scout-pro — Claude Code skill: what it does, how to install
scout-pro scans conversation history, verifies installed tools, and builds multi-skill chains tailored to your current development task.
MIT 244 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill scout-pro -a claude-codeWhat scout-pro does
The skill acts as an orchestrator for local tools. It reads manifests across ~/.claude/skills/, .claude/skills/, and active plugin directories using Read and Glob before suggesting any workflow.
Instead of pointing to single actions, it links multiple tools into sequential chains where each step feeds the next. It checks recurring patterns in ~/.claude/rules/session-context.md and workspace memory in ~/.claude/projects/ to spot underused tooling or blockers.
Recommendations and reported outcomes get recorded in ~/.claude/scout-pro-usage-log.json. A strict rule prevents recommending missing tools, so the agent stays silent if matching skills are not found on disk.
What it helps with
- orchestrate multi-step skill workflows for complex tasks
- identify underutilized tools across installed project skills
- log successful skill runs into
scout-pro-usage-log.json - detect recurring patterns and blockers across past sessions
Example prompts for the agent
- Analyze our conversation and suggest a multi-skill workflow for this task
- Check installed skills and build a chain to handle testing and deployment
- Review scout-pro-usage-log.json to see which workflows succeeded previously
How to install scout-pro
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill scout-pro -a claude-code2Manually: put the files in place
~/.claude/skills/scout-pro/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/scout-pro/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill scout-pro -a codex2Manually: put the files in place
.agents/skills/scout-pro/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill scout-pro -a cursor2Manually: put the files in place
.cursor/skills/scout-pro/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills scout-pro2Manually: put the files in place
.github/skills/scout-pro/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill scout-pro -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path scout-proManually: put the files in place
.devin/skills/scout-pro/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill scout-pro -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about scout-pro
How do I install scout-pro in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill scout-pro -a claude-code in your terminal.
What does scout-pro do?
It inspects conversation context, scans your local skill folders, and suggests multi-skill chains with clear rationales.
Where does scout-pro track workflow outcomes?
It reads and updates ~/.claude/scout-pro-usage-log.json while taking history from ~/.claude/rules/session-context.md.
Source text
SKILL.md · MIT
--- name: scout-pro description: Enhanced skill navigator that maps conversation history, recommends multi-skill chains, identifies patterns from past usage, and learns from session outcomes. Goes beyond basic scout with deep context analysis and workflow orchestration. tools: Read, Glob, Grep, WebFetch, WebSearch model: inherit --- # Scout Pro Advanced meta-agent that analyzes full conversation context, maps working patterns, recommends multi-skill workflows (not just single skills), and maintains a learning log of what works. ## Contents - references/skill-inventory.md - how to scan the skills directory and the category snapshot - references/chains.md - chain design principles, notation, library, and custom-chain builder - references/patterns-and-logging.md - pattern recognition, usage log schema, learning, proactive tips - references/response-format.md - required response structure, context templates, edge cases, carryover ## Workflow 1. **Deep context scan.** Read the full conversation from start to current message. Identify the primary goal, sub-goals, dependencies, blockers, and past attempts. Check session history in `~/.claude/`. Use the context template in references/response-format.md. 2. **Inventory skills.** Scan the installed skills directories (`~/.claude/skills/` for personal skills, `.claude/skills/` in the current project, and any plugin skill folders) and read each SKILL.md frontmatter. Never recommend a skill without verifying it exists. See references/skill-inventory.md. 3. **Design chains.** Where the task has multiple steps, design a multi-skill workflow so each step feeds the next. Use the notation, library, and builder protocol in references/chains.md. 4. **Recognize patterns.** Read `~/.claude/rules/session-context.md` and `~/.claude/projects/` memory. Detect recurring tasks, workflow gaps, and underutilized skills. See references/patterns-and-logging.md. 5. **Log usage.** Read the existing log at `~/.claude/scout-pro-usage-log.json`, factor past outcomes into current recommendations, then append the new recommendation. Update entries when the user reports an outcome. See references/patterns-and-logging.md. 6. **Recommend proactively.** Surface valuable unsolicited suggestions grounded in observed patterns. 7. **Respond.** Emit the analysis using the structure in references/response-format.md. ## Rules 1. Never recommend a skill without verifying it exists; scan the directory first, every run. 2. Always explain the "why" behind a recommendation. Do not just list skills. 3. Prefer chains over individual skills when the task has multiple steps. 4. Respect the user's time. If a one-skill solution works, do not recommend a five-skill chain. 5. Be honest about limitations. If no skill is a great fit, say so. 6. Update the usage log on every recommendation. 7. Do not hallucinate skills. Only recommend skills that exist in the directory or as known slash commands.
© OneWave-AI · MIT · OneWave-AI/claude-skills