CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-hooks

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Concise and highly actionable content with executable examples and good organization. Weaknesses are the missing explicit validation feedback loop and the absence of the referenced bundle files.

Suggestions

Add an explicit validate->fix->retry checkpoint, e.g. "Run `echo '{...}' | ./hooks/validate.sh` and confirm exit code 0 before enabling the hook in settings.json."

Create the referenced ./references/hook-events.md, configuration.md, and security-patterns.md files so the progressive-disclosure structure is real, or remove the dangling references.

DimensionReasoningScore

Conciseness

Lean tables and terse executable snippets with no padding or explanations of concepts Claude already knows; every token earns its place.

3 / 3

Actionability

Provides copy-paste-ready JSON config, an executable bash hook script with documented exit codes, matcher patterns, and concrete debug commands.

3 / 3

Workflow Clarity

Steps are present (configure, write script, test) and a Security Checklist exists, but there is no explicit validate-then-fix-retry feedback loop for the risky deny/block operations.

2 / 3

Progressive Disclosure

Content is well-organized with clearly signaled one-level references, but the referenced ./references/*.md files do not exist on disk, so the structure cannot be fully verified.

2 / 3

Total

10

/

12

Passed

Description

82%

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 strong, specific description with good trigger-term coverage and clear distinctiveness. Its main weakness is the absence of an explicit "Use when..." usage clause, capping completeness at 2.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when configuring Claude Code hook scripts for pre/post tool validation, audit logging, or permission gating."

Include natural user-facing variations like "Claude Code hooks" or "automate tool execution" alongside the technical trigger terms.

DimensionReasoningScore

Specificity

"hook system for pre/post tool execution" plus "tool validation, audit logging" lists multiple concrete, specific actions rather than vague language.

3 / 3

Completeness

It states what the skill does and offers an explicit trigger list, but lacks a canonical "Use when..." clause, which the guidelines cap at 2.

2 / 3

Trigger Term Quality

"hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging" are natural terms a user would actually say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

The Claude Code hooks niche with distinct triggers (PreToolUse, PostToolUse) is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
NeverSight/skills_feed
Reviewed

Table of Contents

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.