llm-gate

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Quality

72%

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 ./skills/llm-gate/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.

A well-structured, actionable skill body with concrete copy-paste JSON examples, a clear setup sequence, and a validation reminder. Main gaps are fragment-vs-complete example wrappers, the testing checkpoint being separated from the workflow rather than inline, and a body length that could benefit from offloading examples to a reference file.

Suggestions

Make every example gate a complete hooks.json snippet (full PreToolUse wrapper) rather than a bare hook object, so each is directly copy-pasteable.

Promote 'Test hooks before deploying' into the Setup Guide as an explicit final step with a feedback loop (e.g. '6. Test: run a sample gated operation; if it blocks incorrectly, adjust the prompt and re-test').

Consider moving the Example Gates and Agent Hooks blocks into a references/ file (e.g. EXAMPLES.md) and linking from the body, to reduce inline length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude's competence, and avoids explaining concepts Claude already knows — code examples and rules carry the weight with minimal padding. Not a 5 because the 'How Prompt Hooks Work' numbered breakdown and the Setup Guide restate some information that could be tightened.	4 / 5
Actionability	Provides concrete, copy-paste-ready JSON hook examples and a concrete 5-step setup guide with model/timeout specifics. Not a 5 because most example gates are hook-object fragments rather than complete hooks.json wrappers (only the first example is fully wrapped), leaving a minor gap for direct reuse.	4 / 5
Workflow Clarity	The Setup Guide gives a clear 5-step sequence (choose operations, write prompt, pick model, set timeout, add to hooks.json) and the Rules include a validation checkpoint ('Test hooks before deploying to avoid blocking workflows'). Not a 5 because the validation/testing checkpoint sits in a separate Rules section rather than inline as an explicit workflow step with a feedback loop.	4 / 5
Progressive Disclosure	Content is well-organized into clearly labeled sections (Trigger, How Prompt Hooks Work, Example Gates, Agent Hooks, Setup Guide, Rules) with no nested references and easy navigation. Not a 5 because the body exceeds ~50 lines with several full code examples that, for a skill of this size, could be split into a reference file; there are no bundle files present.	4 / 5
	Total	16 / 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.

A solid description that clearly states both what the skill does and when to use it, with good natural trigger terms and a distinct prompt-hook niche. Its main weakness is the when clause being generic ('intelligent guardrails') rather than concrete trigger phrases, and the action list being narrow variants of validation.

Suggestions

Replace the generic 'Use to set up intelligent guardrails' with concrete trigger phrases, e.g. 'Use when setting up commit message validation, enforcing code conventions beyond linters, or adding AI guardrails to operations'.

Broaden the action list beyond variants of 'validates' to show distinct capabilities, e.g. 'Validates commit messages, blocks destructive commands, prevents secret leaks, and enforces conventions before operations'.

Add common synonyms/file mentions users might say (e.g. 'hooks.json', 'conventional commits', 'pre-commit checks') to strengthen trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (prompt hooks) and lists a couple of concrete actions ('Validates commit messages, code patterns, and conventions using AI before allowing operations'), but all actions are variants of 'validates X' rather than a comprehensive, distinct set of capabilities — matching the anchor that names the domain with 1-2 concrete actions. Not a 4 because coverage is narrow rather than 'several specific actions with minor gaps'.	3 / 5
Completeness	Clearly states what it does ('LLM-powered quality verification using prompt hooks... Validates... using AI before allowing operations') and provides an explicit when clause ('Use to set up intelligent guardrails'), matching the anchor where both what and when are present but when could be more specific. Not a 5 because the trigger clause is generic rather than concrete trigger phrases; not capped at 3 because an explicit 'Use to...' trigger clause is present.	4 / 5
Trigger Term Quality	Includes several natural terms a user would say — 'commit messages', 'code patterns', 'conventions', 'guardrails', 'prompt hooks' — giving good keyword coverage. Not a 5 because common synonyms and concrete file/extension triggers are missing, and 'intelligent guardrails' is somewhat generic.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (prompt hooks for AI quality gates) with distinct triggers, giving mostly-distinct positioning with only minor overlap risk against closely related guardrail/hook skills. Not a 5 because 'intelligent guardrails' and 'quality verification' are broad enough to overlap slightly with general linting/convention skills.	4 / 5
	Total	15 / 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: rohitg00/pro-workflow
Path: skills/llm-gate/SKILL.md
Commit: 7f7209d

Reviewed: 3 days 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.