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.
80
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/setperms/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies its niche (Claude Code tool permissions), provides explicit trigger terms, and answers both what and when. The main weakness is that the capability description could be more specific about the concrete actions performed (e.g., editing settings.json, creating permission rules), but overall it is well-constructed for skill selection.
Suggestions
Add more specific concrete actions like 'edit .claude/settings.json', 'define allowed/denied shell commands', or 'configure MCP tool permissions' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (tool permissions for Claude Code) and some actions (configures allowed commands, rules, preferences), but doesn't list specific concrete actions like 'create allowlist files', 'define MCP tool permissions', or 'set up .claude/settings.json'. | 2 / 3 |
Completeness | Clearly answers both 'what' (set tool permissions, configure allowed commands/rules/preferences in .claude/ directory) and 'when' (explicit 'Triggers on:' clause with multiple trigger terms), satisfying the requirement for explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger terms that users would actually say: 'setperms', 'init tools', 'configure permissions', 'setup project', 'set permissions', 'init claude'. These cover common variations of how users would request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — Claude Code tool permissions and .claude/ directory configuration. The trigger terms are distinct and unlikely to conflict with general coding, configuration, or permissions skills outside the Claude Code context. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 a clear workflow and good validation checkpoints, but suffers significantly from verbosity. The same tool information is repeated three times: in the 'What This Does' overview, in the JSON permissions blob, and in the rules markdown file. The inline templates are necessary for execution but the duplicative overview section and extensive explanatory tables waste tokens.
Suggestions
Remove the 'What This Does' tool listing section entirely — the tools are already fully documented in the JSON permissions and rules file templates that follow.
Consider moving the large JSON and markdown templates to separate reference files (e.g., templates/settings.json and templates/cli-tools.md) and referencing them from the main skill.
The rules file content (~100 lines of markdown tables) could be stored as a separate template file rather than inline, significantly reducing the skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. The massive JSON blob and extensive markdown tables for the rules file could be written directly without being displayed inline. The tool lists in 'What This Does' duplicate information that appears again in the permissions JSON and again in the rules file. Much of this content is redundant repetition across three different representations of the same information. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready content: exact JSON for settings.local.json, exact markdown for the rules file, specific bash commands for directory creation and file checking, and a clear confirmation message template. Every step has concrete, executable guidance. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with an explicit execution flow diagram. Step 1 includes validation (check for existing files) with a decision point (overwrite vs skip). The process handles the destructive case of overwriting existing config by asking the user first. The --force flag option is also documented. | 3 / 3 |
Progressive Disclosure | The skill dumps everything inline in one massive file rather than splitting the JSON and markdown templates into separate reference files. The options section and full template additions are reasonably organized, but the enormous inline JSON and markdown content that Claude will write to files bloats the main skill unnecessarily. These templates could be referenced from separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
c50d4b5
- 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.