CtrlK
BlogDocsLog inGet started
Tessl Logo

hooks-manager

Create, validate, and deploy Claude Code hooks for workflow automation. Hooks enable event-driven automation at 8 lifecycle points (PreToolUse, PostToolUse, UserPromptSubmit, etc.) with structured JSON control. Use when automating code formatting, security gates, observability integration, validation enforcement, or any event-driven workflow automation in Claude Code.

59

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/hooks-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 rich with executable, actionable hook examples organized into clear operations, but it is bloated by heavy cross-section duplication and fails progressive disclosure entirely as a monolithic file with a dangling reference. Invented management commands and checklist-only validation prevent the actionability and workflow dimensions from reaching the top.

Suggestions

Split the monolithic body into bundle files (e.g., templates/, references/hook-events.md, references/structured-json.md) and turn SKILL.md into a concise overview that links one level deep, fixing the dangling 'see examples/' reference.

De-duplicate the PostToolUse formatting hook and the 8-event listing so each appears once (detail in an appendix/reference, summary in the body), cutting hundreds of redundant lines.

Replace the invented 'deploy-hook'/'validate-hook' commands with real, executable equivalents (e.g., plain cp/mv into ~/.claude/hooks and jq-based validation), and add explicit validate->fix->retry loops to the destructive/batch operations.

DimensionReasoningScore

Conciseness

The ~1035-line body is noticeably verbose with substantial duplication: the 8 hook events are restated in the Overview, Appendix A, and Quick Reference table, and the PostToolUse formatting hook JSON recurs across Operation 1, Template 1, Pattern 1, and the Quick Reference. This is padded redundancy, not lean efficiency; not a 1 because most content is concrete rather than concept-explaining filler.

2 / 5

Actionability

Provides mostly executable guidance with real bash scripts (security-check.sh, validate-json.sh, session-init.sh) and JSON configs, but references invented commands ("deploy-hook --global", "validate-hook formatting-hook.json") that do not exist as standard tooling, leaving minor gaps; not a 5 because of those non-functional commands.

4 / 5

Workflow Clarity

Each operation is a clearly numbered sequence with a Validation checklist and troubleshooting guidance, so most checkpoints are present; not a 5 because validation is checklist-style rather than explicit validate->fix->retry feedback loops, and the validate-hook step relies on a non-existent command.

4 / 5

Progressive Disclosure

This is a monolithic single-file manual with no bundle files (references/, scripts/, assets/, examples/ all absent) inlining templates, event reference, and structured-JSON appendices that clearly belong in separate files, and its one cross-reference ("For templates, see examples/") points to a non-existent directory; not a 1 only because internal section headers provide some structure.

2 / 5

Total

12

/

20

Passed

Description

87%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 strong description that clearly states what the skill does and when to use it, anchored to a distinctive Claude Code hooks niche with concrete trigger terms. Slightly generic action verbs and missing synonyms keep specificity and trigger quality just below the top anchor.

DimensionReasoningScore

Specificity

Lists concrete actions ("Create, validate, and deploy Claude Code hooks") plus 8 named lifecycle points (PreToolUse, PostToolUse, UserPromptSubmit), giving several specific actions with only minor coverage gaps; not a 5 because the verbs are somewhat generic compared to fully concrete capability lists.

4 / 5

Completeness

Explicitly answers both what ("Create, validate, and deploy Claude Code hooks... structured JSON control") and when ("Use when automating code formatting, security gates...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases a user would say appear ("code formatting", "security gates", "observability integration", "validation enforcement", "workflow automation"), giving good keyword coverage; not a 5 because synonyms and extension-style variants are absent.

4 / 5

Distinctiveness Conflict Risk

The Claude Code hooks niche with named lifecycle events (PreToolUse, PostToolUse) and structured JSON control is a clear, distinct trigger space with minimal overlap risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1036 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

14

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.