Communitygithub.com

OneWave-AI/claude-skills

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.

Qu'est-ce que claude-skills ?

claude-skills is a Claude Code agent skill that 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.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/OneWave-AI/claude-skills/tree/HEAD/scout-pro
Voir l'original→Voir toutes les compétences

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

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.

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

OneWave-AI/claude-skills

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

OneWave-AI/claude-skills

Generate animated videos and motion graphics from natural language descriptions. Creates a standalone Vite + React project with Framer Motion scenes that auto-play in the browser. Use when the user wants to create animations, motion graphics, video intros, animated presentations, or product demos.

OneWave-AI/claude-skills

Post-mortem analysis when a client churns. Takes client history, engagement data, support tickets, usage logs, and exit feedback to produce a comprehensive churn autopsy with root cause classification, timeline of decline, and preventive measures.

OneWave-AI/claude-skills

Assemble 2-3 complementary experts to collaboratively analyze anything. Experts work together to explore topics from multiple expert angles.

OneWave-AI/claude-skills

Convert any topic into playable browser games. Types: trivia, matching, word puzzles, adventure games. Uses Phaser.js or Kaboom.js.

OneWave-AI/claude-skills

Audit a codebase for LLM calls that are really classifications in disguise, then produce a costed swap plan for a System One model. Use when asked to cut AI inference cost or latency, when scoping a performance engagement for a client, when reviewing an agent loop that feels slow, or when asked "where could we use Jev here". Produces a ranked table of candidates with measured latency and dollar deltas.

OneWave-AI/claude-skills

Build and run a labelled eval set for a System One model (Jev, Von, or any typed-decision config), then sweep criteria wordings and thresholds against it. Use when a Jev/Von classification is wrong or unreliable, when choosing between the hosted API and a local open model, when tuning noul thresholds, or before shipping any typed-decision feature. Produces an accuracy-by-wording matrix and a calibrated threshold.

OneWave-AI/claude-skills

Wire a System One model (Jev, or an open reproduction like Von) into a product feature — routing, guardrails, scoring, classification. Use when replacing an LLM call that returns a label rather than prose, when adding a typed decision to an agent loop, or when deciding between the hosted Jev API and a local open model. Covers question design, the eval-set-first workflow, threshold calibration, confidence gates, and the traps measured on real data.

OneWave-AI/claude-skills

Optimize landing pages for conversions, performance, and SEO. Use when improving landing pages, increasing conversions, or optimizing page performance.

OneWave-AI/claude-skills

TAM/SAM/SOM calculator with deep market research. Produces comprehensive market-sizing.md with top-down and bottom-up estimates, methodology, data sources, assumptions, sensitivity ranges, growth projections, competitive landscape, and Mermaid visualizations. Use when user needs market size estimates, addressable market analysis, go-to-market sizing, investor-ready market analysis, or business plan market validation.

OneWave-AI/claude-skills

Create multiple choice, true/false, fill-in-blank, matching quizzes. Auto-generate plausible distractors. Instant grading with explanations.

OneWave-AI/claude-skills

Analyzes current conversation context to recommend the best skills and subagents for the task at hand. Use proactively when unsure which tool, skill, or agent to use.

OneWave-AI/claude-skills

Agent skill at social-repurposer/SKILL.md

Skills associés

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

community

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

community