engineer-hook

Create and configure event hooks/plugins that manage agent behavior — command filtering, auditing, automation, script-based blocking of actions. Use when you need to create or configure a hook. Works across IDEs (Cursor, Claude Code, OpenCode).

Quality

75%

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-hook/SKILL.md

Quality

Content

75%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-organized, actionable reference with executable examples per IDE and clear navigation to bundled reference files. Its weaknesses are the heavy inline event-mapping table and shallow validation guidance in the workflow for security-sensitive hooks.

Suggestions

Move the large Cross-IDE Event Mapping table into a reference file and keep only a condensed representative subset inline, with a pointer.

Strengthen the workflow's test step into an explicit feedback loop (e.g. trigger a known-blocked command, confirm exit 2 / block message, fix, re-run) since these hooks gate destructive actions.

Add a short executable example for at least one non-command Claude Code hook type (e.g. prompt-based) so all four types are exemplified.

Dimension	Reasoning	Score
Conciseness	The body is dense but mostly high-value tables and executable snippets with little concept padding; the large inline cross-IDE event-mapping table is reference data that could arguably live in a reference file, keeping it just below 5.	4 / 5
Actionability	Provides copy-paste-ready config JSON, bash guard scripts, and a TypeScript plugin covering the common "block rm -rf" case across all three IDEs; minor gaps are the unexemplified Claude Code HTTP/prompt/agent hook types, so not a 5.	4 / 5
Workflow Clarity	The 7-step Main Workflow is clearly sequenced and includes a final "Test: Verify the hook fires correctly" step; validation is present but light (no explicit fix-and-retest feedback loop), matching the 4 anchor rather than 5.	4 / 5
Progressive Disclosure	Overview points to three real one-level-deep reference files (hooks_api.md, claude_code_hooks_api.md, opencode_plugins_api.md) and a real asset (hook_template.sh), each clearly signaled via "For … see [file]"; the inline 20+ row event-mapping table is the main organization gap versus a 5.	4 / 5
	Total	16 / 20 Passed

Description

75%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 specific and well-structured, clearly stating both capability and trigger conditions with concrete action verbs and IDE names. The main weakness is the slightly circular "Use when you need to create or configure a hook" trigger, which could name richer user-facing scenarios.

Suggestions

Expand the "Use when" clause with concrete user scenarios (e.g. "Use when the user wants to block dangerous commands, audit tool calls, or auto-format files after edits").

Add common synonyms/users phrases such as "guardrail", "pre-tool hook", or file/IDE-specific triggers to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (event hooks/plugins) and lists several concrete actions — "command filtering, auditing, automation, script-based blocking of actions" — with only minor coverage gaps, fitting the 4 anchor better than the 5 anchor's comprehensive coverage.	4 / 5
Completeness	Explicitly answers both what (create/configure hooks managing agent behavior) and when ("Use when you need to create or configure a hook"), but the when-clause is somewhat circular and could be more specific, matching the 4 anchor.	4 / 5
Trigger Term Quality	Includes natural terms a user would say ("hook", "plugin", "create or configure", plus IDE names Cursor/Claude Code/OpenCode); good coverage though a few synonyms are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (agent event hooks/plugins across specific IDEs) with distinct triggers; minor overlap risk with general config/automation skills keeps it just below 5.	4 / 5
	Total	16 / 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: 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.