agent-tools
Reference for configuring tool permissions when launching Claude Code agents. Use when setting up --allowedTools flags, restricting file access, or configuring agent permissions.
96
95%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 well-crafted description that clearly identifies its niche (Claude Code agent permissions) and provides explicit 'Use when' triggers. The main weakness is that the capability description could be more specific about what actions the skill enables beyond 'configuring' - listing concrete operations would strengthen it further.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (tool permissions, Claude Code agents) and some actions (configuring, setting up flags, restricting access), but doesn't list comprehensive specific actions like 'whitelist specific tools', 'deny network access', or 'scope file permissions to directories'. | 2 / 3 |
Completeness | Clearly answers both what ('Reference for configuring tool permissions when launching Claude Code agents') and when ('Use when setting up --allowedTools flags, restricting file access, or configuring agent permissions') with explicit trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: '--allowedTools', 'flags', 'file access', 'agent permissions', 'Claude Code agents'. These are terms a developer would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Claude Code agent permissions with distinct triggers like '--allowedTools flags' that are unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
Excellent reference skill that maximizes information density through effective use of tables, concrete examples, and logical organization. The content is immediately actionable with copy-paste ready commands and covers edge cases (security notes, pattern matching behavior) without verbosity. The progression from tool listing to restrictions to complete examples serves both quick lookup and learning use cases.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely efficient use of tokens. Uses tables for dense information, no unnecessary explanations of what tools do beyond brief descriptions, and assumes Claude understands CLI syntax and patterns. | 3 / 3 |
Actionability | Fully executable examples throughout with copy-paste ready CLI commands. Every pattern is demonstrated with concrete syntax and real-world use cases like Django and React agents. | 3 / 3 |
Workflow Clarity | This is a reference skill, not a multi-step workflow. The single task (configuring tool permissions) is unambiguous with clear syntax patterns, tables showing what matches vs doesn't match, and security notes for edge cases. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from basic (Available Tools) to specific (Path Restrictions, Bash Restrictions) to practical (Recommended Configurations, Complete Examples). Quick Reference table at end enables fast lookup. | 3 / 3 |
Total | 12 / 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
- jpoutrin/product-forge
- Commit
0ebe7ae
- 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.