surface the asset template earlier (e.g. a one-line pointer in the Cursor/Claude Code sections) so users reach hook_template.sh without scrolling to Resources.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly efficient (tables, compact code blocks, pointed tips) with only minor over-explanation such as the overview paragraph restating what hooks do, which could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready, executable examples for all three IDEs (guard.sh for Cursor/Claude Code, settings.json snippet, TypeScript plugin) covering the common blocking case, plus concrete config locations and exit-code semantics.	5 / 5
Workflow Clarity	A clear 7-step Main Workflow with IDE detection strategy and an explicit Test step is present, but it lacks a strong validate-then-fix-then-retest feedback loop for the security/destructive command-blocking use case, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references ("For ... see [hooks_api.md]"), an explicit Resources section, and content appropriately split between SKILL.md and three reference files plus one asset — all of which exist in the bundle.	5 / 5
	Total	18 / 20 Passed

Description

83%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 well-constructed description that explicitly covers what the skill does and when to use it, with concrete actions and decent trigger terms. The only notable issue is the second-person "you" phrasing in the Use-when clause, which violates the prescribed third-person voice.

Suggestions

Rewrite the trigger clause in third person to avoid the voice penalty, e.g. "Use when creating a new hook... configuring hooks/plugins... or implementing logic to block or modify agent actions".

Add a few more natural synonyms users might say (e.g. "intercept commands", "guard rails", "pre/post tool hooks") to broaden trigger-term coverage.

Tighten the broad scope phrase "manage agent behavior, command filtering, auditing, and automation" so the niche reads more distinctly from general automation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Creation and configuration", "command filtering, auditing, and automation", "blocking or modifying agent actions via scripts") matching the score-5 anchor, but the second-person "Use when you need to" triggers the voice penalty reducing specificity by 1.	4 / 5
Completeness	Clearly answers both what ("Creation and configuration of event hooks/plugins...") and when ("Use when you need to: (1)... (2)... (3)...") with explicit concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-term coverage ("event hooks/plugins", "formatting", "security checks", "configure hooks/plugins") that users would plausibly say, though a few common synonyms and concrete IDE-by-task phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	The hook/plugin + IDE-specific framing carves a clear niche with distinct triggers, though "manage agent behavior, command filtering, auditing, and automation" is broad enough to risk minor overlap with adjacent automation skills.	4 / 5
	Total	17 / 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-hook/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.