Enhanced skill navigator that maps conversation history

Scout pro

by OneWave-AI · MIT license · ★ 306 on GitHub

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.

---
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

Overview

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.

Manual install (npx, ZIP)

Claude Codenpx skills add OneWave-AI/claude-skills --skill scout-pro -g -a claude-code

Claude Code (degit)npx degit OneWave-AI/claude-skills/scout-pro#main ~/.claude/skills/scout-pro

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.9 KB

Read SKILL.md here

OneWave-AI/main1 file shown

SKILL.md2.9 KB

Browse every file on GitHub↗

SKILL.md

Show the full text38 lines

scout-pro/SKILL.md38 lines · 2.9 KB

PreviewCode

Outline

RawView on GitHub

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.

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

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.
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.
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.
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.
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.
Recommend proactively. Surface valuable unsolicited suggestions grounded in observed patterns.
Respond. Emit the analysis using the structure in references/response-format.md.

Rules

Never recommend a skill without verifying it exists; scan the directory first, every run.
Always explain the "why" behind a recommendation. Do not just list skills.
Prefer chains over individual skills when the task has multiple steps.
Respect the user's time. If a one-skill solution works, do not recommend a five-skill chain.
Be honest about limitations. If no skill is a great fit, say so.
Update the usage log on every recommendation.
Do not hallucinate skills. Only recommend skills that exist in the directory or as known slash commands.

1	---
2	name: scout-pro
3	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.
4	tools: Read, Glob, Grep, WebFetch, WebSearch
5	model: inherit
6	---
7
8	# Scout Pro
9
10	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.
11
12	## Contents
13
14	- references/skill-inventory.md - how to scan the skills directory and the category snapshot
15	- references/chains.md - chain design principles, notation, library, and custom-chain builder
16	- references/patterns-and-logging.md - pattern recognition, usage log schema, learning, proactive tips
17	- references/response-format.md - required response structure, context templates, edge cases, carryover
18
19	## Workflow
20
21	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.
22	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.
23	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.
24	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.
25	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.
26	6. Recommend proactively. Surface valuable unsolicited suggestions grounded in observed patterns.
27	7. Respond. Emit the analysis using the structure in references/response-format.md.
28
29	## Rules
30
31	1. Never recommend a skill without verifying it exists; scan the directory first, every run.
32	2. Always explain the "why" behind a recommendation. Do not just list skills.
33	3. Prefer chains over individual skills when the task has multiple steps.
34	4. Respect the user's time. If a one-skill solution works, do not recommend a five-skill chain.
35	5. Be honest about limitations. If no skill is a great fit, say so.
36	6. Update the usage log on every recommendation.
37	7. Do not hallucinate skills. Only recommend skills that exist in the directory or as known slash commands.
38