setperms

Set tool permissions for Claude Code. Configures allowed commands, rules, and preferences in .claude/ directory. Triggers on: setperms, init tools, configure permissions, setup project, set permissions, init claude.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/setperms/SKILL.md

Quality

Content

65%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 skill is highly actionable with complete, executable artifacts, but it is verbose and inlines large configuration blocks that would better live in separate reference files. Workflow sequencing is clear but missing explicit validation for destructive writes.

Suggestions

Move the full settings.local.json and rules/cli-tools.md content into bundled reference files (e.g. references/permissions.json, references/cli-tools.md) and reference them from SKILL.md to improve progressive disclosure and token efficiency.

Add an explicit validation checkpoint after writing settings.local.json (e.g. parse the JSON to confirm validity) before reporting success, since overwriting project config is destructive.

Trim the duplicate tool listings between the 'What This Does' section and the rules tables to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is largely a long dump of full permission lists and tables that Claude could derive, with some redundancy between the 'What This Does' tool list and the rules tables, so it is mostly efficient but could be tightened considerably.	3 / 5
Actionability	Provides fully copy-paste-ready JSON for settings.local.json and a complete rules markdown file, plus concrete bash commands for every step, covering the common cases completely.	5 / 5
Workflow Clarity	Steps are clearly sequenced and it checks for existing files before overwriting, but this destructive/batch write operation lacks an explicit validation checkpoint (e.g. JSON validity check) after writing, capping it at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Structure is reasonable with labeled sections, but the full permissions JSON and rules file are inlined entirely in SKILL.md rather than split into reference files, so content that should be separate remains inline with no bundle files present.	3 / 5
	Total	14 / 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, third-person, and includes an explicit trigger list that addresses both what and when, making it above-average quality. It would reach the top anchor with a cleaner 'Use when...' phrasing and tighter trigger terms.

Suggestions

Convert the 'Triggers on:' keyword list into a natural 'Use when the user wants to configure Claude Code permissions or set up project tooling.' sentence so the 'when' clause is explicit rather than stuffed.

Drop overly broad triggers like 'setup project' which could conflict with general project-setup skills, and keep terms tightly tied to permission configuration.

Avoid comma-separated keyword dumps; favor one or two concrete natural phrases users would actually say.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Configures allowed commands, rules, and preferences') but they are somewhat high-level relative to the actual skill scope, with minor gaps in coverage.	4 / 5
Completeness	States both what it does and when to use it via 'Triggers on', but the 'when' is keyword-stuffed rather than a cleanly explicit 'Use when...' clause, so it is not maximally explicit.	4 / 5
Trigger Term Quality	Provides a broad 'Triggers on' list of natural phrases (setperms, configure permissions, setup project) with good coverage, missing only a few synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	The setperms trigger and .claude/ scope give it a clear niche with minimal overlap risk against other skills, though 'setup project' is broad enough to risk minor overlap.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/setperms/SKILL.md
Commit: 2f57aec

Reviewed: about 21 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.