ac-hooks-manager

Hook installation and management for autonomous coding. Use when setting up Stop hooks, managing pre/post tool hooks, or configuring autonomous continuation.

Quality

71%

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/ac-hooks-manager/SKILL.md

Quality

Content

60%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 actionable and well-sequenced with real safety checkpoints for autonomous operation, but it is hurt by redundancy (diagram vs. How It Works, repeated safety snippets) and especially by broken bundle references — most cited reference and script files do not exist while their content is inlined.

Suggestions

Create the referenced bundle files (references/HOOK-MECHANICS.md, STOP-HOOK.md, SAFETY.md and scripts/autonomous-loop.sh, analyze.py, hook_installer.py, validate.sh) or remove the dangling references, so navigation is not broken.

Move the full autonomous-loop.sh listing and the duplicated Safety Mechanisms snippets into references/SAFETY.md (or STOP-HOOK.md) and keep SKILL.md as a concise overview, eliminating the inline duplication.

Collapse the ASCII diagram and the 'How It Works' numbered list into one representation to remove the conciseness redundancy.

Dimension	Reasoning	Score
Conciseness	Mostly code-and-structure rather than concept fluff (no 'what is a hook' padding), but the ASCII diagram and 'How It Works' overlap, and the Safety Mechanisms section re-shows snippets already present in the inlined autonomous-loop.sh — content that could be tightened.	3 / 5
Actionability	Provides concrete, mostly copy-paste-ready Python calls, bash, and JSON config covering common install/status/remove/validate cases; minor gaps because several referenced scripts (analyze.py, validate.sh, autonomous-loop.sh) are shown illustratively rather than as runnable bundled files.	4 / 5
Workflow Clarity	The Stop-hook flow is clearly sequenced (diagram plus numbered 'How It Works') with explicit safety checkpoints (doom-loop guard, iteration/cost limits, failure detection); the install/remove/validate operations are listed as separate ops rather than one validated workflow, a minor gap.	4 / 5
Progressive Disclosure	A References section signals one-level-deep files (HOOK-MECHANICS.md, STOP-HOOK.md, SAFETY.md) and scripts (analyze.py, autonomous-loop.sh, hook_installer.py, validate.sh), but only scripts/hooks_manager.py actually exists — references are broken, and the full autonomous-loop.sh and safety details that belong in those files are inlined in SKILL.md.	2 / 5
	Total	13 / 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 strong description that clearly states both capability and use-conditions with concrete, natural trigger phrases. It is specific and well-targeted to a distinct niche, with only minor coverage and synonym gaps.

Dimension	Reasoning	Score
Specificity	Names the domain ('Hook installation and management for autonomous coding') and lists several concrete actions — 'setting up Stop hooks, managing pre/post tool hooks, or configuring autonomous continuation' — with only minor gaps (e.g., session hooks, removal) keeping it just below fully comprehensive.	4 / 5
Completeness	Explicitly answers both what ('Hook installation and management for autonomous coding') and when ('Use when setting up Stop hooks, managing pre/post tool hooks, or configuring autonomous continuation') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('setting up Stop hooks', 'configure hooks', 'install hooks') plus domain terms ('pre/post tool hooks', 'autonomous continuation'); good coverage but missing common synonyms/variants.	4 / 5
Distinctiveness Conflict Risk	The autonomous-coding hook niche with Stop/pre-post tool hook triggers is mostly distinct; only minor overlap risk with general Claude Code configuration skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/ac-hooks-manager/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.