permissions-manager
Configures Claude Code permissions via natural language for CLI tools (git, gcloud, aws, kubectl, maven, gradle, npm, docker), project types (Rust, Java, TypeScript, Python), and file patterns. Use when asked to "configure permissions", "enable git", "allow docker", "setup project permissions", "apply permission profile", or "make files editable". Auto-detects project types and researches unknown tools.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install SpillwaveSolutions/claude_permissions_skill/permissions-manager skilz install SpillwaveSolutions/claude_permissions_skill/permissions-manager --agent opencode skilz install SpillwaveSolutions/claude_permissions_skill/permissions-manager --agent codex skilz install SpillwaveSolutions/claude_permissions_skill/permissions-manager --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/SpillwaveSolutions/claude_permissions_skill cp -r claude_permissions_skill ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
automating-mail
by SpillwaveSolutionsAutomates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation",...
automating-reminders
by SpillwaveSolutionsAutomates Apple Reminders using JavaScript for Automation (JXA). Use when asked to "create reminders programmatically", "automate reminder lists", "JX...
mastering-postgresql
by SpillwaveSolutionsPostgreSQL development for Python with full-text search (tsvector, tsquery, BM25 via pg_search), vector similarity (pgvector with HNSW/IVFFlat), JSONB...
automating-contacts
by SpillwaveSolutionsAutomates macOS Contacts via JXA with AppleScript dictionary discovery. Use when asked to "automate contacts", "JXA contacts automation", "macOS addre...
Agentic Skill Details
- Owner
- SpillwaveSolutions (GitHub)
- Repository
- claude_permissions_skill
- Type
- Other
- Meta-Domain
- N/A
- Primary Domain
- N/A
- Market Score
- 96.0
Agent Skill Grade
A
Score: 96/100
Click to see breakdown
Score Breakdown
Areas to Improve
- At 544 lines, the CLI workflow is large for a single reference file; could benefit from internal TOC
- Four examples follow nearly identical structure; could be condensed with a template pattern
- Success criteria checklist exists but is buried; no quick-reference checklist at top
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/18/2026
Developer Feedback
I took a look at your claude_permissions_skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 96/100, solid A territory. This is based on Anthropic's skill best practices rubric. Your strongest areas are spec compliance (14/15) and the layered architecture - you've got a clean 3-tier setup that keeps things modular. The weakest area is utility (18/20), which is surprising given how practical this skill actually is. Turns out the grading system just wanted to see more template examples and feedback loops.
What's Working Well
- Progressive Disclosure is chef's kiss - You're saving 90%+ tokens with surgical grep/jq patterns and explicit token budgets per tier. The separation between SKILL.md, guides/workflows/, and references/ is exactly how this should be structured.
- The trigger phrases are solid - Eight of them covering different user intents ('enable git', 'setup project permissions', 'apply permission profile'). Makes the skill actually discoverable.
- Comprehensive CLI tool routing - Handling 20+ CLI tools with read/write modes and automatic safety rules is no joke. Most permission managers don't think about constraint levels (minimal/standard/strict).
- Smart backup-before-write pattern - You're validating configurations and backing things up. That's the kind of defensive UX that builds trust.
The Big One: Missing Templates Hold Back Utility
Here's the thing - your skill solves a real problem, but you're only showing the happy path. The grading system dinged you 2 points on templates and feedback loops because developers need more than examples; they need patterns they can remix.
What to add:
Create a new file guides/templates/permission-rule-templates.md with copy-paste patterns:
- Safe read-only rule template (git, npm, etc.)
- Write-only template (for build tools)
- Deny-list template (for sensitive patterns)
- Custom tool template (for unknown tools)
Keep each under 10 lines so devs actually use them. Reference this file from the CLI workflow - that's low lift, high impact. Should gain you +1-2 on the utility pillar.
Other Things Worth Fixing
CLI workflow needs a TOC - At 544 lines, the file is unwieldy. Add an internal table of contents at the top linking to major sections (Steps, Examples, Error Handling). Takes 10 minutes, fixes the navigation_signals gap. +1 point.
Condense the example redundancy - You've got four workflow examples that follow nearly identical step-by-step structures around line 249-341. Keep the diverse ones (known tool + unknown tool routing), reference a pattern for the others. Saves ~300 tokens and improves readability. +1 point on writing style.
Add a master checklist to SKILL.md - Right now success criteria are buried in section 8. Drop a condensed 4-item checklist in the Quick Reference (backup → validate → apply → restart). Helps developers actually use it faster.
Quick Wins
- Biggest bang for buck: Add permission-rule-templates.md → +1-2 utility points
- Easy cleanup: TOC in cli-tool-workflow.md → +1 point
- UX boost: Master checklist in SKILL.md quick ref → +1 point
- All three together? You're looking at 99-100/100.
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that installs skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
AI-Detected Topics
Extracted using NLP analysis
Report Security Issue
Found a security vulnerability in this agent skill?