Tool Advisor
Discovers your full tool environment and amplifies prompts with capability awareness. Suggests optimal tool compositions as non-binding options. Use when the user asks "what tools should I use", "best approach for this task", "how should I tackle", or explicitly mentions tool-advisor / $tool-advisor / ta. Do NOT trigger for direct coding requests, explanations, or reviews without tool-selection intent.
Install
/plugin marketplace add dragon1086/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add dragon1086/claude-skills --skill tool-advisorgit clone --depth 1 https://github.com/dragon1086/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/.agents/skills/tool-advisor ~/.claude/skills/tool-advisorPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Tool Advisor v3.4 — Cross-Agent Amplifier + Optional Composer You are a **Tool Amplifier**: DISCOVER what the user has, DELIVER enriched context, SUGGEST tool compositions as options. You arm the model with knowledge — you never replace its judgment. --- ## Iron Rules 1. **NEVER execute mutating actions.** No edits, commits, installs, or task executors. Read-only scans (Phase 1) are permitted. You scan and advise. 2. **Complete ALL 6 phases.** Each produces visible output or "N/A — [reason]". No skipping. 3. **MUST end with Quick Action table.** Copy-paste first steps. No exceptions. 4. **No internal deliberation in output.** Reason internally, present conclusions only. 5. **Follow the output template literally.** Small=collapsed (<10 lines). Medium+=full. Every section appears or gets "N/A". 6. **STOP after template output.** The template IS your deliverable. Do not execute any approach. 7. **Scale output to task complexity.** Don't over-engineer a typo fix. 8. **Max 3 questions, one message.** If unknowns exist, ask once then proceed with sensible defaults. 9. **Human-in-the-loop for installs.** Never auto-install anything. --- ## Phase 1: Discover Environment ### Layer 1 — Native Tools (enumerate, don't scan) - **File/Search**: Read, Write, Edit, Glob, Grep (or equivalent agent-native tools) - **Execution**: shell/terminal execution tools - **Web**: web search/fetch tools (if available) - **Agent**: subagent/delegation tools (if available)
Details
- Skill name
tool-advisor- Repository
- dragon1086/claude-skills
- Path
.agents/skills/tool-advisor/SKILL.md- License
- MIT
- Repo updated
- 23 April 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Tool Advisor skill do?
Discovers your full tool environment and amplifies prompts with capability awareness. Suggests optimal tool compositions as non-binding options. Use when the user asks "what tools should I use", "best approach for this task", "how should I tackle", or explicitly mentions tool-advisor / $tool-advisor / ta. Do NOT trigger for direct coding requests, explanations, or reviews without tool-selection intent.
How do I install the Tool Advisor skill?
Claude Code plugin: /plugin marketplace add dragon1086/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Tool Advisor popular?
It lives in dragon1086/claude-skills, which has 12 GitHub stars and 4 forks, and is included in 1 curated skill list.
Related skills
Twitter Workflow
430xranx/agentbrief
When the user wants to draft tweets, plan threads, post to Twitter/X, or manage their Twitter presence
Todo Discipline
48frankxai/claude-skills-library
Use when starting any complex task (3+ steps) or before declaring work complete. Enforces todo/task state to match reality — merge updates + read verification. Prevents false completion.
Verification
430xranx/agentbrief
Enforce evidence-based verification before claiming any task is complete
Review Process
430xranx/agentbrief
Step-by-step workflow for conducting thorough code reviews
Worker Integration
48frankxai/claude-skills-library
Worker–agent integration for intelligent task dispatch and performance tracking. Use when wiring agents to a worker pool, routing tasks to workers, or instrumenting worker performance.
Release Notes
430xranx/agentbrief
When the user needs to write release notes, changelogs, or document what changed in a release. Use when the user says 'write release notes,' 'changelog,' 'what changed,' 'document this release,' 'update the README after launch,' or after completing a significant feature or version bump.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.