CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

Highly actionable with copy-paste-ready config and clear step sequencing, but it is a verbose inline monolith that bloats the context with tool-preference knowledge Claude largely already has and lacks a progressive-disclosure structure or post-write validation.

Suggestions

Move the full settings.local.json permission list and the rules/cli-tools.md markdown into separate bundled reference files (e.g. references/permissions.json, references/cli-tools.md) and link to them one level deep, keeping only the install steps inline.

Add a validation checkpoint after writing the files (e.g. parse the JSON with jq to confirm validity, confirm both files exist) before the final 'Confirm' step, since this skill performs project-wide config writes.

Trim the explanatory 'Instead of / Use / Why' tool-preference tables to only the non-obvious choices; Claude already knows most of these tool replacements, so the verbose tables add context cost without proportional value.

DimensionReasoningScore

Conciseness

The body is a ~320-line monolith that exhaustively enumerates ~51 permissions and a large replacement-tool table, much of which restates tool knowledge Claude already has and could live in a separate reference file.

1 / 3

Actionability

Provides fully copy-paste-ready, executable artifacts: the complete settings.local.json block, the rules/cli-tools.md markdown, and concrete bash commands for each step.

3 / 3

Workflow Clarity

Steps are numbered and sequenced, but the only validation checkpoint (the 'Check for existing settings' ask-to-overwrite branch) is minimal; there is no verification that the JSON/markdown was written validly before the confirm step.

2 / 3

Progressive Disclosure

No bundle files exist and the entire permissions JSON and rules markdown are inlined verbatim; there is no one-level-deep reference structure or navigation to split this large content out.

1 / 3

Total

7

/

12

Passed

Description

92%

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 specific, trigger-rich description with an explicit 'Triggers on' clause that satisfies both the what and when. Its broadest triggers ('setup project', 'init claude') create some overlap with general project-init skills, slightly raising conflict risk.

DimensionReasoningScore

Specificity

Names concrete actions ('Configures allowed commands, rules, and preferences in .claude/ directory') and the target artifact, listing multiple specific operations rather than vague abstractions.

3 / 3

Completeness

Clearly answers both 'what' (configures allowed commands, rules, preferences in .claude/) and 'when' via an explicit 'Triggers on:' clause, which the rubric treats as an equivalent of a 'Use when...' trigger.

3 / 3

Trigger Term Quality

Includes natural trigger phrases users would actually say ('setperms', 'configure permissions', 'setup project', 'set permissions', 'init claude') with good coverage of phrasing variations.

3 / 3

Distinctiveness Conflict Risk

The 'setup project' and 'init claude'/'init tools' triggers are broad enough to overlap with other project-initialization skills, so it could fire for the wrong skill despite its permission focus.

2 / 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.